diff options
Diffstat (limited to 'tools/perf')
505 files changed, 39041 insertions, 9675 deletions
diff --git a/tools/perf/Build b/tools/perf/Build index 3e486f7df94b..06107f1e1d42 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -65,14 +65,40 @@ gtk-y += ui/gtk/ ifdef SHELLCHECK SHELL_TESTS := $(wildcard *.sh) - TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) + SHELL_TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) else SHELL_TESTS := - TEST_LOGS := + SHELL_TEST_LOGS := endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) $(Q)$(call echo-cmd,test)shellcheck -s bash -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) -perf-y += $(TEST_LOGS) +perf-y += $(SHELL_TEST_LOGS) + +ifdef MYPY + PY_TESTS := $(shell find python -type f -name '*.py') + MYPY_TEST_LOGS := $(PY_TESTS:python/%=python/%.mypy_log) +else + MYPY_TEST_LOGS := +endif + +$(OUTPUT)%.mypy_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false) + +perf-y += $(MYPY_TEST_LOGS) + +ifdef PYLINT + PY_TESTS := $(shell find python -type f -name '*.py') + PYLINT_TEST_LOGS := $(PY_TESTS:python/%=python/%.pylint_log) +else + PYLINT_TEST_LOGS := +endif + +$(OUTPUT)%.pylint_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false) + +perf-y += $(PYLINT_TEST_LOGS) diff --git a/tools/perf/Documentation/callchain-overhead-calculation.txt b/tools/perf/Documentation/callchain-overhead-calculation.txt index 1a757927195e..e0202bf5bd1a 100644 --- a/tools/perf/Documentation/callchain-overhead-calculation.txt +++ b/tools/perf/Documentation/callchain-overhead-calculation.txt @@ -1,7 +1,8 @@ Overhead calculation -------------------- -The overhead can be shown in two columns as 'Children' and 'Self' when -perf collects callchains. The 'self' overhead is simply calculated by +The CPU overhead can be shown in two columns as 'Children' and 'Self' +when perf collects callchains (and corresponding 'Wall' columns for +wall-clock overhead). The 'self' overhead is simply calculated by adding all period values of the entry - usually a function (symbol). This is the value that perf shows traditionally and sum of all the 'self' overhead values should be 100%. diff --git a/tools/perf/Documentation/cpu-and-latency-overheads.txt b/tools/perf/Documentation/cpu-and-latency-overheads.txt new file mode 100644 index 000000000000..3b6d63705465 --- /dev/null +++ b/tools/perf/Documentation/cpu-and-latency-overheads.txt @@ -0,0 +1,85 @@ +CPU and latency overheads +------------------------- +There are two notions of time: wall-clock time and CPU time. +For a single-threaded program, or a program running on a single-core machine, +these notions are the same. However, for a multi-threaded/multi-process program +running on a multi-core machine, these notions are significantly different. +Each second of wall-clock time we have number-of-cores seconds of CPU time. +Perf can measure overhead for both of these times (shown in 'overhead' and +'latency' columns for CPU and wall-clock time correspondingly). + +Optimizing CPU overhead is useful to improve 'throughput', while optimizing +latency overhead is useful to improve 'latency'. It's important to understand +which one is useful in a concrete situation at hand. For example, the former +may be useful to improve max throughput of a CI build server that runs on 100% +CPU utilization, while the latter may be useful to improve user-perceived +latency of a single interactive program build. +These overheads may be significantly different in some cases. For example, +consider a program that executes function 'foo' for 9 seconds with 1 thread, +and then executes function 'bar' for 1 second with 128 threads (consumes +128 seconds of CPU time). The CPU overhead is: 'foo' - 6.6%, 'bar' - 93.4%. +While the latency overhead is: 'foo' - 90%, 'bar' - 10%. If we try to optimize +running time of the program looking at the (wrong in this case) CPU overhead, +we would concentrate on the function 'bar', but it can yield only 10% running +time improvement at best. + +By default, perf shows only CPU overhead. To show latency overhead, use +'perf record --latency' and 'perf report': + +----------------------------------- +Overhead Latency Command + 93.88% 25.79% cc1 + 1.90% 39.87% gzip + 0.99% 10.16% dpkg-deb + 0.57% 1.00% as + 0.40% 0.46% sh +----------------------------------- + +To sort by latency overhead, use 'perf report --latency': + +----------------------------------- +Latency Overhead Command + 39.87% 1.90% gzip + 25.79% 93.88% cc1 + 10.16% 0.99% dpkg-deb + 4.17% 0.29% git + 2.81% 0.11% objtool +----------------------------------- + +To get insight into the difference between the overheads, you may check +parallelization histogram with '--sort=latency,parallelism,comm,symbol --hierarchy' +flags. It shows fraction of (wall-clock) time the workload utilizes different +numbers of cores ('Parallelism' column). For example, in the following case +the workload utilizes only 1 core most of the time, but also has some +highly-parallel phases, which explains significant difference between +CPU and wall-clock overheads: + +----------------------------------- + Latency Overhead Parallelism / Command / Symbol ++ 56.98% 2.29% 1 ++ 16.94% 1.36% 2 ++ 4.00% 20.13% 125 ++ 3.66% 18.25% 124 ++ 3.48% 17.66% 126 ++ 3.26% 0.39% 3 ++ 2.61% 12.93% 123 +----------------------------------- + +By expanding corresponding lines, you may see what commands/functions run +at the given parallelism level: + +----------------------------------- + Latency Overhead Parallelism / Command / Symbol +- 56.98% 2.29% 1 + 32.80% 1.32% gzip + 4.46% 0.18% cc1 + 2.81% 0.11% objtool + 2.43% 0.10% dpkg-source + 2.22% 0.09% ld + 2.10% 0.08% dpkg-genchanges +----------------------------------- + +To see the normal function-level profile for particular parallelism levels +(number of threads actively running on CPUs), you may use '--parallelism' +filter. For example, to see the profile only for low parallelism phases +of a workload use '--latency --parallelism=1-2' flags. diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt index e7a776ad25d7..0379903673a4 100644 --- a/tools/perf/Documentation/intel-hybrid.txt +++ b/tools/perf/Documentation/intel-hybrid.txt @@ -8,15 +8,15 @@ Part of events are available on core cpu, part of events are available on atom cpu and even part of events are available on both. Kernel exports two new cpu pmus via sysfs: -/sys/devices/cpu_core -/sys/devices/cpu_atom +/sys/bus/event_source/devices/cpu_core +/sys/bus/event_source/devices/cpu_atom The 'cpus' files are created under the directories. For example, -cat /sys/devices/cpu_core/cpus +cat /sys/bus/event_source/devices/cpu_core/cpus 0-15 -cat /sys/devices/cpu_atom/cpus +cat /sys/bus/event_source/devices/cpu_atom/cpus 16-23 It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus. @@ -60,8 +60,8 @@ can't carry pmu information. So now this type is extended to be PMU aware type. The PMU type ID is stored at attr.config[63:32]. PMU type ID is retrieved from sysfs. -/sys/devices/cpu_atom/type -/sys/devices/cpu_core/type +/sys/bus/event_source/devices/cpu_atom/type +/sys/bus/event_source/devices/cpu_core/type The new attr.config layout for PERF_TYPE_HARDWARE: diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 156c5f37b051..46090c5b42b4 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -168,6 +168,10 @@ include::itrace.txt[] --skip-empty:: Do not display empty (or dummy) events. +--code-with-type:: + Show data type info in code annotation (for memory instructions only). + Currently it only works with --stdio option. + SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index d0c65fad419a..8914f12d2b85 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -27,7 +27,7 @@ Don't print descriptions. -v:: --long-desc:: -Print longer event descriptions. +Print longer event descriptions and all similar PMUs with alphanumeric suffixes. --debug:: Enable debugging output. @@ -188,7 +188,7 @@ in the CPU vendor specific documentation. The available PMUs and their raw parameters can be listed with - ls /sys/devices/*/format + ls /sys/bus/event_source/devices/*/format For example the raw event "LSD.UOPS" core pmu event above could be specified as diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index d3793054f7d3..859dc11a7372 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -179,8 +179,9 @@ CONTENTION OPTIONS -o:: --lock-owner:: - Show lock contention stat by owners. Implies --threads and - requires --use-bpf. + Show lock contention stat by owners. This option can be combined with -t, + which shows owner's per thread lock stats, or -v, which shows owner's + stacktrace. Requires --use-bpf. -Y:: --type-filter=<value>:: diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 80686d590de2..c7fc1ba265e2 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -227,6 +227,10 @@ OPTIONS '--filter' exists, the new filter expression will be combined with them by '&&'. +--latency:: + Enable data collection for latency profiling. + Use perf report --latency for latency-centric profile. + -a:: --all-cpus:: System-wide collection from all CPUs (default if no target is specified). diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 87f864519406..3376c4710575 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -44,7 +44,7 @@ OPTIONS --comms=:: Only consider symbols in these comms. CSV that understands file://filename entries. This option will affect the percentage of - the overhead column. See --percentage for more info. + the overhead and latency columns. See --percentage for more info. --pid=:: Only show events for given process ID (comma separated list). @@ -54,12 +54,12 @@ OPTIONS --dsos=:: Only consider symbols in these dsos. CSV that understands file://filename entries. This option will affect the percentage of - the overhead column. See --percentage for more info. + the overhead and latency columns. See --percentage for more info. -S:: --symbols=:: Only consider these symbols. CSV that understands file://filename entries. This option will affect the percentage of - the overhead column. See --percentage for more info. + the overhead and latency columns. See --percentage for more info. --symbol-filter=:: Only show symbols that match (partially) with this filter. @@ -68,6 +68,21 @@ OPTIONS --hide-unresolved:: Only display entries resolved to a symbol. +--parallelism:: + Only consider these parallelism levels. Parallelism level is the number + of threads that actively run on CPUs at the time of sample. The flag + accepts single number, comma-separated list, and ranges (for example: + "1", "7,8", "1,64-128"). This is useful in understanding what a program + is doing during sequential/low-parallelism phases as compared to + high-parallelism phases. This option will affect the percentage of + the overhead and latency columns. See --percentage for more info. + Also see the `CPU and latency overheads' section for more details. + +--latency:: + Show latency-centric profile rather than the default + CPU-consumption-centric profile + (requires perf record --latency flag). + -s:: --sort=:: Sort histogram entries by given key(s) - multiple keys can be specified @@ -87,6 +102,7 @@ OPTIONS entries are displayed as "[other]". - cpu: cpu number the task ran at the time of sample - socket: processor socket number the task ran at the time of sample + - parallelism: number of running threads at the time of sample - srcline: filename and line number executed at the time of sample. The DWARF debugging info must be provided. - srcfile: file name of the source file of the samples. Requires dwarf @@ -97,12 +113,14 @@ OPTIONS - cgroup_id: ID derived from cgroup namespace device and inode numbers. - cgroup: cgroup pathname in the cgroupfs. - transaction: Transaction abort flags. - - overhead: Overhead percentage of sample - - overhead_sys: Overhead percentage of sample running in system mode - - overhead_us: Overhead percentage of sample running in user mode - - overhead_guest_sys: Overhead percentage of sample running in system mode + - overhead: CPU overhead percentage of sample. + - latency: latency (wall-clock) overhead percentage of sample. + See the `CPU and latency overheads' section for more details. + - overhead_sys: CPU overhead percentage of sample running in system mode + - overhead_us: CPU overhead percentage of sample running in user mode + - overhead_guest_sys: CPU overhead percentage of sample running in system mode on guest machine - - overhead_guest_us: Overhead percentage of sample running in user mode on + - overhead_guest_us: CPU overhead percentage of sample running in user mode on guest machine - sample: Number of sample - period: Raw number of event count of sample @@ -125,8 +143,8 @@ OPTIONS - weight2: Average value of event specific weight (2nd field of weight_struct). - weight3: Average value of event specific weight (3rd field of weight_struct). - By default, comm, dso and symbol keys are used. - (i.e. --sort comm,dso,symbol) + By default, overhead, comm, dso and symbol keys are used. + (i.e. --sort overhead,comm,dso,symbol). If --branch-stack option is used, following sort keys are also available: @@ -201,9 +219,9 @@ OPTIONS --fields=:: Specify output field - multiple keys can be specified in CSV format. Following fields are available: - overhead, overhead_sys, overhead_us, overhead_children, sample, period, - weight1, weight2, weight3, ins_lat, p_stage_cyc and retire_lat. The - last 3 names are alias for the corresponding weights. When the weight + overhead, latency, overhead_sys, overhead_us, overhead_children, sample, + period, weight1, weight2, weight3, ins_lat, p_stage_cyc and retire_lat. + The last 3 names are alias for the corresponding weights. When the weight fields are used, they will show the average value of the weight. Also it can contain any sort key(s). @@ -289,7 +307,7 @@ OPTIONS Accumulate callchain of children to parent entry so that then can show up in the output. The output will have a new "Children" column and will be sorted on the data. It requires callchains are recorded. - See the `overhead calculation' section for more details. Enabled by + See the `Overhead calculation' section for more details. Enabled by default, disable with --no-children. --max-stack:: @@ -442,9 +460,9 @@ OPTIONS --call-graph option for details. --percentage:: - Determine how to display the overhead percentage of filtered entries. - Filters can be applied by --comms, --dsos and/or --symbols options and - Zoom operations on the TUI (thread, dso, etc). + Determine how to display the CPU and latency overhead percentage + of filtered entries. Filters can be applied by --comms, --dsos, --symbols + and/or --parallelism options and Zoom operations on the TUI (thread, dso, etc). "relative" means it's relative to filtered entries only so that the sum of shown entries will be always 100%. "absolute" means it retains @@ -627,6 +645,8 @@ include::itrace.txt[] --skip-empty:: Do not print 0 results in the --stat output. +include::cpu-and-latency-overheads.txt[] + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index b72866ef270b..28bec7e78bc8 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -239,13 +239,22 @@ OPTIONS i.e., -F "" is not allowed. The brstack output includes branch related information with raw addresses using the - /v/v/v/v/cycles syntax in the following order: - FROM: branch source instruction - TO : branch target instruction - M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported - X/- : X=branch inside a transactional region, -=not in transaction region or not supported - A/- : A=TSX abort entry, -=not aborted region or not supported - cycles + FROM/TO/EVENT/INTX/ABORT/CYCLES/TYPE/SPEC syntax in the following order: + FROM : branch source instruction + TO : branch target instruction + EVENT : M=branch target or direction was mispredicted + P=branch target or direction was predicted + N=branch not-taken + -=no event or not supported + INTX : X=branch inside a transactional region + -=branch not in transaction region or not supported + ABORT : A=TSX abort entry + -=not aborted region or not supported + CYCLES: the number of cycles that have elapsed since the last branch was recorded + TYPE : branch type: COND/UNCOND/IND/CALL/IND_CALL/RET etc. + -=not supported + SPEC : branch speculation info: SPEC_WRONG_PATH/NON_SPEC_CORRECT_PATH/SPEC_CORRECT_PATH + -=not supported The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible. diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index fb3d2af33844..887dc37773d0 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -150,6 +150,10 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. To be used with -s or -S, to show stats for the errnos experienced by syscalls, using only this option will trigger --summary. +--summary-mode=mode:: + To be used with -s or -S, to select how to show summary. By default it'll + show the syscall summary by thread. Possible values are: thread, total. + --tool_stats:: Show tool stats such as number of times fd->pathname was discovered thru hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc. diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index 67b326ba0040..3fee9b2a88ea 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -62,3 +62,7 @@ To show context switches in perf report sample context add --switch-events to pe To show time in nanoseconds in record/report add --ns To compare hot regions in two workloads use perf record -b -o file ... ; perf diff --stream file1 file2 To compare scalability of two workload samples use perf diff -c ratio file1 file2 +For latency profiling, try: perf record/report --latency +For parallelism histogram, try: perf report --hierarchy --sort latency,parallelism,comm,symbol +To analyze particular parallelism levels, try: perf report --latency --parallelism=32-64 +To see how parallelism changes over time, try: perf report -F time,latency,parallelism --time-quantum=1s diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index a148ca9efca9..eea95c6c0c71 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -497,13 +497,14 @@ ifeq ($(feature-setns), 1) $(call detected,CONFIG_SETNS) endif +ifeq ($(feature-reallocarray), 0) + CFLAGS += -DCOMPAT_NEED_REALLOCARRAY +endif + ifdef CORESIGHT $(call feature_check,libopencsd) ifeq ($(feature-libopencsd), 1) CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS) - ifeq ($(feature-reallocarray), 0) - CFLAGS += -DCOMPAT_NEED_REALLOCARRAY - endif LDFLAGS += $(LIBOPENCSD_LDFLAGS) EXTLIBS += $(OPENCSDLIBS) $(call detected,CONFIG_LIBOPENCSD) @@ -820,7 +821,7 @@ else PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) - PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto% -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) @@ -1103,9 +1104,6 @@ ifndef NO_AUXTRACE ifndef NO_AUXTRACE $(call detected,CONFIG_AUXTRACE) CFLAGS += -DHAVE_AUXTRACE_SUPPORT - ifeq ($(feature-reallocarray), 0) - CFLAGS += -DCOMPAT_NEED_REALLOCARRAY - endif endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 05c083bb1122..979d4691221a 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -158,7 +158,7 @@ ifneq ($(OUTPUT),) VPATH += $(OUTPUT) export VPATH # create symlink to the original source -SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source) +SOURCE := $(shell ln -sfn $(srctree)/tools/perf $(OUTPUT)/source) endif # Do not use make's built-in rules @@ -248,7 +248,7 @@ else force_fixdep := $(config) endif -# Runs shellcheck on perf test shell scripts +# Runs shellcheck on perf shell scripts ifeq ($(NO_SHELLCHECK),1) SHELLCHECK := else @@ -265,8 +265,18 @@ ifneq ($(SHELLCHECK),) endif endif +# Runs mypy on perf python files +ifeq ($(MYPY),1) + MYPY := $(shell which mypy 2> /dev/null) +endif + +# Runs pylint on perf python files +ifeq ($(PYLINT),1) + PYLINT := $(shell which pylint 2> /dev/null) +endif + export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK -export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK +export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK MYPY PYLINT include $(srctree)/tools/build/Makefile.include @@ -298,7 +308,6 @@ ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump) FEATURE_TESTS := all endif endif -include $(srctree)/tools/perf/scripts/Makefile.syscalls include Makefile.config endif @@ -518,6 +527,14 @@ beauty_ioctl_outdir := $(beauty_outdir)/ioctl # Create output directory if not already present $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)') +syscall_array := $(beauty_outdir)/syscalltbl.c +syscall_tbl := $(srctree)/tools/perf/trace/beauty/syscalltbl.sh +syscall_tbl_data := $(srctree)/tools/scripts/syscall.tbl \ + $(wildcard $(srctree)/tools/perf/arch/*/entry/syscalls/syscall*.tbl) + +$(syscall_array): $(syscall_tbl) $(syscall_tbl_data) + $(Q)$(SHELL) '$(syscall_tbl)' $(srctree)/tools $@ + fs_at_flags_array := $(beauty_outdir)/fs_at_flags_array.c fs_at_flags_tbl := $(srctree)/tools/perf/trace/beauty/fs_at_flags.sh @@ -837,6 +854,7 @@ build-dir = $(or $(__build-dir),.) prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders \ arm64-sysreg-defs \ + $(syscall_array) \ $(fs_at_flags_array) \ $(clone_flags_array) \ $(drm_ioctl_array) \ diff --git a/tools/perf/arch/alpha/entry/syscalls/Kbuild b/tools/perf/arch/alpha/entry/syscalls/Kbuild deleted file mode 100644 index 9a41e3572c3a..000000000000 --- a/tools/perf/arch/alpha/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls b/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 690168aac34d..000000000000 --- a/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,5 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_64 += - -syscalltbl = $(srctree)/tools/perf/arch/alpha/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/alpha/include/syscall_table.h b/tools/perf/arch/alpha/include/syscall_table.h deleted file mode 100644 index b53e31c15805..000000000000 --- a/tools/perf/arch/alpha/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/arc/entry/syscalls/Kbuild b/tools/perf/arch/arc/entry/syscalls/Kbuild deleted file mode 100644 index 11707c481a24..000000000000 --- a/tools/perf/arch/arc/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h diff --git a/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 391d30ab7a83..000000000000 --- a/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += arc time32 renameat stat64 rlimit diff --git a/tools/perf/arch/arc/include/syscall_table.h b/tools/perf/arch/arc/include/syscall_table.h deleted file mode 100644 index 4c942821662d..000000000000 --- a/tools/perf/arch/arc/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/arm/entry/syscalls/Kbuild b/tools/perf/arch/arm/entry/syscalls/Kbuild deleted file mode 100644 index 9d777540f089..000000000000 --- a/tools/perf/arch/arm/entry/syscalls/Kbuild +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += oabi -syscalltbl = $(srctree)/tools/perf/arch/arm/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 11707c481a24..000000000000 --- a/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h diff --git a/tools/perf/arch/arm/include/syscall_table.h b/tools/perf/arch/arm/include/syscall_table.h deleted file mode 100644 index 4c942821662d..000000000000 --- a/tools/perf/arch/arm/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c index 9bc304cb7762..f421910e0709 100644 --- a/tools/perf/arch/arm/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -45,7 +45,7 @@ static int sample_ustack(struct perf_sample *sample, int test__arch_unwind_sample(struct perf_sample *sample, struct thread *thread) { - struct regs_dump *regs = &sample->user_regs; + struct regs_dump *regs = perf_sample__user_regs(sample); u64 *buf; buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 57dc94a6e38c..f70075c89aa0 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -18,7 +18,7 @@ void perf_pmu__arch_init(struct perf_pmu *pmu) { - struct perf_cpu_map *intersect; + struct perf_cpu_map *intersect, *online = cpu_map__online(); #ifdef HAVE_AUXTRACE_SUPPORT if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) { @@ -41,7 +41,8 @@ void perf_pmu__arch_init(struct perf_pmu *pmu) } #endif /* Workaround some ARM PMU's failing to correctly set CPU maps for online processors. */ - intersect = perf_cpu_map__intersect(cpu_map__online(), pmu->cpus); + intersect = perf_cpu_map__intersect(online, pmu->cpus); + perf_cpu_map__put(online); perf_cpu_map__put(pmu->cpus); pmu->cpus = intersect; } diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index 4e02cef461e3..fbb643f224ec 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -8,7 +8,7 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[PERF_REG_ARM_MAX]; #define REG(r) ({ \ diff --git a/tools/perf/arch/arm64/entry/syscalls/Kbuild b/tools/perf/arch/arm64/entry/syscalls/Kbuild deleted file mode 100644 index 84c6599b4ea6..000000000000 --- a/tools/perf/arch/arm64/entry/syscalls/Kbuild +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls deleted file mode 100644 index e7e78c2d1c02..000000000000 --- a/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += -syscall_abis_64 += renameat rlimit memfd_secret - -syscalltbl = $(srctree)/tools/perf/arch/arm64/entry/syscalls/syscall_%.tbl diff --git a/tools/perf/arch/arm64/include/syscall_table.h b/tools/perf/arch/arm64/include/syscall_table.h deleted file mode 100644 index 7ff51b783000..000000000000 --- a/tools/perf/arch/arm64/include/syscall_table.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/bitsperlong.h> - -#if __BITS_PER_LONG == 64 -#include <asm/syscalls_64.h> -#else -#include <asm/syscalls_32.h> -#endif diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c index b2603d0d3737..440d00f0de14 100644 --- a/tools/perf/arch/arm64/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c @@ -45,7 +45,7 @@ static int sample_ustack(struct perf_sample *sample, int test__arch_unwind_sample(struct perf_sample *sample, struct thread *thread) { - struct regs_dump *regs = &sample->user_regs; + struct regs_dump *regs = perf_sample__user_regs(sample); u64 *buf; buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 4301181b8e45..4f2833b62ff5 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -40,6 +40,19 @@ struct arm_spe_recording { bool *wrapped; }; +/* Iterate config list to detect if the "freq" parameter is set */ +static bool arm_spe_is_set_freq(struct evsel *evsel) +{ + struct evsel_config_term *term; + + list_for_each_entry(term, &evsel->config_terms, list) { + if (term->type == EVSEL__CONFIG_TERM_FREQ) + return true; + } + + return false; +} + /* * arm_spe_find_cpus() returns a new cpu map, and the caller should invoke * perf_cpu_map__put() to release the map after use. @@ -389,6 +402,14 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, return -EINVAL; } opts->full_auxtrace = true; + + if (opts->user_freq != UINT_MAX || + arm_spe_is_set_freq(evsel)) { + pr_err("Arm SPE: Frequency is not supported. " + "Set period with -c option or PMU parameter (-e %s/period=NUM/).\n", + evsel->pmu->name); + return -EINVAL; + } } } diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c index e056d50ab42e..b89b0a7e5ad9 100644 --- a/tools/perf/arch/arm64/util/unwind-libdw.c +++ b/tools/perf/arch/arm64/util/unwind-libdw.c @@ -8,7 +8,7 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX], dwarf_pc; #define REG(r) ({ \ diff --git a/tools/perf/arch/csky/entry/syscalls/Kbuild b/tools/perf/arch/csky/entry/syscalls/Kbuild deleted file mode 100644 index 11707c481a24..000000000000 --- a/tools/perf/arch/csky/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h diff --git a/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls b/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls deleted file mode 100644 index ea2dd10d0571..000000000000 --- a/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += csky time32 stat64 rlimit diff --git a/tools/perf/arch/csky/include/syscall_table.h b/tools/perf/arch/csky/include/syscall_table.h deleted file mode 100644 index 4c942821662d..000000000000 --- a/tools/perf/arch/csky/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/csky/util/unwind-libdw.c b/tools/perf/arch/csky/util/unwind-libdw.c index 79df4374ab18..b20b1569783d 100644 --- a/tools/perf/arch/csky/util/unwind-libdw.c +++ b/tools/perf/arch/csky/util/unwind-libdw.c @@ -10,7 +10,7 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[PERF_REG_CSKY_MAX]; #define REG(r) ({ \ diff --git a/tools/perf/arch/loongarch/entry/syscalls/Kbuild b/tools/perf/arch/loongarch/entry/syscalls/Kbuild deleted file mode 100644 index 9a41e3572c3a..000000000000 --- a/tools/perf/arch/loongarch/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls b/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 47d32da2aed8..000000000000 --- a/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_64 += diff --git a/tools/perf/arch/loongarch/include/syscall_table.h b/tools/perf/arch/loongarch/include/syscall_table.h deleted file mode 100644 index 9d0646d3455c..000000000000 --- a/tools/perf/arch/loongarch/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscall_table_64.h> diff --git a/tools/perf/arch/loongarch/util/unwind-libdw.c b/tools/perf/arch/loongarch/util/unwind-libdw.c index 7b3b9a4b21f8..60b1144bedd5 100644 --- a/tools/perf/arch/loongarch/util/unwind-libdw.c +++ b/tools/perf/arch/loongarch/util/unwind-libdw.c @@ -10,7 +10,7 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[PERF_REG_LOONGARCH_MAX]; #define REG(r) ({ \ diff --git a/tools/perf/arch/mips/entry/syscalls/Kbuild b/tools/perf/arch/mips/entry/syscalls/Kbuild deleted file mode 100644 index 9a41e3572c3a..000000000000 --- a/tools/perf/arch/mips/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls b/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 9ee914bdfb05..000000000000 --- a/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,5 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_64 += n64 - -syscalltbl = $(srctree)/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl diff --git a/tools/perf/arch/mips/include/syscall_table.h b/tools/perf/arch/mips/include/syscall_table.h deleted file mode 100644 index b53e31c15805..000000000000 --- a/tools/perf/arch/mips/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/parisc/entry/syscalls/Kbuild b/tools/perf/arch/parisc/entry/syscalls/Kbuild deleted file mode 100644 index 84c6599b4ea6..000000000000 --- a/tools/perf/arch/parisc/entry/syscalls/Kbuild +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls deleted file mode 100644 index ae326fecb83b..000000000000 --- a/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += -syscall_abis_64 += - -syscalltbl = $(srctree)/tools/perf/arch/parisc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/parisc/include/syscall_table.h b/tools/perf/arch/parisc/include/syscall_table.h deleted file mode 100644 index 7ff51b783000..000000000000 --- a/tools/perf/arch/parisc/include/syscall_table.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/bitsperlong.h> - -#if __BITS_PER_LONG == 64 -#include <asm/syscalls_64.h> -#else -#include <asm/syscalls_32.h> -#endif diff --git a/tools/perf/arch/powerpc/entry/syscalls/Kbuild b/tools/perf/arch/powerpc/entry/syscalls/Kbuild deleted file mode 100644 index 84c6599b4ea6..000000000000 --- a/tools/perf/arch/powerpc/entry/syscalls/Kbuild +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls deleted file mode 100644 index e35afbc57c79..000000000000 --- a/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += nospu -syscall_abis_64 += nospu - -syscalltbl = $(srctree)/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/powerpc/include/syscall_table.h b/tools/perf/arch/powerpc/include/syscall_table.h deleted file mode 100644 index 7ff51b783000..000000000000 --- a/tools/perf/arch/powerpc/include/syscall_table.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/bitsperlong.h> - -#if __BITS_PER_LONG == 64 -#include <asm/syscalls_64.h> -#else -#include <asm/syscalls_32.h> -#endif diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c index 5ecf82893b84..66af884baa66 100644 --- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c +++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c @@ -45,7 +45,7 @@ static int sample_ustack(struct perf_sample *sample, int test__arch_unwind_sample(struct perf_sample *sample, struct thread *thread) { - struct regs_dump *regs = &sample->user_regs; + struct regs_dump *regs = perf_sample__user_regs(sample); u64 *buf; buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index c7df534dbf8f..0be74f048f96 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -14,8 +14,8 @@ static bool is_compat_mode(void) { - u64 base_platform = getauxval(AT_BASE_PLATFORM); - u64 platform = getauxval(AT_PLATFORM); + unsigned long base_platform = getauxval(AT_BASE_PLATFORM); + unsigned long platform = getauxval(AT_PLATFORM); if (!strcmp((char *)platform, (char *)base_platform)) return false; diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c index e9a5a8bb67d9..82d0c28ae345 100644 --- a/tools/perf/arch/powerpc/util/unwind-libdw.c +++ b/tools/perf/arch/powerpc/util/unwind-libdw.c @@ -16,7 +16,7 @@ static const int special_regs[3][2] = { bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[32], dwarf_nip; size_t i; diff --git a/tools/perf/arch/riscv/entry/syscalls/Kbuild b/tools/perf/arch/riscv/entry/syscalls/Kbuild deleted file mode 100644 index 9a41e3572c3a..000000000000 --- a/tools/perf/arch/riscv/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls b/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 9668fd1faf60..000000000000 --- a/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += riscv memfd_secret -syscall_abis_64 += riscv rlimit memfd_secret diff --git a/tools/perf/arch/riscv/include/syscall_table.h b/tools/perf/arch/riscv/include/syscall_table.h deleted file mode 100644 index 7ff51b783000..000000000000 --- a/tools/perf/arch/riscv/include/syscall_table.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/bitsperlong.h> - -#if __BITS_PER_LONG == 64 -#include <asm/syscalls_64.h> -#else -#include <asm/syscalls_32.h> -#endif diff --git a/tools/perf/arch/riscv/util/unwind-libdw.c b/tools/perf/arch/riscv/util/unwind-libdw.c index 5c98010d8b59..dc1476e16321 100644 --- a/tools/perf/arch/riscv/util/unwind-libdw.c +++ b/tools/perf/arch/riscv/util/unwind-libdw.c @@ -10,7 +10,7 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[32]; #define REG(r) ({ \ diff --git a/tools/perf/arch/s390/entry/syscalls/Kbuild b/tools/perf/arch/s390/entry/syscalls/Kbuild deleted file mode 100644 index 9a41e3572c3a..000000000000 --- a/tools/perf/arch/s390/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls b/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 9762d7abf17c..000000000000 --- a/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,5 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_64 += renameat rlimit memfd_secret - -syscalltbl = $(srctree)/tools/perf/arch/s390/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/s390/include/syscall_table.h b/tools/perf/arch/s390/include/syscall_table.h deleted file mode 100644 index b53e31c15805..000000000000 --- a/tools/perf/arch/s390/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/s390/util/unwind-libdw.c b/tools/perf/arch/s390/util/unwind-libdw.c index f50fb6dbb35c..c27c7a0d1076 100644 --- a/tools/perf/arch/s390/util/unwind-libdw.c +++ b/tools/perf/arch/s390/util/unwind-libdw.c @@ -11,7 +11,7 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[ARRAY_SIZE(s390_dwarf_regs)]; #define REG(r) ({ \ diff --git a/tools/perf/arch/sh/entry/syscalls/Kbuild b/tools/perf/arch/sh/entry/syscalls/Kbuild deleted file mode 100644 index 11707c481a24..000000000000 --- a/tools/perf/arch/sh/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h diff --git a/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls b/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 25080390e4ed..000000000000 --- a/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += -syscalltbl = $(srctree)/tools/perf/arch/sh/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/sh/include/syscall_table.h b/tools/perf/arch/sh/include/syscall_table.h deleted file mode 100644 index 4c942821662d..000000000000 --- a/tools/perf/arch/sh/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/sparc/entry/syscalls/Kbuild b/tools/perf/arch/sparc/entry/syscalls/Kbuild deleted file mode 100644 index 84c6599b4ea6..000000000000 --- a/tools/perf/arch/sparc/entry/syscalls/Kbuild +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls deleted file mode 100644 index 212c1800b644..000000000000 --- a/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,5 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += -syscall_abis_64 += -syscalltbl = $(srctree)/tools/perf/arch/sparc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/sparc/include/syscall_table.h b/tools/perf/arch/sparc/include/syscall_table.h deleted file mode 100644 index 7ff51b783000..000000000000 --- a/tools/perf/arch/sparc/include/syscall_table.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/bitsperlong.h> - -#if __BITS_PER_LONG == 64 -#include <asm/syscalls_64.h> -#else -#include <asm/syscalls_32.h> -#endif diff --git a/tools/perf/arch/x86/Build b/tools/perf/arch/x86/Build index 02a1ca780a20..afae7b8f6bd6 100644 --- a/tools/perf/arch/x86/Build +++ b/tools/perf/arch/x86/Build @@ -2,14 +2,14 @@ perf-util-y += util/ perf-test-y += tests/ ifdef SHELLCHECK - TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) + SHELL_TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) else SHELL_TESTS := - TEST_LOGS := + SHELL_TEST_LOGS := endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) -perf-test-y += $(TEST_LOGS) +perf-test-y += $(SHELL_TEST_LOGS) diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index ae94b1f0b9cc..c6d403eae744 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -410,7 +410,7 @@ static void update_insn_state_x86(struct type_state *state, retry: /* Check stack variables with offset */ - if (sreg == fbreg) { + if (sreg == fbreg || sreg == state->stack_reg) { struct type_state_stack *stack; int offset = src->offset - fboff; @@ -433,8 +433,13 @@ retry: return; } - pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d", - insn_offset, -offset, dst->reg1); + if (sreg == fbreg) { + pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d", + insn_offset, -offset, dst->reg1); + } else { + pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d", + insn_offset, offset, sreg, dst->reg1); + } pr_debug_type_name(&tsr->type, tsr->kind); } /* And then dereference the pointer if it has one */ @@ -561,7 +566,7 @@ retry: return; /* Check stack variables with offset */ - if (dst->reg1 == fbreg) { + if (dst->reg1 == fbreg || dst->reg1 == state->stack_reg) { struct type_state_stack *stack; int offset = dst->offset - fboff; @@ -584,8 +589,13 @@ retry: &tsr->type); } - pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)", - insn_offset, src->reg1, -offset); + if (dst->reg1 == fbreg) { + pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)", + insn_offset, src->reg1, -offset); + } else { + pr_debug_dtp("mov [%x] reg%d -> %#x(reg%d)", + insn_offset, src->reg1, offset, dst->reg1); + } pr_debug_type_name(&tsr->type, tsr->kind); } /* diff --git a/tools/perf/arch/x86/entry/syscalls/Kbuild b/tools/perf/arch/x86/entry/syscalls/Kbuild deleted file mode 100644 index 84c6599b4ea6..000000000000 --- a/tools/perf/arch/x86/entry/syscalls/Kbuild +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h -syscall-y += syscalls_64.h diff --git a/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls b/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls deleted file mode 100644 index db3d5d6d4e56..000000000000 --- a/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,6 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += i386 -syscall_abis_64 += - -syscalltbl = $(srctree)/tools/perf/arch/x86/entry/syscalls/syscall_%.tbl diff --git a/tools/perf/arch/x86/include/syscall_table.h b/tools/perf/arch/x86/include/syscall_table.h deleted file mode 100644 index 7ff51b783000..000000000000 --- a/tools/perf/arch/x86/include/syscall_table.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/bitsperlong.h> - -#if __BITS_PER_LONG == 64 -#include <asm/syscalls_64.h> -#else -#include <asm/syscalls_32.h> -#endif diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 3227053f3355..86262c720857 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -13,14 +13,14 @@ perf-test-y += amd-ibs-via-core-pmu.o ifdef SHELLCHECK SHELL_TESTS := gen-insn-x86-dat.sh - TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) + SHELL_TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) else SHELL_TESTS := - TEST_LOGS := + SHELL_TEST_LOGS := endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) -perf-test-y += $(TEST_LOGS) +perf-test-y += $(SHELL_TEST_LOGS) diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index c05c0a85dad4..e91a73d09cec 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -53,7 +53,7 @@ static int sample_ustack(struct perf_sample *sample, int test__arch_unwind_sample(struct perf_sample *sample, struct thread *thread) { - struct regs_dump *regs = &sample->user_regs; + struct regs_dump *regs = perf_sample__user_regs(sample); u64 *buf; buf = malloc(sizeof(u64) * PERF_REGS_MAX); diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index 447a734e591c..1969758cc8c1 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -39,28 +39,13 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) * 26,319,024 slots * 2,427,791 instructions * 2,683,508 topdown-retiring - * - * If slots event and topdown metrics events are not in same group, the - * topdown metrics events must be first event after the slots event group, - * otherwise topdown metrics events can't be regrouped correctly, e.g. - * - * a. perf stat -e "{instructions,slots},cycles,topdown-retiring" -C0 sleep 1 + * e. slots event and metrics event are not in a group and not adjacent + * perf stat -e "{instructions,slots},cycles,topdown-retiring" -C0 sleep 1 * WARNING: events were regrouped to match PMUs - * Performance counter stats for 'CPU(s) 0': - * 17,923,134 slots - * 2,154,855 instructions - * 3,015,058 cycles - * <not supported> topdown-retiring - * - * If slots event and topdown metrics events are in two groups, the group which - * has topdown metrics events must contain only the topdown metrics event, - * otherwise topdown metrics event can't be regrouped correctly as well, e.g. - * - * a. perf stat -e "{instructions,slots},{topdown-retiring,cycles}" -C0 sleep 1 - * WARNING: events were regrouped to match PMUs - * Error: - * The sys_perf_event_open() syscall returned with 22 (Invalid argument) for - * event (topdown-retiring) + * 68,433,522 slots + * 8,856,102 topdown-retiring + * 7,791,494 instructions + * 11,469,513 cycles */ if (topdown_sys_has_perf_metrics() && (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) { @@ -76,12 +61,15 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) * topdown metrics events are already in same group with slots * event, do nothing. */ - if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs) && - lhs->core.leader != rhs->core.leader) - return -1; - if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs) && - lhs->core.leader != rhs->core.leader) - return 1; + if (lhs->core.leader != rhs->core.leader) { + bool lhs_topdown = arch_is_topdown_metrics(lhs); + bool rhs_topdown = arch_is_topdown_metrics(rhs); + + if (lhs_topdown && !rhs_topdown) + return -1; + if (!lhs_topdown && rhs_topdown) + return 1; + } } /* Retire latency event should not be group leader*/ diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index 00f645a0c18a..7442a2cd87ed 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -32,7 +32,7 @@ #define MAX_PATH 1024 #endif -#define UNCORE_IIO_PMU_PATH "devices/uncore_iio_%d" +#define UNCORE_IIO_PMU_PATH "bus/event_source/devices/uncore_iio_%d" #define SYSFS_UNCORE_PMU_PATH "%s/"UNCORE_IIO_PMU_PATH #define PLATFORM_MAPPING_PATH UNCORE_IIO_PMU_PATH"/die%d" diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c index f63747d0abdf..d1c654839049 100644 --- a/tools/perf/arch/x86/util/topdown.c +++ b/tools/perf/arch/x86/util/topdown.c @@ -81,7 +81,7 @@ bool arch_topdown_sample_read(struct evsel *leader) */ evlist__for_each_entry(leader->evlist, evsel) { if (evsel->core.leader != leader->core.leader) - return false; + continue; if (evsel != leader && arch_is_topdown_metrics(evsel)) return true; } diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c index edb77e20e083..798493e887d7 100644 --- a/tools/perf/arch/x86/util/unwind-libdw.c +++ b/tools/perf/arch/x86/util/unwind-libdw.c @@ -8,7 +8,7 @@ bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { struct unwind_info *ui = arg; - struct regs_dump *user_regs = &ui->sample->user_regs; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[17]; unsigned nregs; diff --git a/tools/perf/arch/xtensa/entry/syscalls/Kbuild b/tools/perf/arch/xtensa/entry/syscalls/Kbuild deleted file mode 100644 index 11707c481a24..000000000000 --- a/tools/perf/arch/xtensa/entry/syscalls/Kbuild +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -syscall-y += syscalls_32.h diff --git a/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls b/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls deleted file mode 100644 index d4aa2358460c..000000000000 --- a/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -syscall_abis_32 += -syscalltbl = $(srctree)/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/xtensa/include/syscall_table.h b/tools/perf/arch/xtensa/include/syscall_table.h deleted file mode 100644 index 4c942821662d..000000000000 --- a/tools/perf/arch/xtensa/include/syscall_table.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/syscalls_32.h> diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index e2562677df96..70139036d68f 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -204,17 +204,10 @@ static void *worker_thread(void *__tdata) } for (i = 0; i < loops; i++) { - if (!td->nr) { - ret = read_pipe(td); - BUG_ON(ret != sizeof(int)); - ret = write(td->pipe_write, &m, sizeof(int)); - BUG_ON(ret != sizeof(int)); - } else { - ret = write(td->pipe_write, &m, sizeof(int)); - BUG_ON(ret != sizeof(int)); - ret = read_pipe(td); - BUG_ON(ret != sizeof(int)); - } + ret = write(td->pipe_write, &m, sizeof(int)); + BUG_ON(ret != sizeof(int)); + ret = read_pipe(td); + BUG_ON(ret != sizeof(int)); } return NULL; diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c index ea4dfc07cbd6..e7dc216f717f 100644 --- a/tools/perf/bench/syscall.c +++ b/tools/perf/bench/syscall.c @@ -22,8 +22,7 @@ #define __NR_fork -1 #endif -#define LOOPS_DEFAULT 10000000 -static int loops = LOOPS_DEFAULT; +static int loops; static const struct option options[] = { OPT_INTEGER('l', "loop", &loops, "Specify number of loops"), @@ -80,6 +79,18 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) const char *name = NULL; int i; + switch (syscall) { + case __NR_fork: + case __NR_execve: + /* Limit default loop to 10000 times to save time */ + loops = 10000; + break; + default: + loops = 10000000; + break; + } + + /* Options -l and --loops override default above */ argc = parse_options(argc, argv, options, bench_syscall_usage, 0); gettimeofday(&start, NULL); @@ -94,16 +105,9 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) break; case __NR_fork: test_fork(); - /* Only loop 10000 times to save time */ - if (i == 10000) - loops = 10000; break; case __NR_execve: test_execve(); - /* Only loop 10000 times to save time */ - if (i == 10000) - loops = 10000; - break; default: break; } diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 836ae0122dab..9833c2c82a2f 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -321,14 +321,14 @@ static int process_feature_event(struct perf_session *session, return 0; } -static int hist_entry__tty_annotate(struct hist_entry *he, +static int hist_entry__stdio_annotate(struct hist_entry *he, struct evsel *evsel, struct perf_annotate *ann) { - if (!ann->use_stdio2) - return symbol__tty_annotate(&he->ms, evsel); + if (ann->use_stdio2) + return hist_entry__tty_annotate2(he, evsel); - return symbol__tty_annotate2(&he->ms, evsel); + return hist_entry__tty_annotate(he, evsel); } static void print_annotate_data_stat(struct annotated_data_stat *s) @@ -541,7 +541,7 @@ find_next: if (next != NULL) nd = next; } else { - hist_entry__tty_annotate(he, evsel, ann); + hist_entry__stdio_annotate(he, evsel, ann); nd = rb_next(nd); } } @@ -788,6 +788,8 @@ int cmd_annotate(int argc, const char **argv) "Show instruction stats for the data type annotation"), OPT_BOOLEAN(0, "skip-empty", &symbol_conf.skip_empty, "Do not display empty (or dummy) events in the output"), + OPT_BOOLEAN(0, "code-with-type", &annotate_opts.code_with_type, + "Show data type info in code annotation (memory instructions only)"), OPT_END() }; int ret; @@ -913,6 +915,13 @@ int cmd_annotate(int argc, const char **argv) annotate_opts.annotate_src = false; symbol_conf.annotate_data_member = true; symbol_conf.annotate_data_sample = true; + } else if (annotate_opts.code_with_type) { + symbol_conf.annotate_data_member = true; + + if (!annotate.use_stdio) { + pr_err("--code-with-type only works with --stdio.\n"); + goto out_delete; + } } setup_browser(true); diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 15e1fce71c72..5d5bb0f32334 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -3239,6 +3239,7 @@ static int perf_c2c__record(int argc, const char **argv) { int rec_argc, i = 0, j; const char **rec_argv; + char *event_name_storage = NULL; int ret; bool all_user = false, all_kernel = false; bool event_set = false; @@ -3300,7 +3301,7 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "--phys-data"; rec_argv[i++] = "--sample-cpu"; - ret = perf_mem_events__record_args(rec_argv, &i); + ret = perf_mem_events__record_args(rec_argv, &i, &event_name_storage); if (ret) goto out; @@ -3327,6 +3328,7 @@ static int perf_c2c__record(int argc, const char **argv) ret = cmd_record(i, rec_argv); out: + free(event_name_storage); free(rec_argv); return ret; } diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index cfd770ec7286..7caa18d5ffc3 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -733,6 +733,7 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[], { int min_latency = ftrace->min_latency; int max_latency = ftrace->max_latency; + unsigned int bucket_num = ftrace->bucket_num; char *p, *q; char *unit; double num; @@ -797,10 +798,10 @@ static void make_histogram(struct perf_ftrace *ftrace, int buckets[], if (num > 0) // 1st entry: [ 1 unit .. bucket_range units ] i = num / ftrace->bucket_range + 1; if (num >= max_latency - min_latency) - i = NUM_BUCKET -1; + i = bucket_num -1; } - if (i >= NUM_BUCKET) - i = NUM_BUCKET - 1; + if ((unsigned)i >= bucket_num) + i = bucket_num - 1; num += min_latency; do_inc: @@ -820,13 +821,14 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) { int min_latency = ftrace->min_latency; bool use_nsec = ftrace->use_nsec; - int i; + unsigned int bucket_num = ftrace->bucket_num; + unsigned int i; int total = 0; int bar_total = 46; /* to fit in 80 column */ char bar[] = "###############################################"; int bar_len; - for (i = 0; i < NUM_BUCKET; i++) + for (i = 0; i < bucket_num; i++) total += buckets[i]; if (total == 0) { @@ -839,14 +841,17 @@ static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) bar_len = buckets[0] * bar_total / total; - printf(" %4d - %4d %s | %10d | %.*s%*s |\n", - 0, min_latency ?: 1, use_nsec ? "ns" : "us", - buckets[0], bar_len, bar, bar_total - bar_len, ""); + if (!ftrace->hide_empty || buckets[0]) + printf(" %4d - %4d %s | %10d | %.*s%*s |\n", + 0, min_latency ?: 1, use_nsec ? "ns" : "us", + buckets[0], bar_len, bar, bar_total - bar_len, ""); - for (i = 1; i < NUM_BUCKET - 1; i++) { + for (i = 1; i < bucket_num - 1; i++) { unsigned int start, stop; const char *unit = use_nsec ? "ns" : "us"; + if (ftrace->hide_empty && !buckets[i]) + continue; if (!ftrace->bucket_range) { start = (1 << (i - 1)); stop = 1 << i; @@ -881,11 +886,13 @@ print_bucket_info: bar_total - bar_len, ""); } - bar_len = buckets[NUM_BUCKET - 1] * bar_total / total; + bar_len = buckets[bucket_num - 1] * bar_total / total; + if (ftrace->hide_empty && !buckets[bucket_num - 1]) + goto print_stats; if (!ftrace->bucket_range) { printf(" %4d - %-4s %s", 1, "...", use_nsec ? "ms" : "s "); } else { - unsigned int upper_outlier = (NUM_BUCKET - 2) * ftrace->bucket_range + min_latency; + unsigned int upper_outlier = (bucket_num - 2) * ftrace->bucket_range + min_latency; if (upper_outlier > ftrace->max_latency) upper_outlier = ftrace->max_latency; @@ -897,9 +904,10 @@ print_bucket_info: printf(" %4d - %4s %s", upper_outlier, "...", use_nsec ? "ns" : "us"); } } - printf(" | %10d | %.*s%*s |\n", buckets[NUM_BUCKET - 1], + printf(" | %10d | %.*s%*s |\n", buckets[bucket_num - 1], bar_len, bar, bar_total - bar_len, ""); +print_stats: printf("\n# statistics (in %s)\n", ftrace->use_nsec ? "nsec" : "usec"); printf(" total time: %20.0f\n", latency_stats.mean * latency_stats.n); printf(" avg time: %20.0f\n", latency_stats.mean); @@ -997,7 +1005,7 @@ static int __cmd_latency(struct perf_ftrace *ftrace) struct pollfd pollfd = { .events = POLLIN, }; - int buckets[NUM_BUCKET] = { }; + int *buckets; trace_fd = prepare_func_latency(ftrace); if (trace_fd < 0) @@ -1011,6 +1019,12 @@ static int __cmd_latency(struct perf_ftrace *ftrace) evlist__start_workload(ftrace->evlist); + buckets = calloc(ftrace->bucket_num, sizeof(*buckets)); + if (buckets == NULL) { + pr_err("failed to allocate memory for the buckets\n"); + goto out; + } + line[0] = '\0'; while (!done) { if (poll(&pollfd, 1, -1) < 0) @@ -1030,7 +1044,7 @@ static int __cmd_latency(struct perf_ftrace *ftrace) if (workload_exec_errno) { const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf)); pr_err("workload failed: %s\n", emsg); - goto out; + goto out_free_buckets; } /* read remaining buffer contents */ @@ -1045,6 +1059,8 @@ static int __cmd_latency(struct perf_ftrace *ftrace) display_histogram(ftrace, buckets); +out_free_buckets: + free(buckets); out: close(trace_fd); cleanup_func_latency(ftrace); @@ -1634,7 +1650,9 @@ int cmd_ftrace(int argc, const char **argv) OPT_UINTEGER(0, "min-latency", &ftrace.min_latency, "Minimum latency (1st bucket). Works only with --bucket-range."), OPT_UINTEGER(0, "max-latency", &ftrace.max_latency, - "Maximum latency (last bucket). Works only with --bucket-range and total buckets less than 22."), + "Maximum latency (last bucket). Works only with --bucket-range."), + OPT_BOOLEAN(0, "hide-empty", &ftrace.hide_empty, + "Hide empty buckets in the histogram"), OPT_PARENT(common_options), }; const struct option profile_options[] = { @@ -1751,10 +1769,25 @@ int cmd_ftrace(int argc, const char **argv) ret = -EINVAL; goto out_delete_filters; } - if (ftrace.bucket_range && !ftrace.max_latency) { - /* default max latency should depend on bucket range and num_buckets */ - ftrace.max_latency = (NUM_BUCKET - 2) * ftrace.bucket_range + - ftrace.min_latency; + if (ftrace.bucket_range && ftrace.max_latency && + ftrace.max_latency < ftrace.min_latency + ftrace.bucket_range) { + /* we need at least 1 bucket excluding min and max buckets */ + pr_err("--max-latency must be larger than min-latency + bucket-range\n"); + parse_options_usage(ftrace_usage, options, + "max-latency", /*short_opt=*/false); + ret = -EINVAL; + goto out_delete_filters; + } + /* set default unless max_latency is set and valid */ + ftrace.bucket_num = NUM_BUCKET; + if (ftrace.bucket_range) { + if (ftrace.max_latency) + ftrace.bucket_num = (ftrace.max_latency - ftrace.min_latency) / + ftrace.bucket_range + 2; + else + /* default max latency should depend on bucket range and num_buckets */ + ftrace.max_latency = (NUM_BUCKET - 2) * ftrace.bucket_range + + ftrace.min_latency; } cmd_func = __cmd_latency; break; diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 9e7fdfcdd7ff..fed482adb039 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -163,11 +163,10 @@ static void default_print_event(void *ps, const char *topic, const char *pmu_nam } else fputc('\n', fp); - if (long_desc && print_state->long_desc) { - fprintf(fp, "%*s", 8, "["); - wordwrap(fp, long_desc, 8, pager_get_columns(), 0); - fprintf(fp, "]\n"); - } else if (desc && print_state->desc) { + if (long_desc && print_state->long_desc) + desc = long_desc; + + if (desc && (print_state->desc || print_state->long_desc)) { char *desc_with_unit = NULL; int desc_len = -1; @@ -528,7 +527,7 @@ int cmd_list(int argc, const char **argv) OPT_BOOLEAN('d', "desc", &default_ps.desc, "Print extra event descriptions. --no-desc to not print."), OPT_BOOLEAN('v', "long-desc", &default_ps.long_desc, - "Print longer event descriptions."), + "Print longer event descriptions and all similar PMUs with alphanumeric suffixes."), OPT_BOOLEAN(0, "details", &default_ps.detailed, "Print information on the perf event names and expressions used internally by events."), OPT_STRING('o', "output", &output_path, "file", "output file name"), diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 5d405cd8e696..05e7bc30488a 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -418,16 +418,13 @@ static void combine_lock_stats(struct lock_stat *st) rb_insert_color(&st->rb, &sorted); } -static void insert_to_result(struct lock_stat *st, - int (*bigger)(struct lock_stat *, struct lock_stat *)) +static void insert_to(struct rb_root *rr, struct lock_stat *st, + int (*bigger)(struct lock_stat *, struct lock_stat *)) { - struct rb_node **rb = &result.rb_node; + struct rb_node **rb = &rr->rb_node; struct rb_node *parent = NULL; struct lock_stat *p; - if (combine_locks && st->combined) - return; - while (*rb) { p = container_of(*rb, struct lock_stat, rb); parent = *rb; @@ -439,13 +436,21 @@ static void insert_to_result(struct lock_stat *st, } rb_link_node(&st->rb, parent, rb); - rb_insert_color(&st->rb, &result); + rb_insert_color(&st->rb, rr); } -/* returns left most element of result, and erase it */ -static struct lock_stat *pop_from_result(void) +static inline void insert_to_result(struct lock_stat *st, + int (*bigger)(struct lock_stat *, + struct lock_stat *)) +{ + if (combine_locks && st->combined) + return; + insert_to(&result, st, bigger); +} + +static inline struct lock_stat *pop_from(struct rb_root *rr) { - struct rb_node *node = result.rb_node; + struct rb_node *node = rr->rb_node; if (!node) return NULL; @@ -453,8 +458,15 @@ static struct lock_stat *pop_from_result(void) while (node->rb_left) node = node->rb_left; - rb_erase(node, &result); + rb_erase(node, rr); return container_of(node, struct lock_stat, rb); + +} + +/* returns left most element of result, and erase it */ +static struct lock_stat *pop_from_result(void) +{ + return pop_from(&result); } struct trace_lock_handler { @@ -1805,6 +1817,22 @@ static void print_contention_result(struct lock_contention *con) break; } + if (con->owner && con->save_callstack && verbose > 0) { + struct rb_root root = RB_ROOT; + + if (symbol_conf.field_sep) + fprintf(lock_output, "# owner stack trace:\n"); + else + fprintf(lock_output, "\n=== owner stack trace ===\n\n"); + while ((st = pop_owner_stack_trace(con))) + insert_to(&root, st, compare); + + while ((st = pop_from(&root))) { + print_lock_stat(con, st); + free(st); + } + } + if (print_nr_entries) { /* update the total/bad stats */ while ((st = pop_from_result())) { @@ -1950,8 +1978,10 @@ static int check_lock_contention_options(const struct option *options, } } - if (show_lock_owner) - show_thread_stats = true; + if (show_lock_owner && !show_thread_stats) { + pr_warning("Now -o try to show owner's callstack instead of pid and comm.\n"); + pr_warning("Please use -t option too to keep the old behavior.\n"); + } return 0; } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 99d5e1491a28..5ec83cd85650 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -74,6 +74,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem, int rec_argc, i = 0, j; int start, end; const char **rec_argv; + char *event_name_storage = NULL; int ret; struct perf_mem_event *e; struct perf_pmu *pmu; @@ -140,7 +141,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem, rec_argv[i++] = "--data-page-size"; start = i; - ret = perf_mem_events__record_args(rec_argv, &i); + ret = perf_mem_events__record_args(rec_argv, &i, &event_name_storage); if (ret) goto out; end = i; @@ -170,6 +171,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem, ret = cmd_record(i, rec_argv); out: + free(event_name_storage); free(rec_argv); return ret; } @@ -521,6 +523,7 @@ int cmd_mem(int argc, const char **argv) NULL, NULL }; + int ret; argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -536,14 +539,15 @@ int cmd_mem(int argc, const char **argv) } if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) - return __cmd_record(argc, argv, &mem, record_options); + ret = __cmd_record(argc, argv, &mem, record_options); else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) - return __cmd_report(argc, argv, &mem, report_options); + ret = __cmd_report(argc, argv, &mem, report_options); else usage_with_options(mem_usage, mem_options); /* free usage string allocated by parse_options_subcommand */ free((void *)mem_usage[0]); + free(sort_order_help); - return 0; + return ret; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 5db1aedf48df..ba20bf7c011d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -161,6 +161,7 @@ struct record { struct evlist *sb_evlist; pthread_t thread_id; int realtime_prio; + bool latency; bool switch_output_event_set; bool no_buildid; bool no_buildid_set; @@ -1917,9 +1918,10 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel, u16 misc_flag) { struct perf_sample_id *sid; - struct perf_sample sample = {}; + struct perf_sample sample; int id_hdr_size; + perf_sample__init(&sample, /*all=*/true); lost->lost = lost_count; if (evsel->core.ids) { sid = xyarray__entry(evsel->core.sample_id, cpu_idx, thread_idx); @@ -1931,6 +1933,7 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel, lost->header.size = sizeof(*lost) + id_hdr_size; lost->header.misc = misc_flag; record__write(rec, NULL, lost, lost->header.size); + perf_sample__exit(&sample); } static void record__read_lost_samples(struct record *rec) @@ -2532,6 +2535,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_free_threads; } + if (!evlist__needs_bpf_sb_event(rec->evlist)) + opts->no_bpf_event = true; + err = record__setup_sb_evlist(rec); if (err) goto out_free_threads; @@ -3371,6 +3377,9 @@ static struct option __record_options[] = { parse_events_option), OPT_CALLBACK(0, "filter", &record.evlist, "filter", "event filter", parse_filter), + OPT_BOOLEAN(0, "latency", &record.latency, + "Enable data collection for latency profiling.\n" + "\t\t\t Use perf report --latency for latency-centric profile."), OPT_CALLBACK_NOOPT(0, "exclude-perf", &record.evlist, NULL, "don't record events from perf itself", exclude_perf), @@ -4017,6 +4026,22 @@ int cmd_record(int argc, const char **argv) } + if (record.latency) { + /* + * There is no fundamental reason why latency profiling + * can't work for system-wide mode, but exact semantics + * and details are to be defined. + * See the following thread for details: + * https://lore.kernel.org/all/Z4XDJyvjiie3howF@google.com/ + */ + if (record.opts.target.system_wide) { + pr_err("Failed: latency profiling is not supported with system-wide collection.\n"); + err = -EINVAL; + goto out_opts; + } + record.opts.record_switch_events = true; + } + if (rec->buildid_mmap) { if (!perf_can_record_build_id()) { pr_err("Failed: no support to record build id in mmap events, update your kernel.\n"); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f5fbd670d619..b030ce72e13e 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -112,6 +112,8 @@ struct report { u64 nr_entries; u64 queue_size; u64 total_cycles; + u64 total_samples; + u64 singlethreaded_samples; int socket_filter; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); struct branch_type_stat brtype_stat; @@ -331,6 +333,10 @@ static int process_sample_event(const struct perf_tool *tool, &rep->total_cycles, evsel); } + rep->total_samples++; + if (al.parallelism == 1) + rep->singlethreaded_samples++; + ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep); if (ret < 0) pr_debug("problem adding hist entry, skipping event\n"); @@ -1079,6 +1085,11 @@ static int __cmd_report(struct report *rep) return ret; } + /* Don't show Latency column for non-parallel profiles by default. */ + if (!symbol_conf.prefer_latency && rep->total_samples && + rep->singlethreaded_samples * 100 / rep->total_samples >= 99) + perf_hpp__cancel_latency(); + evlist__check_mem_load_aux(session->evlist); if (rep->stats_mode) @@ -1390,6 +1401,8 @@ int cmd_report(int argc, const char **argv) symbol__config_symfs), OPT_STRING('C', "cpu", &report.cpu_list, "cpu", "list of cpus to profile"), + OPT_STRING(0, "parallelism", &symbol_conf.parallelism_list_str, "parallelism", + "only consider these parallelism levels (cpu set format)"), OPT_BOOLEAN('I', "show-info", &report.show_full_info, "Display extended information about perf.data file"), OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src, @@ -1466,6 +1479,10 @@ int cmd_report(int argc, const char **argv) "Disable raw trace ordering"), OPT_BOOLEAN(0, "skip-empty", &report.skip_empty, "Do not display empty (or dummy) events in the output"), + OPT_BOOLEAN(0, "latency", &symbol_conf.prefer_latency, + "Show latency-centric profile rather than the default\n" + "\t\t\t CPU-consumption-centric profile\n" + "\t\t\t (requires perf record --latency flag)."), OPT_END() }; struct perf_data data = { @@ -1553,12 +1570,12 @@ int cmd_report(int argc, const char **argv) input_name = "perf.data"; } +repeat: data.path = input_name; data.force = symbol_conf.force; symbol_conf.skip_empty = report.skip_empty; -repeat: perf_tool__init(&report.tool, ordered_events); report.tool.sample = process_sample_event; report.tool.mmap = perf_event__process_mmap; @@ -1568,6 +1585,7 @@ repeat: report.tool.cgroup = perf_event__process_cgroup; report.tool.exit = perf_event__process_exit; report.tool.fork = perf_event__process_fork; + report.tool.context_switch = perf_event__process_switch; report.tool.lost = perf_event__process_lost; report.tool.read = process_read_event; report.tool.attr = process_attr; @@ -1655,8 +1673,6 @@ repeat: if (symbol_conf.report_hierarchy) { /* disable incompatible options */ - symbol_conf.cumulate_callchain = false; - if (field_order) { pr_err("Error: --hierarchy and --fields options cannot be used together\n"); parse_options_usage(report_usage, options, "F", 1); @@ -1703,6 +1719,9 @@ repeat: report.data_type = true; annotate_opts.annotate_src = false; + /* disable incompatible options */ + symbol_conf.cumulate_callchain = false; + #ifndef HAVE_LIBDW_SUPPORT pr_err("Error: Data type profiling is disabled due to missing DWARF support\n"); goto error; @@ -1719,22 +1738,45 @@ repeat: symbol_conf.annotate_data_sample = true; } - if (sort_order && strstr(sort_order, "ipc")) { - parse_options_usage(report_usage, options, "s", 1); - goto error; + symbol_conf.enable_latency = true; + if (report.disable_order || !perf_session__has_switch_events(session)) { + if (symbol_conf.parallelism_list_str || + symbol_conf.prefer_latency || + (sort_order && (strstr(sort_order, "latency") || + strstr(sort_order, "parallelism"))) || + (field_order && (strstr(field_order, "latency") || + strstr(field_order, "parallelism")))) { + if (report.disable_order) + ui__error("Use of latency profile or parallelism is incompatible with --disable-order.\n"); + else + ui__error("Use of latency profile or parallelism requires --latency flag during record.\n"); + return -1; + } + /* + * If user did not ask for anything related to + * latency/parallelism explicitly, just don't show it. + */ + symbol_conf.enable_latency = false; } - if (sort_order && strstr(sort_order, "symbol")) { - if (sort__mode == SORT_MODE__BRANCH) { - snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", - sort_order, "ipc_lbr"); - report.symbol_ipc = true; - } else { - snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", - sort_order, "ipc_null"); + if (last_key != K_SWITCH_INPUT_DATA) { + if (sort_order && strstr(sort_order, "ipc")) { + parse_options_usage(report_usage, options, "s", 1); + goto error; } - sort_order = sort_tmp; + if (sort_order && strstr(sort_order, "symbol")) { + if (sort__mode == SORT_MODE__BRANCH) { + snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", + sort_order, "ipc_lbr"); + report.symbol_ipc = true; + } else { + snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", + sort_order, "ipc_null"); + } + + sort_order = sort_tmp; + } } if ((last_key != K_SWITCH_INPUT_DATA && last_key != K_RELOAD) && @@ -1826,6 +1868,11 @@ repeat: if (ret == K_SWITCH_INPUT_DATA || ret == K_RELOAD) { perf_session__delete(session); last_key = K_SWITCH_INPUT_DATA; + /* + * To support switching between data with and without callchains. + * report__setup_sample_type() will update it properly. + */ + symbol_conf.use_callchain = false; goto repeat; } else ret = 0; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 33667b534634..9b16df881af8 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -400,10 +400,20 @@ static inline int output_type(unsigned int type) static inline int evsel__output_type(struct evsel *evsel) { - if (evsel->script_output_type == OUTPUT_TYPE_UNSET) - evsel->script_output_type = output_type(evsel->core.attr.type); + int type = evsel->script_output_type; - return evsel->script_output_type; + if (type == OUTPUT_TYPE_UNSET) { + type = output_type(evsel->core.attr.type); + if (type == OUTPUT_TYPE_OTHER) { + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu && pmu->is_core) + type = PERF_TYPE_RAW; + } + evsel->script_output_type = type; + } + + return type; } static bool output_set_by_user(void) @@ -783,14 +793,20 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen, static int perf_sample__fprintf_iregs(struct perf_sample *sample, struct perf_event_attr *attr, const char *arch, FILE *fp) { - return perf_sample__fprintf_regs(&sample->intr_regs, + if (!sample->intr_regs) + return 0; + + return perf_sample__fprintf_regs(perf_sample__intr_regs(sample), attr->sample_regs_intr, arch, fp); } static int perf_sample__fprintf_uregs(struct perf_sample *sample, struct perf_event_attr *attr, const char *arch, FILE *fp) { - return perf_sample__fprintf_regs(&sample->user_regs, + if (!sample->user_regs) + return 0; + + return perf_sample__fprintf_regs(perf_sample__user_regs(sample), attr->sample_regs_user, arch, fp); } @@ -929,19 +945,25 @@ static int perf_sample__fprintf_start(struct perf_script *script, return printed; } -static inline char -mispred_str(struct branch_entry *br) +static inline size_t +bstack_event_str(struct branch_entry *br, char *buf, size_t sz) { - if (!(br->flags.mispred || br->flags.predicted)) - return '-'; + if (!(br->flags.mispred || br->flags.predicted || br->flags.not_taken)) + return snprintf(buf, sz, "-"); - return br->flags.predicted ? 'P' : 'M'; + return snprintf(buf, sz, "%s%s", + br->flags.predicted ? "P" : "M", + br->flags.not_taken ? "N" : ""); } static int print_bstack_flags(FILE *fp, struct branch_entry *br) { - return fprintf(fp, "/%c/%c/%c/%d/%s/%s ", - mispred_str(br), + char events[16] = { 0 }; + size_t pos; + + pos = bstack_event_str(br, events, sizeof(events)); + return fprintf(fp, "/%s/%c/%c/%d/%s/%s ", + pos < 0 ? "-" : events, br->flags.in_tx ? 'X' : '-', br->flags.abort ? 'A' : '-', br->flags.cycles, @@ -1703,9 +1725,14 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { char str[SAMPLE_FLAGS_BUF_SIZE]; + int ret; + + ret = perf_sample__sprintf_flags(flags, str, sizeof(str)); + if (ret < 0) + return fprintf(fp, " raw flags:0x%-*x ", + SAMPLE_FLAGS_STR_ALIGNED_SIZE - 12, flags); - perf_sample__sprintf_flags(flags, str, sizeof(str)); - return fprintf(fp, " %-21s ", str); + return fprintf(fp, " %-*s ", SAMPLE_FLAGS_STR_ALIGNED_SIZE, str); } struct printer_data { diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 77e327d4a9a7..68ea7589c143 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -97,7 +97,7 @@ #include <internal/threadmap.h> #define DEFAULT_SEPARATOR " " -#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" +#define FREEZE_ON_SMI_PATH "bus/event_source/devices/cpu/freeze_on_smi" static void print_counters(struct timespec *ts, int argc, const char **argv); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 4fd31d29b2ab..1061f4eebc3f 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -263,7 +263,7 @@ static void perf_top__show_details(struct perf_top *top) printf("Showing %s for %s\n", evsel__name(top->sym_evsel), symbol->name); printf(" Events Pcnt (>=%d%%)\n", annotate_opts.min_pcnt); - more = symbol__annotate_printf(&he->ms, top->sym_evsel); + more = hist_entry__annotate_printf(he, top->sym_evsel); if (top->evlist->enabled) { if (top->zero) @@ -1157,6 +1157,7 @@ static int deliver_event(struct ordered_events *qe, return 0; } + perf_sample__init(&sample, /*all=*/false); ret = evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); @@ -1167,8 +1168,10 @@ static int deliver_event(struct ordered_events *qe, assert(evsel != NULL); if (event->header.type == PERF_RECORD_SAMPLE) { - if (evswitch__discard(&top->evswitch, evsel)) - return 0; + if (evswitch__discard(&top->evswitch, evsel)) { + ret = 0; + goto next_event; + } ++top->samples; } @@ -1219,6 +1222,7 @@ static int deliver_event(struct ordered_events *qe, ret = 0; next_event: + perf_sample__exit(&sample); return ret; } @@ -1818,6 +1822,9 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } + if (!evlist__needs_bpf_sb_event(top.evlist)) + top.record_opts.no_bpf_event = true; + #ifdef HAVE_LIBBPF_SUPPORT if (!top.record_opts.no_bpf_event) { top.sb_evlist = evlist__new(); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index d466447ae928..6ac51925ea42 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -39,6 +39,7 @@ #include "util/synthetic-events.h" #include "util/evlist.h" #include "util/evswitch.h" +#include "util/hashmap.h" #include "util/mmap.h" #include <subcmd/pager.h> #include <subcmd/exec-cmd.h> @@ -63,9 +64,9 @@ #include "print_binary.h" #include "string2.h" #include "syscalltbl.h" -#include "rb_resort.h" #include "../perf.h" #include "trace_augment.h" +#include "dwarf-regs.h" #include <errno.h> #include <inttypes.h> @@ -86,6 +87,7 @@ #include <linux/ctype.h> #include <perf/mmap.h> +#include <tools/libc_compat.h> #ifdef HAVE_LIBTRACEEVENT #include <event-parse.h> @@ -139,11 +141,19 @@ struct syscall_fmt { bool hexret; }; +enum summary_mode { + SUMMARY__NONE = 0, + SUMMARY__BY_TOTAL, + SUMMARY__BY_THREAD, +}; + struct trace { struct perf_tool tool; - struct syscalltbl *sctbl; struct { - struct syscall *table; + /** Sorted sycall numbers used by the trace. */ + struct syscall **table; + /** Size of table. */ + size_t table_size; struct { struct evsel *sys_enter, *sys_exit, @@ -177,14 +187,25 @@ struct trace { pid_t *entries; struct bpf_map *map; } filter_pids; + /* + * TODO: The map is from an ID (aka system call number) to struct + * syscall_stats. If there is >1 e_machine, such as i386 and x86-64 + * processes, then the stats here will gather wrong the statistics for + * the non EM_HOST system calls. A fix would be to add the e_machine + * into the key, but this would make the code inconsistent with the + * per-thread version. + */ + struct hashmap *syscall_stats; double duration_filter; double runtime_ms; + unsigned long pfmaj, pfmin; struct { u64 vfs_getname, proc_getname; } stats; unsigned int max_stack; unsigned int min_stack; + enum summary_mode summary_mode; int raw_augmented_syscalls_args_size; bool raw_augmented_syscalls; bool fd_path_disabled; @@ -1445,22 +1466,37 @@ static const struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias) return __syscall_fmt__find_by_alias(syscall_fmts, nmemb, alias); } -/* - * is_exit: is this "exit" or "exit_group"? - * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter. - * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc. - * nonexistent: Just a hole in the syscall table, syscall id not allocated +/** + * struct syscall */ struct syscall { + /** @e_machine: The ELF machine associated with the entry. */ + int e_machine; + /** @id: id value from the tracepoint, the system call number. */ + int id; struct tep_event *tp_format; int nr_args; + /** + * @args_size: sum of the sizes of the syscall arguments, anything + * after that is augmented stuff: pathname for openat, etc. + */ + int args_size; struct { struct bpf_program *sys_enter, *sys_exit; } bpf_prog; + /** @is_exit: is this "exit" or "exit_group"? */ bool is_exit; + /** + * @is_open: is this "open" or "openat"? To associate the fd returned in + * sys_exit with the pathname in sys_enter. + */ bool is_open; + /** + * @nonexistent: Name lookup failed. Just a hole in the syscall table, + * syscall id not allocated. + */ bool nonexistent; bool use_btf; struct tep_format_field *args; @@ -1519,16 +1555,48 @@ struct thread_trace { struct file *table; } files; - struct intlist *syscall_stats; + struct hashmap *syscall_stats; }; -static struct thread_trace *thread_trace__new(void) +static size_t syscall_id_hash(long key, void *ctx __maybe_unused) +{ + return key; +} + +static bool syscall_id_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return key1 == key2; +} + +static struct hashmap *alloc_syscall_stats(void) +{ + return hashmap__new(syscall_id_hash, syscall_id_equal, NULL); +} + +static void delete_syscall_stats(struct hashmap *syscall_stats) +{ + struct hashmap_entry *pos; + size_t bkt; + + if (syscall_stats == NULL) + return; + + hashmap__for_each_entry(syscall_stats, pos, bkt) + zfree(&pos->pvalue); + hashmap__free(syscall_stats); +} + +static struct thread_trace *thread_trace__new(struct trace *trace) { struct thread_trace *ttrace = zalloc(sizeof(struct thread_trace)); if (ttrace) { ttrace->files.max = -1; - ttrace->syscall_stats = intlist__new(NULL); + if (trace->summary) { + ttrace->syscall_stats = alloc_syscall_stats(); + if (IS_ERR(ttrace->syscall_stats)) + zfree(&ttrace); + } } return ttrace; @@ -1543,14 +1611,14 @@ static void thread_trace__delete(void *pttrace) if (!ttrace) return; - intlist__delete(ttrace->syscall_stats); + delete_syscall_stats(ttrace->syscall_stats); ttrace->syscall_stats = NULL; thread_trace__free_files(ttrace); zfree(&ttrace->entry_str); free(ttrace); } -static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) +static struct thread_trace *thread__trace(struct thread *thread, struct trace *trace) { struct thread_trace *ttrace; @@ -1558,7 +1626,7 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) goto fail; if (thread__priv(thread) == NULL) - thread__set_priv(thread, thread_trace__new()); + thread__set_priv(thread, thread_trace__new(trace)); if (thread__priv(thread) == NULL) goto fail; @@ -1568,7 +1636,7 @@ static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) return ttrace; fail: - color_fprintf(fp, PERF_COLOR_RED, + color_fprintf(trace->output, PERF_COLOR_RED, "WARNING: not enough memory, dropping samples!\n"); return NULL; } @@ -2066,22 +2134,21 @@ static int syscall__set_arg_fmts(struct syscall *sc) return 0; } -static int trace__read_syscall_info(struct trace *trace, int id) +static int syscall__read_info(struct syscall *sc, struct trace *trace) { char tp_name[128]; - struct syscall *sc; - const char *name = syscalltbl__name(trace->sctbl, id); + const char *name; int err; - if (trace->syscalls.table == NULL) { - trace->syscalls.table = calloc(trace->sctbl->syscalls.max_id + 1, sizeof(*sc)); - if (trace->syscalls.table == NULL) - return -ENOMEM; - } - sc = trace->syscalls.table + id; if (sc->nonexistent) return -EEXIST; + if (sc->name) { + /* Info already read. */ + return 0; + } + + name = syscalltbl__name(sc->e_machine, sc->id); if (name == NULL) { sc->nonexistent = true; return -EEXIST; @@ -2104,15 +2171,16 @@ static int trace__read_syscall_info(struct trace *trace, int id) */ if (IS_ERR(sc->tp_format)) { sc->nonexistent = true; - return PTR_ERR(sc->tp_format); + err = PTR_ERR(sc->tp_format); + sc->tp_format = NULL; + return err; } /* * The tracepoint format contains __syscall_nr field, so it's one more * than the actual number of syscall arguments. */ - if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? - RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields - 1)) + if (syscall__alloc_arg_fmts(sc, sc->tp_format->format.nr_fields - 1)) return -ENOMEM; sc->args = sc->tp_format->format.fields; @@ -2180,10 +2248,14 @@ static int trace__validate_ev_qualifier(struct trace *trace) strlist__for_each_entry(pos, trace->ev_qualifier) { const char *sc = pos->s; - int id = syscalltbl__id(trace->sctbl, sc), match_next = -1; + /* + * TODO: Assume more than the validation/warnings are all for + * the same binary type as perf. + */ + int id = syscalltbl__id(EM_HOST, sc), match_next = -1; if (id < 0) { - id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next); + id = syscalltbl__strglobmatch_first(EM_HOST, sc, &match_next); if (id >= 0) goto matches; @@ -2203,7 +2275,7 @@ matches: continue; while (1) { - id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next); + id = syscalltbl__strglobmatch_next(EM_HOST, sc, &match_next); if (id < 0) break; if (nr_allocated == nr_used) { @@ -2401,13 +2473,92 @@ next_arg: return printed; } +static struct syscall *syscall__new(int e_machine, int id) +{ + struct syscall *sc = zalloc(sizeof(*sc)); + + if (!sc) + return NULL; + + sc->e_machine = e_machine; + sc->id = id; + return sc; +} + +static void syscall__delete(struct syscall *sc) +{ + if (!sc) + return; + + free(sc->arg_fmt); + free(sc); +} + +static int syscall__bsearch_cmp(const void *key, const void *entry) +{ + const struct syscall *a = key, *b = *((const struct syscall **)entry); + + if (a->e_machine != b->e_machine) + return a->e_machine - b->e_machine; + + return a->id - b->id; +} + +static int syscall__cmp(const void *va, const void *vb) +{ + const struct syscall *a = *((const struct syscall **)va); + const struct syscall *b = *((const struct syscall **)vb); + + if (a->e_machine != b->e_machine) + return a->e_machine - b->e_machine; + + return a->id - b->id; +} + +static struct syscall *trace__find_syscall(struct trace *trace, int e_machine, int id) +{ + struct syscall key = { + .e_machine = e_machine, + .id = id, + }; + struct syscall *sc, **tmp; + + if (trace->syscalls.table) { + struct syscall **sc_entry = bsearch(&key, trace->syscalls.table, + trace->syscalls.table_size, + sizeof(trace->syscalls.table[0]), + syscall__bsearch_cmp); + + if (sc_entry) + return *sc_entry; + } + + sc = syscall__new(e_machine, id); + if (!sc) + return NULL; + + tmp = reallocarray(trace->syscalls.table, trace->syscalls.table_size + 1, + sizeof(trace->syscalls.table[0])); + if (!tmp) { + syscall__delete(sc); + return NULL; + } + + trace->syscalls.table = tmp; + trace->syscalls.table[trace->syscalls.table_size++] = sc; + qsort(trace->syscalls.table, trace->syscalls.table_size, sizeof(trace->syscalls.table[0]), + syscall__cmp); + return sc; +} + typedef int (*tracepoint_handler)(struct trace *trace, struct evsel *evsel, union perf_event *event, struct perf_sample *sample); -static struct syscall *trace__syscall_info(struct trace *trace, - struct evsel *evsel, int id) +static struct syscall *trace__syscall_info(struct trace *trace, struct evsel *evsel, + int e_machine, int id) { + struct syscall *sc; int err = 0; if (id < 0) { @@ -2432,28 +2583,20 @@ static struct syscall *trace__syscall_info(struct trace *trace, err = -EINVAL; - if (id > trace->sctbl->syscalls.max_id) { - goto out_cant_read; - } - - if ((trace->syscalls.table == NULL || trace->syscalls.table[id].name == NULL) && - (err = trace__read_syscall_info(trace, id)) != 0) - goto out_cant_read; + sc = trace__find_syscall(trace, e_machine, id); + if (sc) + err = syscall__read_info(sc, trace); - if (trace->syscalls.table && trace->syscalls.table[id].nonexistent) - goto out_cant_read; - - return &trace->syscalls.table[id]; - -out_cant_read: - if (verbose > 0) { + if (err && verbose > 0) { char sbuf[STRERR_BUFSIZE]; - fprintf(trace->output, "Problems reading syscall %d: %d (%s)", id, -err, str_error_r(-err, sbuf, sizeof(sbuf))); - if (id <= trace->sctbl->syscalls.max_id && trace->syscalls.table[id].name != NULL) - fprintf(trace->output, "(%s)", trace->syscalls.table[id].name); + + fprintf(trace->output, "Problems reading syscall %d: %d (%s)", id, -err, + str_error_r(-err, sbuf, sizeof(sbuf))); + if (sc && sc->name) + fprintf(trace->output, "(%s)", sc->name); fputs(" information\n", trace->output); } - return NULL; + return err ? NULL : sc; } struct syscall_stats { @@ -2464,24 +2607,26 @@ struct syscall_stats { }; static void thread__update_stats(struct thread *thread, struct thread_trace *ttrace, - int id, struct perf_sample *sample, long err, bool errno_summary) + int id, struct perf_sample *sample, long err, + struct trace *trace) { - struct int_node *inode; - struct syscall_stats *stats; + struct hashmap *syscall_stats = ttrace->syscall_stats; + struct syscall_stats *stats = NULL; u64 duration = 0; - inode = intlist__findnew(ttrace->syscall_stats, id); - if (inode == NULL) - return; + if (trace->summary_mode == SUMMARY__BY_TOTAL) + syscall_stats = trace->syscall_stats; - stats = inode->priv; - if (stats == NULL) { + if (!hashmap__find(syscall_stats, id, &stats)) { stats = zalloc(sizeof(*stats)); if (stats == NULL) return; init_stats(&stats->stats); - inode->priv = stats; + if (hashmap__add(syscall_stats, id, stats) < 0) { + free(stats); + return; + } } if (ttrace->entry_time && sample->time > ttrace->entry_time) @@ -2492,7 +2637,7 @@ static void thread__update_stats(struct thread *thread, struct thread_trace *ttr if (err < 0) { ++stats->nr_failures; - if (!errno_summary) + if (!trace->errno_summary) return; err = -err; @@ -2600,14 +2745,6 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam return NULL; } -static void syscall__exit(struct syscall *sc) -{ - if (!sc) - return; - - zfree(&sc->arg_fmt); -} - static int trace__sys_enter(struct trace *trace, struct evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -2617,16 +2754,17 @@ static int trace__sys_enter(struct trace *trace, struct evsel *evsel, int printed = 0; struct thread *thread; int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1; - int augmented_args_size = 0; + int augmented_args_size = 0, e_machine; void *augmented_args = NULL; - struct syscall *sc = trace__syscall_info(trace, evsel, id); + struct syscall *sc; struct thread_trace *ttrace; - if (sc == NULL) - return -1; - thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); - ttrace = thread__trace(thread, trace->output); + e_machine = thread__e_machine(thread, trace->host); + sc = trace__syscall_info(trace, evsel, e_machine, id); + if (sc == NULL) + goto out_put; + ttrace = thread__trace(thread, trace); if (ttrace == NULL) goto out_put; @@ -2693,17 +2831,19 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct evsel *evsel, struct thread_trace *ttrace; struct thread *thread; int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1; - struct syscall *sc = trace__syscall_info(trace, evsel, id); + struct syscall *sc; char msg[1024]; void *args, *augmented_args = NULL; - int augmented_args_size; + int augmented_args_size, e_machine; size_t printed = 0; - if (sc == NULL) - return -1; thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); - ttrace = thread__trace(thread, trace->output); + e_machine = thread__e_machine(thread, trace->host); + sc = trace__syscall_info(trace, evsel, e_machine, id); + if (sc == NULL) + return -1; + ttrace = thread__trace(thread, trace); /* * We need to get ttrace just to make sure it is there when syscall__scnprintf_args() * and the rest of the beautifiers accessing it via struct syscall_arg touches it. @@ -2767,15 +2907,16 @@ static int trace__sys_exit(struct trace *trace, struct evsel *evsel, bool duration_calculated = false; struct thread *thread; int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0, printed = 0; - int alignment = trace->args_alignment; - struct syscall *sc = trace__syscall_info(trace, evsel, id); + int alignment = trace->args_alignment, e_machine; + struct syscall *sc; struct thread_trace *ttrace; - if (sc == NULL) - return -1; - thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); - ttrace = thread__trace(thread, trace->output); + e_machine = thread__e_machine(thread, trace->host); + sc = trace__syscall_info(trace, evsel, e_machine, id); + if (sc == NULL) + goto out_put; + ttrace = thread__trace(thread, trace); if (ttrace == NULL) goto out_put; @@ -2784,7 +2925,7 @@ static int trace__sys_exit(struct trace *trace, struct evsel *evsel, ret = perf_evsel__sc_tp_uint(evsel, ret, sample); if (trace->summary) - thread__update_stats(thread, ttrace, id, sample, ret, trace->errno_summary); + thread__update_stats(thread, ttrace, id, sample, ret, trace); if (!trace->fd_path_disabled && sc->is_open && ret >= 0 && ttrace->filename.pending_open) { trace__set_fd_pathname(thread, ret, ttrace->filename.name); @@ -2964,7 +3105,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct evsel *evsel, struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); - struct thread_trace *ttrace = thread__trace(thread, trace->output); + struct thread_trace *ttrace = thread__trace(thread, trace); if (ttrace == NULL) goto out_dump; @@ -3084,7 +3225,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, printed += syscall_arg_fmt__scnprintf_val(arg, bf + printed, size - printed, &syscall_arg, val); } - return printed + fprintf(trace->output, "%.*s", (int)printed, bf); + return fprintf(trace->output, "%.*s", (int)printed, bf); } static int trace__event_handler(struct trace *trace, struct evsel *evsel, @@ -3121,7 +3262,8 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel, if (evsel == trace->syscalls.events.bpf_output) { int id = perf_evsel__sc_tp_uint(evsel, id, sample); - struct syscall *sc = trace__syscall_info(trace, evsel, id); + int e_machine = thread ? thread__e_machine(thread, trace->host) : EM_HOST; + struct syscall *sc = trace__syscall_info(trace, evsel, e_machine, id); if (sc) { fprintf(trace->output, "%s(", sc->name); @@ -3218,14 +3360,17 @@ static int trace__pgfault(struct trace *trace, } } - ttrace = thread__trace(thread, trace->output); + ttrace = thread__trace(thread, trace); if (ttrace == NULL) goto out_put; - if (evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ) + if (evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ) { ttrace->pfmaj++; - else + trace->pfmaj++; + } else { ttrace->pfmin++; + trace->pfmin++; + } if (trace->summary_only) goto out; @@ -3384,6 +3529,7 @@ out_free: } static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); +static size_t trace__fprintf_total_summary(struct trace *trace, FILE *fp); static bool evlist__add_vfs_getname(struct evlist *evlist) { @@ -3624,9 +3770,9 @@ out_unaugmented: return trace->skel->progs.syscall_unaugmented; } -static void trace__init_syscall_bpf_progs(struct trace *trace, int id) +static void trace__init_syscall_bpf_progs(struct trace *trace, int e_machine, int id) { - struct syscall *sc = trace__syscall_info(trace, NULL, id); + struct syscall *sc = trace__syscall_info(trace, NULL, e_machine, id); if (sc == NULL) return; @@ -3635,22 +3781,22 @@ static void trace__init_syscall_bpf_progs(struct trace *trace, int id) sc->bpf_prog.sys_exit = trace__find_syscall_bpf_prog(trace, sc, sc->fmt ? sc->fmt->bpf_prog_name.sys_exit : NULL, "exit"); } -static int trace__bpf_prog_sys_enter_fd(struct trace *trace, int id) +static int trace__bpf_prog_sys_enter_fd(struct trace *trace, int e_machine, int id) { - struct syscall *sc = trace__syscall_info(trace, NULL, id); + struct syscall *sc = trace__syscall_info(trace, NULL, e_machine, id); return sc ? bpf_program__fd(sc->bpf_prog.sys_enter) : bpf_program__fd(trace->skel->progs.syscall_unaugmented); } -static int trace__bpf_prog_sys_exit_fd(struct trace *trace, int id) +static int trace__bpf_prog_sys_exit_fd(struct trace *trace, int e_machine, int id) { - struct syscall *sc = trace__syscall_info(trace, NULL, id); + struct syscall *sc = trace__syscall_info(trace, NULL, e_machine, id); return sc ? bpf_program__fd(sc->bpf_prog.sys_exit) : bpf_program__fd(trace->skel->progs.syscall_unaugmented); } -static int trace__bpf_sys_enter_beauty_map(struct trace *trace, int key, unsigned int *beauty_array) +static int trace__bpf_sys_enter_beauty_map(struct trace *trace, int e_machine, int key, unsigned int *beauty_array) { struct tep_format_field *field; - struct syscall *sc = trace__syscall_info(trace, NULL, key); + struct syscall *sc = trace__syscall_info(trace, NULL, e_machine, key); const struct btf_type *bt; char *struct_offset, *tmp, name[32]; bool can_augment = false; @@ -3732,7 +3878,8 @@ static int trace__bpf_sys_enter_beauty_map(struct trace *trace, int key, unsigne return -1; } -static struct bpf_program *trace__find_usable_bpf_prog_entry(struct trace *trace, struct syscall *sc) +static struct bpf_program *trace__find_usable_bpf_prog_entry(struct trace *trace, + struct syscall *sc) { struct tep_format_field *field, *candidate_field; /* @@ -3746,13 +3893,13 @@ static struct bpf_program *trace__find_usable_bpf_prog_entry(struct trace *trace return NULL; try_to_find_pair: - for (int i = 0; i < trace->sctbl->syscalls.nr_entries; ++i) { - int id = syscalltbl__id_at_idx(trace->sctbl, i); - struct syscall *pair = trace__syscall_info(trace, NULL, id); + for (int i = 0, num_idx = syscalltbl__num_idx(sc->e_machine); i < num_idx; ++i) { + int id = syscalltbl__id_at_idx(sc->e_machine, i); + struct syscall *pair = trace__syscall_info(trace, NULL, sc->e_machine, id); struct bpf_program *pair_prog; bool is_candidate = false; - if (pair == NULL || pair == sc || + if (pair == NULL || pair->id == sc->id || pair->bpf_prog.sys_enter == trace->skel->progs.syscall_unaugmented) continue; @@ -3823,7 +3970,8 @@ try_to_find_pair: goto next_candidate; } - pr_debug("Reusing \"%s\" BPF sys_enter augmenter for \"%s\"\n", pair->name, sc->name); + pr_debug("Reusing \"%s\" BPF sys_enter augmenter for \"%s\"\n", pair->name, + sc->name); return pair_prog; next_candidate: continue; @@ -3832,7 +3980,7 @@ try_to_find_pair: return NULL; } -static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace) +static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace, int e_machine) { int map_enter_fd = bpf_map__fd(trace->skel->maps.syscalls_sys_enter); int map_exit_fd = bpf_map__fd(trace->skel->maps.syscalls_sys_exit); @@ -3840,27 +3988,27 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace) int err = 0; unsigned int beauty_array[6]; - for (int i = 0; i < trace->sctbl->syscalls.nr_entries; ++i) { - int prog_fd, key = syscalltbl__id_at_idx(trace->sctbl, i); + for (int i = 0, num_idx = syscalltbl__num_idx(e_machine); i < num_idx; ++i) { + int prog_fd, key = syscalltbl__id_at_idx(e_machine, i); if (!trace__syscall_enabled(trace, key)) continue; - trace__init_syscall_bpf_progs(trace, key); + trace__init_syscall_bpf_progs(trace, e_machine, key); // It'll get at least the "!raw_syscalls:unaugmented" - prog_fd = trace__bpf_prog_sys_enter_fd(trace, key); + prog_fd = trace__bpf_prog_sys_enter_fd(trace, e_machine, key); err = bpf_map_update_elem(map_enter_fd, &key, &prog_fd, BPF_ANY); if (err) break; - prog_fd = trace__bpf_prog_sys_exit_fd(trace, key); + prog_fd = trace__bpf_prog_sys_exit_fd(trace, e_machine, key); err = bpf_map_update_elem(map_exit_fd, &key, &prog_fd, BPF_ANY); if (err) break; /* use beauty_map to tell BPF how many bytes to collect, set beauty_map's value here */ memset(beauty_array, 0, sizeof(beauty_array)); - err = trace__bpf_sys_enter_beauty_map(trace, key, (unsigned int *)beauty_array); + err = trace__bpf_sys_enter_beauty_map(trace, e_machine, key, (unsigned int *)beauty_array); if (err) continue; err = bpf_map_update_elem(beauty_map_fd, &key, beauty_array, BPF_ANY); @@ -3896,9 +4044,9 @@ static int trace__init_syscalls_bpf_prog_array_maps(struct trace *trace) * first and second arg (this one on the raw_syscalls:sys_exit prog * array tail call, then that one will be used. */ - for (int i = 0; i < trace->sctbl->syscalls.nr_entries; ++i) { - int key = syscalltbl__id_at_idx(trace->sctbl, i); - struct syscall *sc = trace__syscall_info(trace, NULL, key); + for (int i = 0, num_idx = syscalltbl__num_idx(e_machine); i < num_idx; ++i) { + int key = syscalltbl__id_at_idx(e_machine, i); + struct syscall *sc = trace__syscall_info(trace, NULL, e_machine, key); struct bpf_program *pair_prog; int prog_fd; @@ -4019,13 +4167,16 @@ static int __trace__deliver_event(struct trace *trace, union perf_event *event) { struct evlist *evlist = trace->evlist; struct perf_sample sample; - int err = evlist__parse_sample(evlist, event, &sample); + int err; + perf_sample__init(&sample, /*all=*/false); + err = evlist__parse_sample(evlist, event, &sample); if (err) fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err); else trace__handle_event(trace, event, &sample); + perf_sample__exit(&sample); return 0; } @@ -4296,6 +4447,12 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_delete_evlist; } + if (trace->summary_mode == SUMMARY__BY_TOTAL) { + trace->syscall_stats = alloc_syscall_stats(); + if (trace->syscall_stats == NULL) + goto out_delete_evlist; + } + evlist__config(evlist, &trace->opts, &callchain_param); if (forks) { @@ -4319,10 +4476,12 @@ static int trace__run(struct trace *trace, int argc, const char **argv) * CPU the bpf-output event's file descriptor. */ perf_cpu_map__for_each_cpu(cpu, i, trace->syscalls.events.bpf_output->core.cpus) { + int mycpu = cpu.cpu; + bpf_map__update_elem(trace->skel->maps.__augmented_syscalls__, - &cpu.cpu, sizeof(int), + &mycpu, sizeof(mycpu), xyarray__entry(trace->syscalls.events.bpf_output->core.fd, - cpu.cpu, 0), + mycpu, 0), sizeof(__u32), BPF_ANY); } } @@ -4335,8 +4494,13 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_error_mem; #ifdef HAVE_BPF_SKEL - if (trace->skel && trace->skel->progs.sys_enter) - trace__init_syscalls_bpf_prog_array_maps(trace); + if (trace->skel && trace->skel->progs.sys_enter) { + /* + * TODO: Initialize for all host binary machine types, not just + * those matching the perf binary. + */ + trace__init_syscalls_bpf_prog_array_maps(trace, EM_HOST); + } #endif if (trace->ev_qualifier_ids.nr > 0) { @@ -4361,7 +4525,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv) * So just disable this beautifier (SCA_FD, SCA_FDAT) when 'close' is * not in use. */ - trace->fd_path_disabled = !trace__syscall_enabled(trace, syscalltbl__id(trace->sctbl, "close")); + /* TODO: support for more than just perf binary machine type close. */ + trace->fd_path_disabled = !trace__syscall_enabled(trace, syscalltbl__id(EM_HOST, "close")); err = trace__expand_filters(trace, &evsel); if (err) @@ -4456,8 +4621,12 @@ out_disable: ordered_events__flush(&trace->oe.data, OE_FLUSH__FINAL); if (!err) { - if (trace->summary) - trace__fprintf_thread_summary(trace, trace->output); + if (trace->summary) { + if (trace->summary_mode == SUMMARY__BY_TOTAL) + trace__fprintf_total_summary(trace, trace->output); + else + trace__fprintf_thread_summary(trace, trace->output); + } if (trace->show_tool_stats) { fprintf(trace->output, "Stats:\n " @@ -4469,6 +4638,7 @@ out_disable: } out_delete_evlist: + delete_syscall_stats(trace->syscall_stats); trace__symbols__exit(trace); evlist__free_syscall_tp_fields(evlist); evlist__delete(evlist); @@ -4528,6 +4698,7 @@ static int trace__replay(struct trace *trace) struct evsel *evsel; int err = -1; + perf_tool__init(&trace->tool, /*ordered_events=*/true); trace->tool.sample = trace__process_sample; trace->tool.mmap = perf_event__process_mmap; trace->tool.mmap2 = perf_event__process_mmap2; @@ -4596,6 +4767,12 @@ static int trace__replay(struct trace *trace) evsel->handler = trace__pgfault; } + if (trace->summary_mode == SUMMARY__BY_TOTAL) { + trace->syscall_stats = alloc_syscall_stats(); + if (trace->syscall_stats == NULL) + goto out; + } + setup_pager(); err = perf_session__process_events(session); @@ -4606,12 +4783,13 @@ static int trace__replay(struct trace *trace) trace__fprintf_thread_summary(trace, trace->output); out: + delete_syscall_stats(trace->syscall_stats); perf_session__delete(session); return err; } -static size_t trace__fprintf_threads_header(FILE *fp) +static size_t trace__fprintf_summary_header(FILE *fp) { size_t printed; @@ -4620,29 +4798,56 @@ static size_t trace__fprintf_threads_header(FILE *fp) return printed; } -DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs, +struct syscall_entry { struct syscall_stats *stats; double msecs; int syscall; -) +}; + +static int entry_cmp(const void *e1, const void *e2) { - struct int_node *source = rb_entry(nd, struct int_node, rb_node); - struct syscall_stats *stats = source->priv; + const struct syscall_entry *entry1 = e1; + const struct syscall_entry *entry2 = e2; - entry->syscall = source->i; - entry->stats = stats; - entry->msecs = stats ? (u64)stats->stats.n * (avg_stats(&stats->stats) / NSEC_PER_MSEC) : 0; + return entry1->msecs > entry2->msecs ? -1 : 1; } -static size_t thread__dump_stats(struct thread_trace *ttrace, - struct trace *trace, FILE *fp) +static struct syscall_entry *syscall__sort_stats(struct hashmap *syscall_stats) +{ + struct syscall_entry *entry; + struct hashmap_entry *pos; + unsigned bkt, i, nr; + + nr = syscall_stats->sz; + entry = malloc(nr * sizeof(*entry)); + if (entry == NULL) + return NULL; + + i = 0; + hashmap__for_each_entry(syscall_stats, pos, bkt) { + struct syscall_stats *ss = pos->pvalue; + struct stats *st = &ss->stats; + + entry[i].stats = ss; + entry[i].msecs = (u64)st->n * (avg_stats(st) / NSEC_PER_MSEC); + entry[i].syscall = pos->key; + i++; + } + assert(i == nr); + + qsort(entry, nr, sizeof(*entry), entry_cmp); + return entry; +} + +static size_t syscall__dump_stats(struct trace *trace, int e_machine, FILE *fp, + struct hashmap *syscall_stats) { size_t printed = 0; struct syscall *sc; - struct rb_node *nd; - DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats); + struct syscall_entry *entries; - if (syscall_stats == NULL) + entries = syscall__sort_stats(syscall_stats); + if (entries == NULL) return 0; printed += fprintf(fp, "\n"); @@ -4651,8 +4856,10 @@ static size_t thread__dump_stats(struct thread_trace *ttrace, printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n"); printed += fprintf(fp, " --------------- -------- ------ -------- --------- --------- --------- ------\n"); - resort_rb__for_each_entry(nd, syscall_stats) { - struct syscall_stats *stats = syscall_stats_entry->stats; + for (size_t i = 0; i < syscall_stats->sz; i++) { + struct syscall_entry *entry = &entries[i]; + struct syscall_stats *stats = entry->stats; + if (stats) { double min = (double)(stats->stats.min) / NSEC_PER_MSEC; double max = (double)(stats->stats.max) / NSEC_PER_MSEC; @@ -4663,10 +4870,13 @@ static size_t thread__dump_stats(struct thread_trace *ttrace, pct = avg ? 100.0 * stddev_stats(&stats->stats) / avg : 0.0; avg /= NSEC_PER_MSEC; - sc = &trace->syscalls.table[syscall_stats_entry->syscall]; + sc = trace__syscall_info(trace, /*evsel=*/NULL, e_machine, entry->syscall); + if (!sc) + continue; + printed += fprintf(fp, " %-15s", sc->name); printed += fprintf(fp, " %8" PRIu64 " %6" PRIu64 " %9.3f %9.3f %9.3f", - n, stats->nr_failures, syscall_stats_entry->msecs, min, avg); + n, stats->nr_failures, entry->msecs, min, avg); printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct); if (trace->errno_summary && stats->nr_failures) { @@ -4680,16 +4890,28 @@ static size_t thread__dump_stats(struct thread_trace *ttrace, } } - resort_rb__delete(syscall_stats); + free(entries); printed += fprintf(fp, "\n\n"); return printed; } +static size_t thread__dump_stats(struct thread_trace *ttrace, + struct trace *trace, int e_machine, FILE *fp) +{ + return syscall__dump_stats(trace, e_machine, fp, ttrace->syscall_stats); +} + +static size_t system__dump_stats(struct trace *trace, int e_machine, FILE *fp) +{ + return syscall__dump_stats(trace, e_machine, fp, trace->syscall_stats); +} + static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace) { size_t printed = 0; struct thread_trace *ttrace = thread__priv(thread); + int e_machine = thread__e_machine(thread, trace->host); double ratio; if (ttrace == NULL) @@ -4709,7 +4931,7 @@ static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trac else if (fputc('\n', fp) != EOF) ++printed; - printed += thread__dump_stats(ttrace, trace, fp); + printed += thread__dump_stats(ttrace, trace, e_machine, fp); return printed; } @@ -4739,7 +4961,7 @@ static int trace_nr_events_cmp(void *priv __maybe_unused, static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) { - size_t printed = trace__fprintf_threads_header(fp); + size_t printed = trace__fprintf_summary_header(fp); LIST_HEAD(threads); if (machine__thread_list(trace->host, &threads) == 0) { @@ -4754,6 +4976,28 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) return printed; } +static size_t trace__fprintf_total_summary(struct trace *trace, FILE *fp) +{ + size_t printed = trace__fprintf_summary_header(fp); + + printed += fprintf(fp, " total, "); + printed += fprintf(fp, "%lu events", trace->nr_events); + + if (trace->pfmaj) + printed += fprintf(fp, ", %lu majfaults", trace->pfmaj); + if (trace->pfmin) + printed += fprintf(fp, ", %lu minfaults", trace->pfmin); + if (trace->sched) + printed += fprintf(fp, ", %.3f msec\n", trace->runtime_ms); + else if (fputc('\n', fp) != EOF) + ++printed; + + /* TODO: get all system e_machines. */ + printed += system__dump_stats(trace, EM_HOST, fp); + + return printed; +} + static int trace__set_duration(const struct option *opt, const char *str, int unset __maybe_unused) { @@ -4941,8 +5185,9 @@ static int trace__parse_events_option(const struct option *opt, const char *str, *sep = '\0'; list = 0; - if (syscalltbl__id(trace->sctbl, s) >= 0 || - syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) { + /* TODO: support for more than just perf binary machine type syscalls. */ + if (syscalltbl__id(EM_HOST, s) >= 0 || + syscalltbl__strglobmatch_first(EM_HOST, s, &idx) >= 0) { list = 1; goto do_concat; } @@ -5025,6 +5270,23 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u return 0; } +static int trace__parse_summary_mode(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct trace *trace = opt->value; + + if (!strcmp(str, "thread")) { + trace->summary_mode = SUMMARY__BY_THREAD; + } else if (!strcmp(str, "total")) { + trace->summary_mode = SUMMARY__BY_TOTAL; + } else { + pr_err("Unknown summary mode: %s\n", str); + return -1; + } + + return 0; +} + static int trace__config(const char *var, const char *value, void *arg) { struct trace *trace = arg; @@ -5071,17 +5333,20 @@ out: static void trace__exit(struct trace *trace) { - int i; - strlist__delete(trace->ev_qualifier); zfree(&trace->ev_qualifier_ids.entries); if (trace->syscalls.table) { - for (i = 0; i <= trace->sctbl->syscalls.max_id; i++) - syscall__exit(&trace->syscalls.table[i]); + for (size_t i = 0; i < trace->syscalls.table_size; i++) + syscall__delete(trace->syscalls.table[i]); zfree(&trace->syscalls.table); } - syscalltbl__delete(trace->sctbl); zfree(&trace->perfconfig_events); + evlist__delete(trace->evlist); + trace->evlist = NULL; +#ifdef HAVE_LIBBPF_SUPPORT + btf__free(trace->btf); + trace->btf = NULL; +#endif } #ifdef HAVE_BPF_SKEL @@ -5172,6 +5437,9 @@ int cmd_trace(int argc, const char **argv) "Show all syscalls and summary with statistics"), OPT_BOOLEAN(0, "errno-summary", &trace.errno_summary, "Show errno stats per syscall, use with -s or -S"), + OPT_CALLBACK(0, "summary-mode", &trace, "mode", + "How to show summary: select thread (default) or total", + trace__parse_summary_mode), OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min", "Trace pagefaults", parse_pagefaults, "maj"), OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"), @@ -5226,9 +5494,8 @@ int cmd_trace(int argc, const char **argv) sigaction(SIGCHLD, &sigchld_act, NULL); trace.evlist = evlist__new(); - trace.sctbl = syscalltbl__new(); - if (trace.evlist == NULL || trace.sctbl == NULL) { + if (trace.evlist == NULL) { pr_err("Not enough memory to run!\n"); err = -ENOMEM; goto out; @@ -5456,8 +5723,10 @@ init_augmented_syscall_tp: } } - if ((argc >= 1) && (strcmp(argv[0], "record") == 0)) - return trace__record(&trace, argc-1, &argv[1]); + if ((argc >= 1) && (strcmp(argv[0], "record") == 0)) { + err = trace__record(&trace, argc-1, &argv[1]); + goto out; + } /* Using just --errno-summary will trigger --summary */ if (trace.errno_summary && !trace.summary && !trace.summary_only) @@ -5468,8 +5737,11 @@ init_augmented_syscall_tp: trace.summary = trace.summary_only; /* Keep exited threads, otherwise information might be lost for summary */ - if (trace.summary) + if (trace.summary) { symbol_conf.keep_exited_threads = true; + if (trace.summary_mode == SUMMARY__NONE) + trace.summary_mode = SUMMARY__BY_THREAD; + } if (output_name != NULL) { err = trace__open_output(&trace, output_name); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index d3c6e10dce73..a4499e5a6f9c 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -26,8 +26,6 @@ FILES=( "include/linux/hash.h" "include/linux/list-sort.h" "include/uapi/linux/hw_breakpoint.h" - "arch/x86/include/asm/disabled-features.h" - "arch/x86/include/asm/required-features.h" "arch/x86/include/asm/cpufeatures.h" "arch/x86/include/asm/inat_types.h" "arch/x86/include/asm/emulate_prefix.h" diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index d941bc9d16e9..32f387d48908 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -41,7 +41,30 @@ $(EMPTY_PMU_EVENTS_TEST_LOG): $(EMPTY_PMU_EVENTS_C) $(TEST_EMPTY_PMU_EVENTS_C) $(call rule_mkdir) $(Q)$(call echo-cmd,test)diff -u $^ 2> $@ || (cat $@ && false) -$(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_LOG) $(EMPTY_PMU_EVENTS_TEST_LOG) +ifdef MYPY + PMU_EVENTS_PY_TESTS := $(wildcard *.py) + PMU_EVENTS_MYPY_TEST_LOGS := $(JEVENTS_PY_TESTS:%=%.mypy_log) +else + PMU_EVENTS_MYPY_TEST_LOGS := +endif + +$(OUTPUT)%.mypy_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false) + +ifdef PYLINT + PMU_EVENTS_PY_TESTS := $(wildcard *.py) + PMU_EVENTS_PYLINT_TEST_LOGS := $(JEVENTS_PY_TESTS:%=%.pylint_log) +else + PMU_EVENTS_PYLINT_TEST_LOGS := +endif + +$(OUTPUT)%.pylint_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false) + +$(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_LOG) \ + $(EMPTY_PMU_EVENTS_TEST_LOG) $(PMU_EVENTS_MYPY_TEST_LOGS) $(PMU_EVENTS_PYLINT_TEST_LOGS) $(call rule_mkdir) $(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(JEVENTS_ARCH) $(JEVENTS_MODEL) pmu-events/arch $@ endif diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/memory.json index 0711782bfa6b..13382d29b25f 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/memory.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/memory.json @@ -1,6 +1,8 @@ [ { - "ArchStdEvent": "LD_RETIRED" + "ArchStdEvent": "LD_RETIRED", + "Errata": "Errata AC03_CPU_52", + "BriefDescription": "Instruction architecturally executed, condition code check pass, load. Impacted by errata -" }, { "ArchStdEvent": "MEM_ACCESS_RD" diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json index a211d94aacde..6c06bc928415 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json @@ -1,6 +1,8 @@ [ { - "ArchStdEvent": "LD_RETIRED" + "ArchStdEvent": "LD_RETIRED", + "Errata": "Errata AC04_CPU_21", + "BriefDescription": "Instruction architecturally executed, condition code check pass, load. Impacted by errata -" }, { "ArchStdEvent": "MEM_ACCESS_RD" diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json index c5d1d22bd034..5228f94a793f 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json @@ -229,19 +229,19 @@ }, { "MetricName": "slots_lost_misspeculation_fraction", - "MetricExpr": "(OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)", + "MetricExpr": "100 * (OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)", "BriefDescription": "Fraction of slots lost due to misspeculation", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", - "ScaleUnit": "100percent of slots" + "ScaleUnit": "1percent of slots" }, { "MetricName": "retired_fraction", - "MetricExpr": "OP_RETIRED / (CPU_CYCLES * #slots)", + "MetricExpr": "100 * OP_RETIRED / (CPU_CYCLES * #slots)", "BriefDescription": "Fraction of slots retiring, useful work", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", - "ScaleUnit": "100percent of slots" + "ScaleUnit": "1percent of slots" }, { "MetricName": "backend_core", @@ -266,7 +266,7 @@ }, { "MetricName": "frontend_bandwidth", - "MetricExpr": "frontend_bound - frontend_latency", + "MetricExpr": "frontend_bound - 100 * frontend_latency", "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)", "MetricGroup": "TopdownL2", "ScaleUnit": "1percent of slots" diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/bus.json new file mode 100644 index 000000000000..2e11a8c4a484 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/bus.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "BUS_ACCESS", + "PublicDescription": "Counts memory transactions issued by the CPU to the external bus, including snoop requests and snoop responses. Each beat of data is counted individually." + }, + { + "ArchStdEvent": "BUS_CYCLES", + "PublicDescription": "Counts bus cycles in the CPU. Bus cycles represent a clock cycle in which a transaction could be sent or received on the interface from the CPU to the external bus. Since that interface is driven at the same clock speed as the CPU, this event is a duplicate of CPU_CYCLES." + }, + { + "ArchStdEvent": "BUS_ACCESS_RD", + "PublicDescription": "Counts memory read transactions seen on the external bus. Each beat of data is counted individually." + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + "PublicDescription": "Counts memory write transactions seen on the external bus. Each beat of data is counted individually." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/exception.json new file mode 100644 index 000000000000..7126fbf292e0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/exception.json @@ -0,0 +1,62 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN", + "PublicDescription": "Counts any taken architecturally visible exceptions such as IRQ, FIQ, SError, and other synchronous exceptions. Exceptions are counted whether or not they are taken locally." + }, + { + "ArchStdEvent": "EXC_RETURN", + "PublicDescription": "Counts any architecturally executed exception return instructions. For example: AArch64: ERET" + }, + { + "ArchStdEvent": "EXC_UNDEF", + "PublicDescription": "Counts the number of synchronous exceptions which are taken locally that are due to attempting to execute an instruction that is UNDEFINED. Attempting to execute instruction bit patterns that have not been allocated. Attempting to execute instructions when they are disabled. Attempting to execute instructions at an inappropriate Exception level. Attempting to execute an instruction when the value of PSTATE.IL is 1." + }, + { + "ArchStdEvent": "EXC_SVC", + "PublicDescription": "Counts SVC exceptions taken locally." + }, + { + "ArchStdEvent": "EXC_PABORT", + "PublicDescription": "Counts synchronous exceptions that are taken locally and caused by Instruction Aborts." + }, + { + "ArchStdEvent": "EXC_DABORT", + "PublicDescription": "Counts exceptions that are taken locally and are caused by data aborts or SErrors. Conditions that could cause those exceptions are attempting to read or write memory where the MMU generates a fault, attempting to read or write memory with a misaligned address, interrupts from the nSEI inputs and internally generated SErrors." + }, + { + "ArchStdEvent": "EXC_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are taken locally." + }, + { + "ArchStdEvent": "EXC_FIQ", + "PublicDescription": "Counts FIQ exceptions including the virtual FIQs that are taken locally." + }, + { + "ArchStdEvent": "EXC_SMC", + "PublicDescription": "Counts SMC exceptions take to EL3." + }, + { + "ArchStdEvent": "EXC_HVC", + "PublicDescription": "Counts HVC exceptions taken to EL2." + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Instruction Aborts. For example, attempting to execute an instruction with a misaligned PC." + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Data Aborts or SError interrupts. Conditions that could cause those exceptions are:\n\n1. Attempting to read or write memory where the MMU generates a fault,\n2. Attempting to read or write memory with a misaligned address,\n3. Interrupts from the SEI input.\n4. internally generated SErrors." + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + "PublicDescription": "Counts the number of synchronous trap exceptions which are not taken locally and are not SVC, SMC, HVC, data aborts, Instruction Aborts, or interrupts." + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are not taken locally." + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + "PublicDescription": "Counts FIQs which are not taken locally but taken from EL0, EL1,\n or EL2 to EL3 (which would be the normal behavior for FIQs when not executing\n in EL3)." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/fp_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/fp_operation.json new file mode 100644 index 000000000000..cec3435ac766 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/fp_operation.json @@ -0,0 +1,22 @@ +[ + { + "ArchStdEvent": "FP_HP_SPEC", + "PublicDescription": "Counts speculatively executed half precision floating point operations." + }, + { + "ArchStdEvent": "FP_SP_SPEC", + "PublicDescription": "Counts speculatively executed single precision floating point operations." + }, + { + "ArchStdEvent": "FP_DP_SPEC", + "PublicDescription": "Counts speculatively executed double precision floating point operations." + }, + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC", + "PublicDescription": "Counts speculatively executed scalable single precision floating point operations." + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC", + "PublicDescription": "Counts speculatively executed non-scalable single precision floating point operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/general.json new file mode 100644 index 000000000000..c5dcdcf43c58 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/general.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES", + "PublicDescription": "Counts CPU clock cycles (not timer cycles). The clock measured by this event is defined as the physical clock driving the CPU logic." + }, + { + "ArchStdEvent": "CNT_CYCLES", + "PublicDescription": "Increments at a constant frequency equal to the rate of increment of the System Counter, CNTPCT_EL0." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l1d_cache.json new file mode 100644 index 000000000000..ee04d9fe1a70 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l1d_cache.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_REFILL", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE", + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) counts as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." + }, + { + "ArchStdEvent": "L1D_CACHE_WB", + "PublicDescription": "Counts write-backs of dirty data from the L1 data cache to the L2 cache. This occurs when either a dirty cache line is evicted from L1 data cache and allocated in the L2 cache or dirty data is written to the L2 and possibly to the next level of cache. This event counts both victim cache line evictions and cache write-backs from snoops or cache maintenance operations. The following cache operations are not counted:\n\n1. Invalidations which do not result in data being transferred out of the L1 (such as evictions of clean data),\n2. Full line writes which write to L2 without writing L1, such as write streaming mode." + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 1 data cache from any memory read operations, that incurred additional latency." + }, + { + "ArchStdEvent": "L1D_CACHE_RD", + "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches counts as both a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + "PublicDescription": "Counts level 1 data cache accesses generated by store operations. This event also counts accesses caused by a DC ZVA (data cache zero, specified by virtual address) instruction. Near atomic operations that resolve in the CPUs caches count as a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + "PublicDescription": "Counts level 1 data cache refills where the cache line data came from caches inside the immediate cluster of the core." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + "PublicDescription": "Counts level 1 data cache refills for which the cache line data came from outside the immediate cluster of the core, like an SLC in the system interconnect or DRAM." + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 1 data cache caused by:\n\n- Cache Maintenance Operations (CMO) that operate by a virtual address.\n- Broadcast cache coherency operations from another CPU in the system.\n\nThis event does not count for the following conditions:\n\n1. A cache refill invalidates a cache line.\n2. A CMO which is executed on that CPU and invalidates a cache line specified by set/way.\n\nNote that CMOs that operate by set/way cannot be broadcast from one CPU to another." + }, + { + "ArchStdEvent": "L1D_CACHE_RW", + "PublicDescription": "Counts level 1 data demand cache accesses from any load or store operation. Near atomic operations that resolve in the CPUs caches counts as both a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_HWPRF", + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations generated by the hardware prefetcher." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_HWPRF", + "PublicDescription": "Counts level 1 data cache refills where the cache line is requested by a hardware prefetcher." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l1i_cache.json new file mode 100644 index 000000000000..633f1030359d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l1i_cache.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL", + "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once." + }, + { + "ArchStdEvent": "L1I_CACHE", + "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted." + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS", + "PublicDescription": "Counts cache line refills into the level 1 instruction cache, that incurred additional latency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l2_cache.json new file mode 100644 index 000000000000..e6cce710c560 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l2_cache.json @@ -0,0 +1,78 @@ +[ + { + "ArchStdEvent": "L2D_CACHE", + "PublicDescription": "Counts accesses to the level 2 cache due to data accesses. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level data cache or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL", + "PublicDescription": "Counts cache line refills into the level 2 cache. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB", + "PublicDescription": "Counts write-backs of data from the L2 cache to outside the CPU. This includes snoops to the L2 (from other CPUs) which return data even if the snoops cause an invalidation. L2 cache line invalidations which do not write data outside the CPU and snoops which return data from an L1 cache are not counted. Data would not be written outside the cache when invalidating a clean cache line." + }, + { + "ArchStdEvent": "L2D_CACHE_ALLOCATE", + "PublicDescription": "Counts level 2 cache line allocates that do not fetch data from outside the level 2 data or unified cache." + }, + { + "ArchStdEvent": "L2I_CACHE", + "PublicDescription": "Counts accesses to the level 2 cache due to instruction accesses. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level instruction cache." + }, + { + "ArchStdEvent": "L2I_CACHE_REFILL", + "PublicDescription": "Counts cache line refills into the level 2 cache. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 instruction cache." + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + "PublicDescription": "Counts level 2 data cache accesses due to memory read operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + "PublicDescription": "Counts level 2 cache accesses due to memory write operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + "PublicDescription": "Counts evictions from the level 2 cache because of a line being allocated into the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 2 cache that are a result of either:\n\n1. Cache maintenance operations,\n\n2. Snoop responses or,\n\n3. Direct cache transfers to another CPU due to a forwarding snoop request." + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 2 cache by cache maintenance operations that operate by a virtual address, or by external coherency operations. This event does not count if either:\n\n1. A cache refill invalidates a cache line or,\n2. A Cache Maintenance Operation (CMO), which invalidates a cache line specified by set/way, is executed on that CPU.\n\nCMOs that operate by set/way cannot be broadcast from one CPU to another." + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 2 unified cache from any memory read operations that incurred additional latency." + }, + { + "ArchStdEvent": "L2I_CACHE_LMISS", + "PublicDescription": "Counts cache line refills into the level 2 unified cache from any instruction read operations that incurred additional latency." + }, + { + "ArchStdEvent": "L2D_CACHE_RW", + "PublicDescription": "Counts level 2 cache demand accesses from any load/store operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2I_CACHE_RD", + "PublicDescription": "Counts level 2 cache accesses that are due to a demand instruction cache access." + }, + { + "ArchStdEvent": "L2D_CACHE_PRF", + "PublicDescription": "Counts level 2 data cache accesses from software preload or prefetch instructions or hardware prefetcher." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_PRF", + "PublicDescription": "Counts refills due to accesses generated as a result of prefetches." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l3_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l3_cache.json new file mode 100644 index 000000000000..8fe51a628419 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/l3_cache.json @@ -0,0 +1,26 @@ +[ + { + "ArchStdEvent": "L3D_CACHE_ALLOCATE", + "PublicDescription": "Counts level 3 cache line allocates that do not fetch data from outside the level 3 data or unified cache. For example, allocates due to streaming stores." + }, + { + "ArchStdEvent": "L3D_CACHE_REFILL", + "PublicDescription": "Counts level 3 accesses that receive data from outside the L3 cache." + }, + { + "ArchStdEvent": "L3D_CACHE", + "PublicDescription": "Counts level 3 cache accesses. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L3D_CACHE_RD", + "PublicDescription": "Counts level 3 cache accesses caused by any memory read operation. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD", + "PublicDescription": "Counts any cache line refill into the level 3 cache from memory read operations that incurred additional latency." + }, + { + "ArchStdEvent": "L3D_CACHE_MISS", + "PublicDescription": "Counts level 3 cache accesses that missed in the level 3 cache." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/ll_cache.json new file mode 100644 index 000000000000..c9259682d39e --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/ll_cache.json @@ -0,0 +1,22 @@ +[ + { + "ArchStdEvent": "LL_CACHE", + "PublicDescription": "Counts transactions that were returned from outside the core cluster. This event counts transactions for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts transactions for L3 cache." + }, + { + "ArchStdEvent": "LL_CACHE_MISS", + "PublicDescription": "Counts transactions that were returned from outside the core cluster and missed in the last level cache" + }, + { + "ArchStdEvent": "LL_CACHE_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for the L3 cache. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for L3 cache. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." + }, + { + "ArchStdEvent": "LL_CACHE_REFILL", + "PublicDescription": "Counts last level accesses that receive data from outside the last level cache." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/memory.json new file mode 100644 index 000000000000..f19204a5faae --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/memory.json @@ -0,0 +1,54 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS", + "PublicDescription": "Counts memory accesses issued by the CPU load store unit, where those accesses are issued due to load or store operations. This event counts memory accesses no matter whether the data is received from any level of cache hierarchy or external memory. If memory accesses are broken up into smaller transactions than what were specified in the load or store instructions, then the event counts those smaller memory transactions." + }, + { + "ArchStdEvent": "REMOTE_ACCESS", + "PublicDescription": "Counts accesses to another chip, which is implemented as a different CMN mesh in the system. If the CHI bus response back to the core indicates that the data source is from another chip (mesh), then the counter is updated. If no data is returned, even if the system snoops another chip/mesh, then the counter is not updated." + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + "PublicDescription": "Counts memory accesses issued by the CPU due to load operations. The event counts any memory load access, no matter whether the data is received from any level of cache hierarchy or external memory. The event also counts atomic load operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + "PublicDescription": "Counts memory accesses issued by the CPU due to store operations. The event counts any memory store access, no matter whether the data is located in any level of cache or external memory. The event also counts atomic load and store operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." + }, + { + "ArchStdEvent": "LDST_ALIGN_LAT", + "PublicDescription": "Counts the number of memory read and write accesses in a cycle that incurred additional latency, due to the alignment of the address and the size of data being accessed, which results in store crossing a single cache line." + }, + { + "ArchStdEvent": "LD_ALIGN_LAT", + "PublicDescription": "Counts the number of memory read accesses in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed, which results in load crossing a single cache line." + }, + { + "ArchStdEvent": "ST_ALIGN_LAT", + "PublicDescription": "Counts the number of memory write access in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed incurred additional latency." + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED", + "PublicDescription": "Counts the number of memory read and write accesses counted by MEM_ACCESS that are tag checked by the Memory Tagging Extension (MTE). This event is implemented as the sum of MEM_ACCESS_CHECKED_RD and MEM_ACCESS_CHECKED_WR" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_RD", + "PublicDescription": "Counts the number of memory read accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)." + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_WR", + "PublicDescription": "Counts the number of memory write accesses in a cycle that is tag checked by the Memory Tagging Extension (MTE)." + }, + { + "ArchStdEvent": "INST_FETCH_PERCYC", + "PublicDescription": "Counts number of instruction fetches outstanding per cycle, which will provide an average latency of instruction fetch." + }, + { + "ArchStdEvent": "MEM_ACCESS_RD_PERCYC", + "PublicDescription": "Counts the number of outstanding loads or memory read accesses per cycle." + }, + { + "ArchStdEvent": "INST_FETCH", + "PublicDescription": "Counts Instruction memory accesses that the PE makes." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/metrics.json new file mode 100644 index 000000000000..eb3a35f244e7 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/metrics.json @@ -0,0 +1,457 @@ +[ + { + "ArchStdEvent": "backend_bound" + }, + { + "MetricName": "backend_busy_bound", + "MetricExpr": "STALL_BACKEND_BUSY / STALL_BACKEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to issue queues being full to accept operations for execution.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_cache_l1d_bound", + "MetricExpr": "STALL_BACKEND_L1D / (STALL_BACKEND_L1D + STALL_BACKEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory access latency issues caused by level 1 data cache misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_cache_l2d_bound", + "MetricExpr": "STALL_BACKEND_MEM / (STALL_BACKEND_L1D + STALL_BACKEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory access latency issues caused by level 2 data cache misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_core_bound", + "MetricExpr": "STALL_BACKEND_CPUBOUND / STALL_BACKEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to backend core resource constraints not related to instruction fetch latency issues caused by memory access components.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_core_rename_bound", + "MetricExpr": "STALL_BACKEND_RENAME / STALL_BACKEND_CPUBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend as the rename unit registers are unavailable.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_bound", + "MetricExpr": "STALL_BACKEND_MEMBOUND / STALL_BACKEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to backend core resource constraints related to memory access latency issues caused by memory access components.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_cache_bound", + "MetricExpr": "(STALL_BACKEND_L1D + STALL_BACKEND_MEM) / STALL_BACKEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory latency issues caused by data cache misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_store_bound", + "MetricExpr": "STALL_BACKEND_ST / STALL_BACKEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to memory write pending caused by stores stalled in the pre-commit stage.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_tlb_bound", + "MetricExpr": "STALL_BACKEND_TLB / STALL_BACKEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory access latency issues caused by data TLB misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_stalled_cycles", + "MetricExpr": "STALL_BACKEND / CPU_CYCLES * 100", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "ArchStdEvent": "bad_speculation", + "MetricExpr": "(1 - STALL_SLOT / (5 * CPU_CYCLES)) * (1 - OP_RETIRED / OP_SPEC) * 100 + STALL_FRONTEND_FLUSH / CPU_CYCLES * 100" + }, + { + "MetricName": "barrier_percentage", + "MetricExpr": "(ISB_SPEC + DSB_SPEC + DMB_SPEC) / INST_SPEC * 100", + "BriefDescription": "This metric measures instruction and data barrier operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "branch_direct_ratio", + "MetricExpr": "BR_IMMED_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of direct branches retired to the total number of branches architecturally executed.", + "MetricGroup": "Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "branch_indirect_ratio", + "MetricExpr": "BR_IND_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of indirect branches retired, including function returns, to the total number of branches architecturally executed.", + "MetricGroup": "Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "branch_misprediction_ratio", + "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.", + "MetricGroup": "Miss_Ratio;Branch_Effectiveness", + "ScaleUnit": "100percent of branches" + }, + { + "MetricName": "branch_mpki", + "MetricExpr": "BR_MIS_PRED_RETIRED / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.", + "MetricGroup": "MPKI;Branch_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "branch_percentage", + "MetricExpr": "PC_WRITE_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "branch_return_ratio", + "MetricExpr": "BR_RETURN_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of branches retired that are function returns to the total number of branches architecturally executed.", + "MetricGroup": "Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "crypto_percentage", + "MetricExpr": "CRYPTO_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "dtlb_mpki", + "MetricExpr": "DTLB_WALK / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "dtlb_walk_ratio", + "MetricExpr": "DTLB_WALK / L1D_TLB", + "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "fp16_percentage", + "MetricExpr": "FP_HP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures half-precision floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "FP_Precision_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "fp32_percentage", + "MetricExpr": "FP_SP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures single-precision floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "FP_Precision_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "fp64_percentage", + "MetricExpr": "FP_DP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures double-precision floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "FP_Precision_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "fp_ops_per_cycle", + "MetricExpr": "(FP_SCALE_OPS_SPEC + FP_FIXED_OPS_SPEC) / CPU_CYCLES", + "BriefDescription": "This metric measures floating point operations per cycle in any precision performed by any instruction. Operations are counted by computation and by vector lanes, fused computations such as multiply-add count as twice per vector lane for example.", + "MetricGroup": "FP_Arithmetic_Intensity", + "ScaleUnit": "1operations per cycle" + }, + { + "ArchStdEvent": "frontend_bound", + "MetricExpr": "(STALL_SLOT_FRONTEND / (5 * CPU_CYCLES) - STALL_FRONTEND_FLUSH / CPU_CYCLES) * 100" + }, + { + "MetricName": "frontend_cache_l1i_bound", + "MetricExpr": "STALL_FRONTEND_L1I / (STALL_FRONTEND_L1I + STALL_FRONTEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to memory access latency issues caused by level 1 instruction cache misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_cache_l2i_bound", + "MetricExpr": "STALL_FRONTEND_MEM / (STALL_FRONTEND_L1I + STALL_FRONTEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to memory access latency issues caused by level 2 instruction cache misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_core_bound", + "MetricExpr": "STALL_FRONTEND_CPUBOUND / STALL_FRONTEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to frontend core resource constraints not related to instruction fetch latency issues caused by memory access components.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_core_flow_bound", + "MetricExpr": "STALL_FRONTEND_FLOW / STALL_FRONTEND_CPUBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend as the decode unit is awaiting input from the branch prediction unit.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_core_flush_bound", + "MetricExpr": "STALL_FRONTEND_FLUSH / STALL_FRONTEND_CPUBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend as the processor is recovering from a pipeline flush caused by bad speculation or other machine resteers.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_mem_bound", + "MetricExpr": "STALL_FRONTEND_MEMBOUND / STALL_FRONTEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to frontend core resource constraints related to the instruction fetch latency issues caused by memory access components.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_mem_cache_bound", + "MetricExpr": "(STALL_FRONTEND_L1I + STALL_FRONTEND_MEM) / STALL_FRONTEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to instruction fetch latency issues caused by instruction cache misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_mem_tlb_bound", + "MetricExpr": "STALL_FRONTEND_TLB / STALL_FRONTEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to instruction fetch latency issues caused by instruction TLB misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_stalled_cycles", + "MetricExpr": "STALL_FRONTEND / CPU_CYCLES * 100", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "integer_dp_percentage", + "MetricExpr": "(DP_SPEC - DSB_SPEC) / INST_SPEC * 100", + "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "ipc", + "MetricExpr": "INST_RETIRED / CPU_CYCLES", + "BriefDescription": "This metric measures the number of instructions retired per cycle.", + "MetricGroup": "General", + "ScaleUnit": "1per cycle" + }, + { + "MetricName": "itlb_mpki", + "MetricExpr": "ITLB_WALK / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "itlb_walk_ratio", + "MetricExpr": "ITLB_WALK / L1I_TLB", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l1d_cache_miss_ratio", + "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", + "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", + "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "l1d_cache_mpki", + "MetricExpr": "L1D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1D_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1d_tlb_miss_ratio", + "MetricExpr": "L1D_TLB_REFILL / L1D_TLB", + "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l1d_tlb_mpki", + "MetricExpr": "L1D_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 data TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_cache_miss_ratio", + "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", + "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", + "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "l1i_cache_mpki", + "MetricExpr": "L1I_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1I_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_tlb_miss_ratio", + "MetricExpr": "L1I_TLB_REFILL / L1I_TLB", + "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l1i_tlb_mpki", + "MetricExpr": "L1I_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_cache_miss_ratio", + "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", + "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "l2_cache_mpki", + "MetricExpr": "L2D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "MPKI;L2_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_tlb_miss_ratio", + "MetricExpr": "L2D_TLB_REFILL / L2D_TLB", + "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l2_tlb_mpki", + "MetricExpr": "L2D_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "ll_cache_read_hit_ratio", + "MetricExpr": "(LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD", + "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "LL_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "ll_cache_read_miss_ratio", + "MetricExpr": "LL_CACHE_MISS_RD / LL_CACHE_RD", + "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "ll_cache_read_mpki", + "MetricExpr": "LL_CACHE_MISS_RD / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;LL_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "load_percentage", + "MetricExpr": "LD_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "nonsve_fp_ops_per_cycle", + "MetricExpr": "FP_FIXED_OPS_SPEC / CPU_CYCLES", + "BriefDescription": "This metric measures floating point operations per cycle in any precision performed by an instruction that is not an SVE instruction. Operations are counted by computation and by vector lanes, fused computations such as multiply-add count as twice per vector lane for example.", + "MetricGroup": "FP_Arithmetic_Intensity", + "ScaleUnit": "1operations per cycle" + }, + { + "ArchStdEvent": "retiring" + }, + { + "MetricName": "scalar_fp_percentage", + "MetricExpr": "VFP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "simd_percentage", + "MetricExpr": "ASE_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "store_percentage", + "MetricExpr": "ST_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_all_percentage", + "MetricExpr": "SVE_INST_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations, including loads and stores, as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_fp_ops_per_cycle", + "MetricExpr": "FP_SCALE_OPS_SPEC / CPU_CYCLES", + "BriefDescription": "This metric measures floating point operations per cycle in any precision performed by SVE instructions. Operations are counted by computation and by vector lanes, fused computations such as multiply-add count as twice per vector lane for example.", + "MetricGroup": "FP_Arithmetic_Intensity", + "ScaleUnit": "1operations per cycle" + }, + { + "MetricName": "sve_predicate_empty_percentage", + "MetricExpr": "SVE_PRED_EMPTY_SPEC / SVE_PRED_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with no active predicates as a percentage of sve predicated operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_predicate_full_percentage", + "MetricExpr": "SVE_PRED_FULL_SPEC / SVE_PRED_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with all active predicates as a percentage of sve predicated operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_predicate_partial_percentage", + "MetricExpr": "SVE_PRED_PARTIAL_SPEC / SVE_PRED_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with at least one active predicates as a percentage of sve predicated operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_predicate_percentage", + "MetricExpr": "SVE_PRED_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with predicates as a percentage of operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/retired.json new file mode 100644 index 000000000000..135e5dbd8c78 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/retired.json @@ -0,0 +1,90 @@ +[ + { + "ArchStdEvent": "SW_INCR", + "PublicDescription": "Counts software writes to the PMSWINC_EL0 (software PMU increment) register. The PMSWINC_EL0 register is a manually updated counter for use by application software.\n\nThis event could be used to measure any user program event, such as accesses to a particular data structure (by writing to the PMSWINC_EL0 register each time the data structure is accessed).\n\nTo use the PMSWINC_EL0 register and event, developers must insert instructions that write to the PMSWINC_EL0 register into the source code.\n\nSince the SW_INCR event records writes to the PMSWINC_EL0 register, there is no need to do a read/increment/write sequence to the PMSWINC_EL0 register." + }, + { + "ArchStdEvent": "INST_RETIRED", + "PublicDescription": "Counts instructions that have been architecturally executed." + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED", + "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR_EL1 register, which usually contain the kernel PID and can be output with hardware trace." + }, + { + "ArchStdEvent": "PC_WRITE_RETIRED", + "PublicDescription": "Counts branch instructions that caused a change of Program Counter, which effectively causes a change in the control flow of the program." + }, + { + "ArchStdEvent": "BR_IMMED_RETIRED", + "PublicDescription": "Counts architecturally executed direct branches." + }, + { + "ArchStdEvent": "BR_RETURN_RETIRED", + "PublicDescription": "Counts architecturally executed procedure returns." + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED", + "PublicDescription": "Counts architectural writes to TTBR0/1_EL1. If virtualization host extensions are enabled (by setting the HCR_EL2.E2H bit to 1), then accesses to TTBR0/1_EL1 that are redirected to TTBR0/1_EL2, or accesses to TTBR0/1_EL12, are counted. TTBRn registers are typically updated when the kernel is swapping user-space threads or applications." + }, + { + "ArchStdEvent": "BR_RETIRED", + "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted. Note that exception generating instructions, exception return instructions and context synchronization instructions are not counted." + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "PublicDescription": "Counts branches counted by BR_RETIRED which were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "OP_RETIRED", + "PublicDescription": "Counts micro-operations that are architecturally executed. This is a count of number of micro-operations retired from the commit queue in a single cycle." + }, + { + "ArchStdEvent": "BR_IMMED_TAKEN_RETIRED", + "PublicDescription": "Counts architecturally executed direct branches that were taken." + }, + { + "ArchStdEvent": "BR_INDNR_TAKEN_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches excluding procedure returns that were taken." + }, + { + "ArchStdEvent": "BR_IMMED_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed direct branches that were correctly predicted." + }, + { + "ArchStdEvent": "BR_IMMED_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed direct branches that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_IND_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches including procedure returns that were correctly predicted." + }, + { + "ArchStdEvent": "BR_IND_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches including procedure returns that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_RETURN_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed procedure returns that were correctly predicted." + }, + { + "ArchStdEvent": "BR_RETURN_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed procedure returns that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_INDNR_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches excluding procedure returns that were correctly predicted." + }, + { + "ArchStdEvent": "BR_INDNR_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches excluding procedure returns that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_PRED_RETIRED", + "PublicDescription": "Counts branch instructions counted by BR_RETIRED which were correctly predicted." + }, + { + "ArchStdEvent": "BR_IND_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches including procedure returns." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/spe.json new file mode 100644 index 000000000000..ca0217fa4681 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/spe.json @@ -0,0 +1,42 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP", + "PublicDescription": "Counts statistical profiling sample population, the count of all operations that could be sampled but may or may not be chosen for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FEED", + "PublicDescription": "Counts statistical profiling samples taken for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE", + "PublicDescription": "Counts statistical profiling samples taken which are not removed by filtering." + }, + { + "ArchStdEvent": "SAMPLE_COLLISION", + "PublicDescription": "Counts statistical profiling samples that have collided with a previous sample and so therefore not taken." + }, + { + "ArchStdEvent": "SAMPLE_FEED_BR", + "PublicDescription": "Counts statistical profiling samples taken which are branches." + }, + { + "ArchStdEvent": "SAMPLE_FEED_LD", + "PublicDescription": "Counts statistical profiling samples taken which are loads or load atomic operations." + }, + { + "ArchStdEvent": "SAMPLE_FEED_ST", + "PublicDescription": "Counts statistical profiling samples taken which are stores or store atomic operations." + }, + { + "ArchStdEvent": "SAMPLE_FEED_OP", + "PublicDescription": "Counts statistical profiling samples taken which are matching any operation type filters supported." + }, + { + "ArchStdEvent": "SAMPLE_FEED_EVENT", + "PublicDescription": "Counts statistical profiling samples taken which are matching event packet filter constraints." + }, + { + "ArchStdEvent": "SAMPLE_FEED_LAT", + "PublicDescription": "Counts statistical profiling samples taken which are exceeding minimum latency set by operation latency filter constraints." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/spec_operation.json new file mode 100644 index 000000000000..f91eb18d683c --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/spec_operation.json @@ -0,0 +1,90 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED", + "PublicDescription": "Counts branches which are speculatively executed and mispredicted." + }, + { + "ArchStdEvent": "BR_PRED", + "PublicDescription": "Counts all speculatively executed branches." + }, + { + "ArchStdEvent": "INST_SPEC", + "PublicDescription": "Counts operations that have been speculatively executed." + }, + { + "ArchStdEvent": "OP_SPEC", + "PublicDescription": "Counts micro-operations speculatively executed. This is the count of the number of micro-operations dispatched in a cycle." + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have not successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed." + }, + { + "ArchStdEvent": "LD_SPEC", + "PublicDescription": "Counts speculatively executed load operations including Single Instruction Multiple Data (SIMD) load operations." + }, + { + "ArchStdEvent": "ST_SPEC", + "PublicDescription": "Counts speculatively executed store operations including Single Instruction Multiple Data (SIMD) store operations." + }, + { + "ArchStdEvent": "DP_SPEC", + "PublicDescription": "Counts speculatively executed logical or arithmetic instructions such as MOV/MVN operations." + }, + { + "ArchStdEvent": "ASE_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations excluding load, store and move micro-operations that move data to or from SIMD (vector) registers." + }, + { + "ArchStdEvent": "VFP_SPEC", + "PublicDescription": "Counts speculatively executed floating point operations. This event does not count operations that move data to or from floating point (vector) registers." + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + "PublicDescription": "Counts speculatively executed operations which cause software changes of the PC. Those operations include all taken branch operations." + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + "PublicDescription": "Counts speculatively executed cryptographic operations except for PMULL and VMULL operations." + }, + { + "ArchStdEvent": "ISB_SPEC", + "PublicDescription": "Counts ISB operations that are executed." + }, + { + "ArchStdEvent": "DSB_SPEC", + "PublicDescription": "Counts DSB operations that are speculatively issued to Load/Store unit in the CPU." + }, + { + "ArchStdEvent": "DMB_SPEC", + "PublicDescription": "Counts DMB operations that are speculatively issued to the Load/Store unit in the CPU. This event does not count implied barriers from load acquire/store release operations." + }, + { + "ArchStdEvent": "RC_LD_SPEC", + "PublicDescription": "Counts any load acquire operations that are speculatively executed. For example: LDAR, LDARH, LDARB" + }, + { + "ArchStdEvent": "RC_ST_SPEC", + "PublicDescription": "Counts any store release operations that are speculatively executed. For example: STLR, STLRH, STLRB" + }, + { + "ArchStdEvent": "ASE_INST_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations." + }, + { + "ArchStdEvent": "CAS_NEAR_PASS", + "PublicDescription": "Counts compare and swap instructions that executed locally to the PE and updated the location accessed." + }, + { + "ArchStdEvent": "CAS_NEAR_SPEC", + "PublicDescription": "Counts compare and swap instructions that executed locally to the PE." + }, + { + "ArchStdEvent": "CAS_FAR_SPEC", + "PublicDescription": "Counts compare and swap instructions that did not execute locally to the PE." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/stall.json new file mode 100644 index 000000000000..51cda27880b9 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/stall.json @@ -0,0 +1,86 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. STALL_FRONTEND_SLOTS counts SLOTS during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL_BACKEND", + "PublicDescription": "Counts cycles whenever the rename unit is unable to send any micro-operations to the backend of the pipeline because of backend resource constraints. Backend resource constraints can include issue stage fullness, execution stage fullness, or other internal pipeline resource fullness. All the backend slots were empty during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL", + "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). This event is the sum of STALL_FRONTEND and STALL_BACKEND" + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints. STALL_BACKEND counts during the cycle when STALL_SLOT_BACKEND counts at least 1." + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend due to frontend resource constraints." + }, + { + "ArchStdEvent": "STALL_SLOT", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). STALL_SLOT is the sum of STALL_SLOT_FRONTEND and STALL_SLOT_BACKEND." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM", + "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the last level core cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEMBOUND", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage due to resource constraints in the memory resources." + }, + { + "ArchStdEvent": "STALL_FRONTEND_L1I", + "PublicDescription": "Counts cycles when the frontend is stalled because there is an instruction fetch request pending in the level 1 instruction cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEM", + "PublicDescription": "Counts cycles when the frontend is stalled because there is an instruction fetch request pending in the last level core cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_TLB", + "PublicDescription": "Counts when the frontend is stalled on any TLB misses being handled. This event also counts the TLB accesses made by hardware prefetches." + }, + { + "ArchStdEvent": "STALL_FRONTEND_CPUBOUND", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage due to resource constraints in the CPU resources excluding memory resources." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLOW", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage due to resource constraints in the branch prediction unit." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLUSH", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage as the frontend is recovering from a machine flush or resteer. Example scenarios that cause a flush include branch mispredictions, taken exceptions, micro-architectural flush etc." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEMBOUND", + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations due to resource constraints in the memory resources." + }, + { + "ArchStdEvent": "STALL_BACKEND_L1D", + "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the level 1 data cache." + }, + { + "ArchStdEvent": "STALL_BACKEND_TLB", + "PublicDescription": "Counts cycles when the backend is stalled on any demand TLB misses being handled." + }, + { + "ArchStdEvent": "STALL_BACKEND_ST", + "PublicDescription": "Counts cycles when the backend is stalled and there is a store that has not reached the pre-commit stage." + }, + { + "ArchStdEvent": "STALL_BACKEND_CPUBOUND", + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations due to any resource constraints in the CPU excluding memory resources." + }, + { + "ArchStdEvent": "STALL_BACKEND_BUSY", + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations because the issue queues are full to take any operations for execution." + }, + { + "ArchStdEvent": "STALL_BACKEND_RENAME", + "PublicDescription": "Counts cycles when backend is stalled even when operations are available from the frontend but at least one is not ready to be sent to the backend because no rename register is available." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/sve.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/sve.json new file mode 100644 index 000000000000..51dab48cb2ba --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/sve.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "SVE_INST_SPEC", + "PublicDescription": "Counts speculatively executed operations that are SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_EMPTY_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with no active predicate elements." + }, + { + "ArchStdEvent": "SVE_PRED_FULL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with all predicate elements active." + }, + { + "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one but not all active predicate elements." + }, + { + "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one non active predicate elements." + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations." + }, + { + "ArchStdEvent": "SVE_LDFF_FAULT_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations that clear at least one bit in the FFR." + }, + { + "ArchStdEvent": "ASE_SVE_INT8_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type an 8-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT16_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 16-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT32_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 32-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT64_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 64-bit integer." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/tlb.json new file mode 100644 index 000000000000..c7aa89c2f19f --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/tlb.json @@ -0,0 +1,74 @@ +[ + { + "ArchStdEvent": "L1I_TLB_REFILL", + "PublicDescription": "Counts level 1 instruction TLB refills from any Instruction fetch. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL", + "PublicDescription": "Counts level 1 data TLB accesses that resulted in TLB refills. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an AT(address translation) instruction." + }, + { + "ArchStdEvent": "L1D_TLB", + "PublicDescription": "Counts level 1 data TLB accesses caused by any memory load or store operation. Note that load or store instructions can be broken up into multiple memory operations. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1I_TLB", + "PublicDescription": "Counts level 1 instruction TLB accesses, whether the access hits or misses in the TLB. This event counts both demand accesses and prefetch or preload generated accesses." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL", + "PublicDescription": "Counts level 2 TLB refills caused by memory operations from both data and instruction fetch, except for those caused by TLB maintenance operations and hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB", + "PublicDescription": "Counts level 2 TLB accesses except those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK", + "PublicDescription": "Counts number of demand data translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK", + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK_PERCYC", + "PublicDescription": "Counts the number of data translation table walks in progress per cycle." + }, + { + "ArchStdEvent": "ITLB_WALK_PERCYC", + "PublicDescription": "Counts the number of instruction translation table walks in progress per cycle." + }, + { + "ArchStdEvent": "DTLB_HWUPD", + "PublicDescription": "Counts number of memory accesses triggered by a data translation table walk and performing an update of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that this event counts accesses triggered by software preloads, but not accesses triggered by hardware prefetchers." + }, + { + "ArchStdEvent": "ITLB_HWUPD", + "PublicDescription": "Counts number of memory accesses triggered by an instruction translation table walk and performing an update of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD." + }, + { + "ArchStdEvent": "DTLB_STEP", + "PublicDescription": "Counts number of memory accesses triggered by a demand data translation table walk and performing a read of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that this event counts accesses triggered by software preloads, but not accesses triggered by hardware prefetchers." + }, + { + "ArchStdEvent": "ITLB_STEP", + "PublicDescription": "Counts number of memory accesses triggered by an instruction translation table walk and performing a read of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD." + }, + { + "ArchStdEvent": "DTLB_WALK_LARGE", + "PublicDescription": "Counts number of demand data translation table walks caused by a miss in the L2 TLB and yielding a large page. The set of large pages is defined as all pages with a final size higher than or equal to 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. If DTLB_WALK_BLOCK is implemented, then it is an alias for this event in this family. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK_LARGE", + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and yielding a large page. The set of large pages is defined as all pages with a final size higher than or equal to 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. In this family, this is equal to ITLB_WALK_BLOCK event. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK_SMALL", + "PublicDescription": "Counts number of data translation table walks caused by a miss in the L2 TLB and yielding a small page. The set of small pages is defined as all pages with a final size lower than 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. If DTLB_WALK_PAGE event is implemented, then it is an alias for this event in this family. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK_SMALL", + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and yielding a small page. The set of small pages is defined as all pages with a final size lower than 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. In this family, this is equal to ITLB_WALK_PAGE event. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/trace.json new file mode 100644 index 000000000000..a09043486cd9 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n3/trace.json @@ -0,0 +1,42 @@ +[ + { + "ArchStdEvent": "TRB_WRAP", + "PublicDescription": "This event is generated each time the current write pointer is wrapped to the base pointer." + }, + { + "ArchStdEvent": "TRB_TRIG", + "PublicDescription": "This event is generated when a Trace Buffer Extension Trigger Event occurs." + }, + { + "ArchStdEvent": "TRCEXTOUT0", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 0." + }, + { + "ArchStdEvent": "TRCEXTOUT1", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 1." + }, + { + "ArchStdEvent": "TRCEXTOUT2", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 2." + }, + { + "ArchStdEvent": "TRCEXTOUT3", + "PublicDescription": "This event is generated each time an event is signaled by ETE external event 3." + }, + { + "ArchStdEvent": "CTI_TRIGOUT4", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 4." + }, + { + "ArchStdEvent": "CTI_TRIGOUT5", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 5." + }, + { + "ArchStdEvent": "CTI_TRIGOUT6", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 6." + }, + { + "ArchStdEvent": "CTI_TRIGOUT7", + "PublicDescription": "This event is generated each time an event is signaled on CTI output trigger 7." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/brbe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/brbe.json new file mode 100644 index 000000000000..9fdf5b0453a0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/brbe.json @@ -0,0 +1,6 @@ +[ + { + "ArchStdEvent": "BRB_FILTRATE", + "PublicDescription": "Counts branch records captured which are not removed by filtering." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/bus.json new file mode 100644 index 000000000000..2e11a8c4a484 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/bus.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "BUS_ACCESS", + "PublicDescription": "Counts memory transactions issued by the CPU to the external bus, including snoop requests and snoop responses. Each beat of data is counted individually." + }, + { + "ArchStdEvent": "BUS_CYCLES", + "PublicDescription": "Counts bus cycles in the CPU. Bus cycles represent a clock cycle in which a transaction could be sent or received on the interface from the CPU to the external bus. Since that interface is driven at the same clock speed as the CPU, this event is a duplicate of CPU_CYCLES." + }, + { + "ArchStdEvent": "BUS_ACCESS_RD", + "PublicDescription": "Counts memory read transactions seen on the external bus. Each beat of data is counted individually." + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + "PublicDescription": "Counts memory write transactions seen on the external bus. Each beat of data is counted individually." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/exception.json new file mode 100644 index 000000000000..7126fbf292e0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/exception.json @@ -0,0 +1,62 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN", + "PublicDescription": "Counts any taken architecturally visible exceptions such as IRQ, FIQ, SError, and other synchronous exceptions. Exceptions are counted whether or not they are taken locally." + }, + { + "ArchStdEvent": "EXC_RETURN", + "PublicDescription": "Counts any architecturally executed exception return instructions. For example: AArch64: ERET" + }, + { + "ArchStdEvent": "EXC_UNDEF", + "PublicDescription": "Counts the number of synchronous exceptions which are taken locally that are due to attempting to execute an instruction that is UNDEFINED. Attempting to execute instruction bit patterns that have not been allocated. Attempting to execute instructions when they are disabled. Attempting to execute instructions at an inappropriate Exception level. Attempting to execute an instruction when the value of PSTATE.IL is 1." + }, + { + "ArchStdEvent": "EXC_SVC", + "PublicDescription": "Counts SVC exceptions taken locally." + }, + { + "ArchStdEvent": "EXC_PABORT", + "PublicDescription": "Counts synchronous exceptions that are taken locally and caused by Instruction Aborts." + }, + { + "ArchStdEvent": "EXC_DABORT", + "PublicDescription": "Counts exceptions that are taken locally and are caused by data aborts or SErrors. Conditions that could cause those exceptions are attempting to read or write memory where the MMU generates a fault, attempting to read or write memory with a misaligned address, interrupts from the nSEI inputs and internally generated SErrors." + }, + { + "ArchStdEvent": "EXC_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are taken locally." + }, + { + "ArchStdEvent": "EXC_FIQ", + "PublicDescription": "Counts FIQ exceptions including the virtual FIQs that are taken locally." + }, + { + "ArchStdEvent": "EXC_SMC", + "PublicDescription": "Counts SMC exceptions take to EL3." + }, + { + "ArchStdEvent": "EXC_HVC", + "PublicDescription": "Counts HVC exceptions taken to EL2." + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Instruction Aborts. For example, attempting to execute an instruction with a misaligned PC." + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Data Aborts or SError interrupts. Conditions that could cause those exceptions are:\n\n1. Attempting to read or write memory where the MMU generates a fault,\n2. Attempting to read or write memory with a misaligned address,\n3. Interrupts from the SEI input.\n4. internally generated SErrors." + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + "PublicDescription": "Counts the number of synchronous trap exceptions which are not taken locally and are not SVC, SMC, HVC, data aborts, Instruction Aborts, or interrupts." + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are not taken locally." + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + "PublicDescription": "Counts FIQs which are not taken locally but taken from EL0, EL1,\n or EL2 to EL3 (which would be the normal behavior for FIQs when not executing\n in EL3)." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/fp_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/fp_operation.json new file mode 100644 index 000000000000..cec3435ac766 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/fp_operation.json @@ -0,0 +1,22 @@ +[ + { + "ArchStdEvent": "FP_HP_SPEC", + "PublicDescription": "Counts speculatively executed half precision floating point operations." + }, + { + "ArchStdEvent": "FP_SP_SPEC", + "PublicDescription": "Counts speculatively executed single precision floating point operations." + }, + { + "ArchStdEvent": "FP_DP_SPEC", + "PublicDescription": "Counts speculatively executed double precision floating point operations." + }, + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC", + "PublicDescription": "Counts speculatively executed scalable single precision floating point operations." + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC", + "PublicDescription": "Counts speculatively executed non-scalable single precision floating point operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/general.json new file mode 100644 index 000000000000..4d816015b8c2 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/general.json @@ -0,0 +1,40 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES", + "PublicDescription": "Counts CPU clock cycles (not timer cycles). The clock measured by this event is defined as the physical clock driving the CPU logic." + }, + { + "PublicDescription": "Count of RXDAT or RXRSP responses received with indication completer fullness indicator set to 0", + "EventCode": "0x198", + "EventName": "L2_CHI_CBUSY0", + "BriefDescription": "Number of RXDAT or RXRSP response received with CBusy of 0" + }, + { + "PublicDescription": "Count of RXDAT or RXRSP responses received with indication completer fullness indicator set to 1", + "EventCode": "0x199", + "EventName": "L2_CHI_CBUSY1", + "BriefDescription": "Number of RXDAT or RXRSP response received with CBusy of 1" + }, + { + "PublicDescription": "Count of RXDAT or RXRSP responses received with indication completer fullness indicator set to 2", + "EventCode": "0x19A", + "EventName": "L2_CHI_CBUSY2", + "BriefDescription": "Number of RXDAT or RXRSP response received with CBusy of 2" + }, + { + "PublicDescription": "Count of RXDAT or RXRSP responses received with indication completer fullness indicator set to 3", + "EventCode": "0x19B", + "EventName": "L2_CHI_CBUSY3", + "BriefDescription": "Number of RXDAT or RXRSP response received with CBusy of 3" + }, + { + "PublicDescription": "Count of RXDAT or RXRSP responses received with indication completer indicating multiple cores actively making requests", + "EventCode": "0x19C", + "EventName": "L2_CHI_CBUSY_MT", + "BriefDescription": "Number of RXDAT or RXRSP response received with CBusy Multi-threaded set" + }, + { + "ArchStdEvent": "CNT_CYCLES", + "PublicDescription": "Increments at a constant frequency equal to the rate of increment of the System Counter, CNTPCT_EL0." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l1d_cache.json new file mode 100644 index 000000000000..891e07631c6e --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l1d_cache.json @@ -0,0 +1,74 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_REFILL", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE", + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) counts as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." + }, + { + "ArchStdEvent": "L1D_CACHE_WB", + "PublicDescription": "Counts write-backs of dirty data from the L1 data cache to the L2 cache. This occurs when either a dirty cache line is evicted from L1 data cache and allocated in the L2 cache or dirty data is written to the L2 and possibly to the next level of cache. This event counts both victim cache line evictions and cache write-backs from snoops or cache maintenance operations. The following cache operations are not counted:\n\n1. Invalidations which do not result in data being transferred out of the L1 (such as evictions of clean data),\n2. Full line writes which write to L2 without writing L1, such as write streaming mode." + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 1 data cache from any memory read operations, that incurred additional latency." + }, + { + "ArchStdEvent": "L1D_CACHE_RD", + "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches counts as both a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + "PublicDescription": "Counts level 1 data cache accesses generated by store operations. This event also counts accesses caused by a DC ZVA (data cache zero, specified by virtual address) instruction. Near atomic operations that resolve in the CPUs caches count as a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load instructions where the memory read operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed store instructions where the memory write operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + "PublicDescription": "Counts level 1 data cache refills where the cache line data came from caches inside the immediate cluster of the core." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + "PublicDescription": "Counts level 1 data cache refills for which the cache line data came from outside the immediate cluster of the core, like an SLC in the system interconnect or DRAM." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + "PublicDescription": "Counts dirty cache line evictions from the level 1 data cache caused by a new cache line allocation. This event does not count evictions caused by cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 1 data cache that are a result of a coherency operation made by another CPU. Event count includes cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 1 data cache caused by:\n\n- Cache Maintenance Operations (CMO) that operate by a virtual address.\n- Broadcast cache coherency operations from another CPU in the system.\n\nThis event does not count for the following conditions:\n\n1. A cache refill invalidates a cache line.\n2. A CMO which is executed on that CPU and invalidates a cache line specified by set/way.\n\nNote that CMOs that operate by set/way cannot be broadcast from one CPU to another." + }, + { + "ArchStdEvent": "L1D_CACHE_RW", + "PublicDescription": "Counts level 1 data demand cache accesses from any load or store operation. Near atomic operations that resolve in the CPUs caches counts as both a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_PRFM", + "PublicDescription": "Counts level 1 data cache accesses from software preload or prefetch instructions." + }, + { + "ArchStdEvent": "L1D_CACHE_MISS", + "PublicDescription": "Counts cache line misses in the level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_PRFM", + "PublicDescription": "Counts level 1 data cache refills where the cache line access was generated by software preload or prefetch instructions." + }, + { + "ArchStdEvent": "L1D_CACHE_HWPRF", + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations generated by the hardware prefetcher." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l1i_cache.json new file mode 100644 index 000000000000..fc511c5d2021 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l1i_cache.json @@ -0,0 +1,62 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL", + "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once." + }, + { + "ArchStdEvent": "L1I_CACHE", + "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted." + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS", + "PublicDescription": "Counts cache line refills into the level 1 instruction cache, that incurred additional latency." + }, + { + "ArchStdEvent": "L1I_CACHE_RD", + "PublicDescription": "Counts demand instruction fetches which access the level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_PRFM", + "PublicDescription": "Counts instruction fetches generated by software preload or prefetch instructions which access the level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_HWPRF", + "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache generated by the hardware prefetcher." + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL_PRFM", + "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch generated by software preload or prefetch instructions. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT_RD", + "PublicDescription": "Counts demand instruction fetches that access the level 1 instruction cache and hit in the L1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT_RD_FPRFM", + "PublicDescription": "Counts demand instruction fetches that access the level 1 instruction cache that hit in the L1 instruction cache and the line was requested by a software prefetch." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT_RD_FHWPRF", + "PublicDescription": "Counts demand instruction fetches generated by hardware prefetch that access the level 1 instruction cache and hit in the L1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT", + "PublicDescription": "Counts instruction fetches that access the level 1 instruction cache and hit in the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT_PRFM", + "PublicDescription": "Counts instruction fetches generated by software preload or prefetch instructions that access the level 1 instruction cache and hit in the level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_LFB_HIT_RD", + "PublicDescription": "Counts demand instruction fetches that access the level 1 instruction cache and hit in a line that is in the process of being loaded into the level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_LFB_HIT_RD_FPRFM", + "PublicDescription": "Counts demand instruction fetches generated by software prefetch instructions that access the level 1 instruction cache and hit in a line that is in the process of being loaded into the level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_LFB_HIT_RD_FHWPRF", + "PublicDescription": "Counts demand instruction fetches generated by hardware prefetch that access the level 1 instruction cache and hit in a line that is in the process of being loaded into the level 1 instruction cache." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l2_cache.json new file mode 100644 index 000000000000..b38d71fd1136 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/l2_cache.json @@ -0,0 +1,78 @@ +[ + { + "ArchStdEvent": "L2D_CACHE", + "PublicDescription": "Counts accesses to the level 2 cache due to data accesses. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level data cache or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL", + "PublicDescription": "Counts cache line refills into the level 2 cache. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB", + "PublicDescription": "Counts write-backs of data from the L2 cache to outside the CPU. This includes snoops to the L2 (from other CPUs) which return data even if the snoops cause an invalidation. L2 cache line invalidations which do not write data outside the CPU and snoops which return data from an L1 cache are not counted. Data would not be written outside the cache when invalidating a clean cache line." + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + "PublicDescription": "Counts level 2 data cache accesses due to memory read operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + "PublicDescription": "Counts level 2 cache accesses due to memory write operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + "PublicDescription": "Counts evictions from the level 2 cache because of a line being allocated into the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 2 cache that are a result of either:\n\n1. Cache maintenance operations,\n\n2. Snoop responses or,\n\n3. Direct cache transfers to another CPU due to a forwarding snoop request." + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 2 cache by cache maintenance operations that operate by a virtual address, or by external coherency operations. This event does not count if either:\n\n1. A cache refill invalidates a cache line or,\n2. A Cache Maintenance Operation (CMO), which invalidates a cache line specified by set/way, is executed on that CPU.\n\nCMOs that operate by set/way cannot be broadcast from one CPU to another." + }, + { + "PublicDescription": "Counts level 2 cache accesses due to level 1 data cache hardware prefetcher.", + "EventCode": "0x1B8", + "EventName": "L2D_CACHE_L1HWPRF", + "BriefDescription": "L2D cache access due to L1 hardware prefetch" + }, + { + "PublicDescription": "Counts level 2 cache refills where the cache line is requested by a level 1 data cache hardware prefetcher.", + "EventCode": "0x1B9", + "EventName": "L2D_CACHE_REFILL_L1HWPRF", + "BriefDescription": "L2D cache refill due to L1 hardware prefetch" + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 2 unified cache from any memory read operations that incurred additional latency." + }, + { + "ArchStdEvent": "L2D_CACHE_RW", + "PublicDescription": "Counts level 2 cache demand accesses from any load/store operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_PRFM", + "PublicDescription": "Counts level 2 data cache accesses generated by software preload or prefetch instructions." + }, + { + "ArchStdEvent": "L2D_CACHE_MISS", + "PublicDescription": "Counts cache line misses in the level 2 cache. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 data cache or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_PRFM", + "PublicDescription": "Counts refills due to accesses generated as a result of software preload or prefetch instructions as counted by L2D_CACHE_PRFM." + }, + { + "ArchStdEvent": "L2D_CACHE_HWPRF", + "PublicDescription": "Counts level 2 data cache accesses generated by L2D hardware prefetchers." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/ll_cache.json new file mode 100644 index 000000000000..fd5a2e0099b8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/ll_cache.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "LL_CACHE_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for the L3 cache. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for L3 cache. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/memory.json new file mode 100644 index 000000000000..0454ffc1d364 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/memory.json @@ -0,0 +1,58 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS", + "PublicDescription": "Counts memory accesses issued by the CPU load store unit, where those accesses are issued due to load or store operations. This event counts memory accesses no matter whether the data is received from any level of cache hierarchy or external memory. If memory accesses are broken up into smaller transactions than what were specified in the load or store instructions, then the event counts those smaller memory transactions." + }, + { + "ArchStdEvent": "MEMORY_ERROR", + "PublicDescription": "Counts any detected correctable or uncorrectable physical memory errors (ECC or parity) in protected CPUs RAMs. On the core, this event counts errors in the caches (including data and tag rams). Any detected memory error (from either a speculative and abandoned access, or an architecturally executed access) is counted. Note that errors are only detected when the actual protected memory is accessed by an operation." + }, + { + "ArchStdEvent": "REMOTE_ACCESS", + "PublicDescription": "Counts accesses to another chip, which is implemented as a different CMN mesh in the system. If the CHI bus response back to the core indicates that the data source is from another chip (mesh), then the counter is updated. If no data is returned, even if the system snoops another chip/mesh, then the counter is not updated." + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + "PublicDescription": "Counts memory accesses issued by the CPU due to load operations. The event counts any memory load access, no matter whether the data is received from any level of cache hierarchy or external memory. The event also counts atomic load operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + "PublicDescription": "Counts memory accesses issued by the CPU due to store operations. The event counts any memory store access, no matter whether the data is located in any level of cache or external memory. The event also counts atomic load and store operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." + }, + { + "ArchStdEvent": "LDST_ALIGN_LAT", + "PublicDescription": "Counts the number of memory read and write accesses in a cycle that incurred additional latency, due to the alignment of the address and the size of data being accessed, which results in store crossing a single cache line." + }, + { + "ArchStdEvent": "LD_ALIGN_LAT", + "PublicDescription": "Counts the number of memory read accesses in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed, which results in load crossing a single cache line." + }, + { + "ArchStdEvent": "ST_ALIGN_LAT", + "PublicDescription": "Counts the number of memory write access in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed incurred additional latency." + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED", + "PublicDescription": "Counts the number of memory read and write accesses counted by MEM_ACCESS that are tag checked by the Memory Tagging Extension (MTE). This event is implemented as the sum of MEM_ACCESS_CHECKED_RD and MEM_ACCESS_CHECKED_WR" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_RD", + "PublicDescription": "Counts the number of memory read accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)." + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_WR", + "PublicDescription": "Counts the number of memory write accesses in a cycle that is tag checked by the Memory Tagging Extension (MTE)." + }, + { + "ArchStdEvent": "INST_FETCH_PERCYC", + "PublicDescription": "Counts number of instruction fetches outstanding per cycle, which will provide an average latency of instruction fetch." + }, + { + "ArchStdEvent": "MEM_ACCESS_RD_PERCYC", + "PublicDescription": "Counts the number of outstanding loads or memory read accesses per cycle." + }, + { + "ArchStdEvent": "INST_FETCH", + "PublicDescription": "Counts Instruction memory accesses that the PE makes." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/metrics.json new file mode 100644 index 000000000000..4a671f55eaf3 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/metrics.json @@ -0,0 +1,457 @@ +[ + { + "ArchStdEvent": "backend_bound" + }, + { + "MetricName": "backend_busy_bound", + "MetricExpr": "STALL_BACKEND_BUSY / STALL_BACKEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to issue queues being full to accept operations for execution.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_cache_l1d_bound", + "MetricExpr": "STALL_BACKEND_L1D / (STALL_BACKEND_L1D + STALL_BACKEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory access latency issues caused by level 1 data cache misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_cache_l2d_bound", + "MetricExpr": "STALL_BACKEND_MEM / (STALL_BACKEND_L1D + STALL_BACKEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory access latency issues caused by level 2 data cache misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_core_bound", + "MetricExpr": "STALL_BACKEND_CPUBOUND / STALL_BACKEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to backend core resource constraints not related to instruction fetch latency issues caused by memory access components.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_core_rename_bound", + "MetricExpr": "STALL_BACKEND_RENAME / STALL_BACKEND_CPUBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend as the rename unit registers are unavailable.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_bound", + "MetricExpr": "STALL_BACKEND_MEMBOUND / STALL_BACKEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to backend core resource constraints related to memory access latency issues caused by memory access components.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_cache_bound", + "MetricExpr": "(STALL_BACKEND_L1D + STALL_BACKEND_MEM) / STALL_BACKEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory latency issues caused by data cache misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_store_bound", + "MetricExpr": "STALL_BACKEND_ST / STALL_BACKEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to memory write pending caused by stores stalled in the pre-commit stage.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_mem_tlb_bound", + "MetricExpr": "STALL_BACKEND_TLB / STALL_BACKEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the backend due to memory access latency issues caused by data TLB misses.", + "MetricGroup": "Topdown_Backend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "backend_stalled_cycles", + "MetricExpr": "STALL_BACKEND / CPU_CYCLES * 100", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "ArchStdEvent": "bad_speculation", + "MetricExpr": "(1 - STALL_SLOT / (10 * CPU_CYCLES)) * (1 - OP_RETIRED / OP_SPEC) * 100 + STALL_FRONTEND_FLUSH / CPU_CYCLES * 100" + }, + { + "MetricName": "barrier_percentage", + "MetricExpr": "(ISB_SPEC + DSB_SPEC + DMB_SPEC) / INST_SPEC * 100", + "BriefDescription": "This metric measures instruction and data barrier operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "branch_direct_ratio", + "MetricExpr": "BR_IMMED_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of direct branches retired to the total number of branches architecturally executed.", + "MetricGroup": "Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "branch_indirect_ratio", + "MetricExpr": "BR_IND_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of indirect branches retired, including function returns, to the total number of branches architecturally executed.", + "MetricGroup": "Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "branch_misprediction_ratio", + "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.", + "MetricGroup": "Miss_Ratio;Branch_Effectiveness", + "ScaleUnit": "100percent of branches" + }, + { + "MetricName": "branch_mpki", + "MetricExpr": "BR_MIS_PRED_RETIRED / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.", + "MetricGroup": "MPKI;Branch_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "branch_percentage", + "MetricExpr": "(BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC * 100", + "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "branch_return_ratio", + "MetricExpr": "BR_RETURN_RETIRED / BR_RETIRED", + "BriefDescription": "This metric measures the ratio of branches retired that are function returns to the total number of branches architecturally executed.", + "MetricGroup": "Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "crypto_percentage", + "MetricExpr": "CRYPTO_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "dtlb_mpki", + "MetricExpr": "DTLB_WALK / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "dtlb_walk_ratio", + "MetricExpr": "DTLB_WALK / L1D_TLB", + "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "fp16_percentage", + "MetricExpr": "FP_HP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures half-precision floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "FP_Precision_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "fp32_percentage", + "MetricExpr": "FP_SP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures single-precision floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "FP_Precision_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "fp64_percentage", + "MetricExpr": "FP_DP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures double-precision floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "FP_Precision_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "fp_ops_per_cycle", + "MetricExpr": "(FP_SCALE_OPS_SPEC + FP_FIXED_OPS_SPEC) / CPU_CYCLES", + "BriefDescription": "This metric measures floating point operations per cycle in any precision performed by any instruction. Operations are counted by computation and by vector lanes, fused computations such as multiply-add count as twice per vector lane for example.", + "MetricGroup": "FP_Arithmetic_Intensity", + "ScaleUnit": "1operations per cycle" + }, + { + "ArchStdEvent": "frontend_bound", + "MetricExpr": "(STALL_SLOT_FRONTEND / (10 * CPU_CYCLES) - STALL_FRONTEND_FLUSH / CPU_CYCLES) * 100" + }, + { + "MetricName": "frontend_cache_l1i_bound", + "MetricExpr": "STALL_FRONTEND_L1I / (STALL_FRONTEND_L1I + STALL_FRONTEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to memory access latency issues caused by level 1 instruction cache misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_cache_l2i_bound", + "MetricExpr": "STALL_FRONTEND_MEM / (STALL_FRONTEND_L1I + STALL_FRONTEND_MEM) * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to memory access latency issues caused by level 2 instruction cache misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_core_bound", + "MetricExpr": "STALL_FRONTEND_CPUBOUND / STALL_FRONTEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to frontend core resource constraints not related to instruction fetch latency issues caused by memory access components.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_core_flow_bound", + "MetricExpr": "STALL_FRONTEND_FLOW / STALL_FRONTEND_CPUBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend as the decode unit is awaiting input from the branch prediction unit.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_core_flush_bound", + "MetricExpr": "STALL_FRONTEND_FLUSH / STALL_FRONTEND_CPUBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend as the processor is recovering from a pipeline flush caused by bad speculation or other machine resteers.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_mem_bound", + "MetricExpr": "STALL_FRONTEND_MEMBOUND / STALL_FRONTEND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to frontend core resource constraints related to the instruction fetch latency issues caused by memory access components.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_mem_cache_bound", + "MetricExpr": "(STALL_FRONTEND_L1I + STALL_FRONTEND_MEM) / STALL_FRONTEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to instruction fetch latency issues caused by instruction cache misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_mem_tlb_bound", + "MetricExpr": "STALL_FRONTEND_TLB / STALL_FRONTEND_MEMBOUND * 100", + "BriefDescription": "This metric is the percentage of total cycles stalled in the frontend due to instruction fetch latency issues caused by instruction TLB misses.", + "MetricGroup": "Topdown_Frontend", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "frontend_stalled_cycles", + "MetricExpr": "STALL_FRONTEND / CPU_CYCLES * 100", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "integer_dp_percentage", + "MetricExpr": "DP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "ipc", + "MetricExpr": "INST_RETIRED / CPU_CYCLES", + "BriefDescription": "This metric measures the number of instructions retired per cycle.", + "MetricGroup": "General", + "ScaleUnit": "1per cycle" + }, + { + "MetricName": "itlb_mpki", + "MetricExpr": "ITLB_WALK / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "itlb_walk_ratio", + "MetricExpr": "ITLB_WALK / L1I_TLB", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l1d_cache_miss_ratio", + "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", + "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", + "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "l1d_cache_mpki", + "MetricExpr": "L1D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1D_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1d_tlb_miss_ratio", + "MetricExpr": "L1D_TLB_REFILL / L1D_TLB", + "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l1d_tlb_mpki", + "MetricExpr": "L1D_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 data TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_cache_miss_ratio", + "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", + "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", + "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "l1i_cache_mpki", + "MetricExpr": "L1I_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1I_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_tlb_miss_ratio", + "MetricExpr": "L1I_TLB_REFILL / L1I_TLB", + "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l1i_tlb_mpki", + "MetricExpr": "L1I_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_cache_miss_ratio", + "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", + "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "l2_cache_mpki", + "MetricExpr": "L2D_CACHE_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "MPKI;L2_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_tlb_miss_ratio", + "MetricExpr": "L2D_TLB_REFILL / L2D_TLB", + "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "100percent of TLB accesses" + }, + { + "MetricName": "l2_tlb_mpki", + "MetricExpr": "L2D_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "ll_cache_read_hit_ratio", + "MetricExpr": "(LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD", + "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "LL_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "ll_cache_read_miss_ratio", + "MetricExpr": "LL_CACHE_MISS_RD / LL_CACHE_RD", + "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness", + "ScaleUnit": "100percent of cache accesses" + }, + { + "MetricName": "ll_cache_read_mpki", + "MetricExpr": "LL_CACHE_MISS_RD / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;LL_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "load_percentage", + "MetricExpr": "LD_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "nonsve_fp_ops_per_cycle", + "MetricExpr": "FP_FIXED_OPS_SPEC / CPU_CYCLES", + "BriefDescription": "This metric measures floating point operations per cycle in any precision performed by an instruction that is not an SVE instruction. Operations are counted by computation and by vector lanes, fused computations such as multiply-add count as twice per vector lane for example.", + "MetricGroup": "FP_Arithmetic_Intensity", + "ScaleUnit": "1operations per cycle" + }, + { + "ArchStdEvent": "retiring" + }, + { + "MetricName": "scalar_fp_percentage", + "MetricExpr": "VFP_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "simd_percentage", + "MetricExpr": "ASE_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "store_percentage", + "MetricExpr": "ST_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_all_percentage", + "MetricExpr": "SVE_INST_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations, including loads and stores, as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_fp_ops_per_cycle", + "MetricExpr": "FP_SCALE_OPS_SPEC / CPU_CYCLES", + "BriefDescription": "This metric measures floating point operations per cycle in any precision performed by SVE instructions. Operations are counted by computation and by vector lanes, fused computations such as multiply-add count as twice per vector lane for example.", + "MetricGroup": "FP_Arithmetic_Intensity", + "ScaleUnit": "1operations per cycle" + }, + { + "MetricName": "sve_predicate_empty_percentage", + "MetricExpr": "SVE_PRED_EMPTY_SPEC / SVE_PRED_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with no active predicates as a percentage of sve predicated operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_predicate_full_percentage", + "MetricExpr": "SVE_PRED_FULL_SPEC / SVE_PRED_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with all active predicates as a percentage of sve predicated operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_predicate_partial_percentage", + "MetricExpr": "SVE_PRED_PARTIAL_SPEC / SVE_PRED_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with at least one active predicates as a percentage of sve predicated operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "sve_predicate_percentage", + "MetricExpr": "SVE_PRED_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations with predicates as a percentage of operations speculatively executed.", + "MetricGroup": "SVE_Effectiveness", + "ScaleUnit": "1percent of operations" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/retired.json new file mode 100644 index 000000000000..04617c399dda --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/retired.json @@ -0,0 +1,98 @@ +[ + { + "ArchStdEvent": "SW_INCR", + "PublicDescription": "Counts software writes to the PMSWINC_EL0 (software PMU increment) register. The PMSWINC_EL0 register is a manually updated counter for use by application software.\n\nThis event could be used to measure any user program event, such as accesses to a particular data structure (by writing to the PMSWINC_EL0 register each time the data structure is accessed).\n\nTo use the PMSWINC_EL0 register and event, developers must insert instructions that write to the PMSWINC_EL0 register into the source code.\n\nSince the SW_INCR event records writes to the PMSWINC_EL0 register, there is no need to do a read/increment/write sequence to the PMSWINC_EL0 register." + }, + { + "ArchStdEvent": "INST_RETIRED", + "PublicDescription": "Counts instructions that have been architecturally executed." + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED", + "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR_EL1 register, which usually contain the kernel PID and can be output with hardware trace." + }, + { + "ArchStdEvent": "BR_IMMED_RETIRED", + "PublicDescription": "Counts architecturally executed direct branches." + }, + { + "ArchStdEvent": "BR_RETURN_RETIRED", + "PublicDescription": "Counts architecturally executed procedure returns." + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED", + "PublicDescription": "Counts architectural writes to TTBR0/1_EL1. If virtualization host extensions are enabled (by setting the HCR_EL2.E2H bit to 1), then accesses to TTBR0/1_EL1 that are redirected to TTBR0/1_EL2, or accesses to TTBR0/1_EL12, are counted. TTBRn registers are typically updated when the kernel is swapping user-space threads or applications." + }, + { + "ArchStdEvent": "BR_RETIRED", + "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted. Note that exception generating instructions, exception return instructions and context synchronization instructions are not counted." + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "PublicDescription": "Counts branches counted by BR_RETIRED which were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "OP_RETIRED", + "PublicDescription": "Counts micro-operations that are architecturally executed. This is a count of number of micro-operations retired from the commit queue in a single cycle." + }, + { + "ArchStdEvent": "BR_INDNR_TAKEN_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches excluding procedure returns that were taken." + }, + { + "ArchStdEvent": "BR_IMMED_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed direct branches that were correctly predicted." + }, + { + "ArchStdEvent": "BR_IMMED_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed direct branches that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_IND_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches including procedure returns that were correctly predicted." + }, + { + "ArchStdEvent": "BR_IND_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches including procedure returns that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_RETURN_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed procedure returns that were correctly predicted." + }, + { + "ArchStdEvent": "BR_RETURN_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed procedure returns that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_INDNR_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches excluding procedure returns that were correctly predicted." + }, + { + "ArchStdEvent": "BR_INDNR_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches excluding procedure returns that were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "BR_TAKEN_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed branches that were taken and were correctly predicted." + }, + { + "ArchStdEvent": "BR_TAKEN_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed branches that were taken and were mispredicted causing a pipeline flush." + }, + { + "ArchStdEvent": "BR_SKIP_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed branches that were not taken and were correctly predicted." + }, + { + "ArchStdEvent": "BR_SKIP_MIS_PRED_RETIRED", + "PublicDescription": "Counts architecturally executed branches that were not taken and were mispredicted causing a pipeline flush." + }, + { + "ArchStdEvent": "BR_PRED_RETIRED", + "PublicDescription": "Counts branch instructions counted by BR_RETIRED which were correctly predicted." + }, + { + "ArchStdEvent": "BR_IND_RETIRED", + "PublicDescription": "Counts architecturally executed indirect branches including procedure returns." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/spe.json new file mode 100644 index 000000000000..ca0217fa4681 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/spe.json @@ -0,0 +1,42 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP", + "PublicDescription": "Counts statistical profiling sample population, the count of all operations that could be sampled but may or may not be chosen for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FEED", + "PublicDescription": "Counts statistical profiling samples taken for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE", + "PublicDescription": "Counts statistical profiling samples taken which are not removed by filtering." + }, + { + "ArchStdEvent": "SAMPLE_COLLISION", + "PublicDescription": "Counts statistical profiling samples that have collided with a previous sample and so therefore not taken." + }, + { + "ArchStdEvent": "SAMPLE_FEED_BR", + "PublicDescription": "Counts statistical profiling samples taken which are branches." + }, + { + "ArchStdEvent": "SAMPLE_FEED_LD", + "PublicDescription": "Counts statistical profiling samples taken which are loads or load atomic operations." + }, + { + "ArchStdEvent": "SAMPLE_FEED_ST", + "PublicDescription": "Counts statistical profiling samples taken which are stores or store atomic operations." + }, + { + "ArchStdEvent": "SAMPLE_FEED_OP", + "PublicDescription": "Counts statistical profiling samples taken which are matching any operation type filters supported." + }, + { + "ArchStdEvent": "SAMPLE_FEED_EVENT", + "PublicDescription": "Counts statistical profiling samples taken which are matching event packet filter constraints." + }, + { + "ArchStdEvent": "SAMPLE_FEED_LAT", + "PublicDescription": "Counts statistical profiling samples taken which are exceeding minimum latency set by operation latency filter constraints." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/spec_operation.json new file mode 100644 index 000000000000..7d7359402e9e --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/spec_operation.json @@ -0,0 +1,126 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED", + "PublicDescription": "Counts branches which are speculatively executed and mispredicted." + }, + { + "ArchStdEvent": "BR_PRED", + "PublicDescription": "Counts all speculatively executed branches." + }, + { + "ArchStdEvent": "INST_SPEC", + "PublicDescription": "Counts operations that have been speculatively executed." + }, + { + "ArchStdEvent": "OP_SPEC", + "PublicDescription": "Counts micro-operations speculatively executed. This is the count of the number of micro-operations dispatched in a cycle." + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + "PublicDescription": "Counts unaligned memory read operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses. The event does not count preload operations (PLD, PLI)." + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + "PublicDescription": "Counts unaligned memory write operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + "PublicDescription": "Counts unaligned memory operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "LDREX_SPEC", + "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. For example: LDREX, LDX" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have not successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed." + }, + { + "ArchStdEvent": "LD_SPEC", + "PublicDescription": "Counts speculatively executed load operations including Single Instruction Multiple Data (SIMD) load operations." + }, + { + "ArchStdEvent": "ST_SPEC", + "PublicDescription": "Counts speculatively executed store operations including Single Instruction Multiple Data (SIMD) store operations." + }, + { + "ArchStdEvent": "LDST_SPEC", + "PublicDescription": "Counts load and store operations that have been speculatively executed." + }, + { + "ArchStdEvent": "DP_SPEC", + "PublicDescription": "Counts speculatively executed logical or arithmetic instructions such as MOV/MVN operations." + }, + { + "ArchStdEvent": "ASE_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations excluding load, store and move micro-operations that move data to or from SIMD (vector) registers." + }, + { + "ArchStdEvent": "VFP_SPEC", + "PublicDescription": "Counts speculatively executed floating point operations. This event does not count operations that move data to or from floating point (vector) registers." + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + "PublicDescription": "Counts speculatively executed operations which cause software changes of the PC. Those operations include all taken branch operations." + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + "PublicDescription": "Counts speculatively executed cryptographic operations except for PMULL and VMULL operations." + }, + { + "ArchStdEvent": "BR_IMMED_SPEC", + "PublicDescription": "Counts direct branch operations which are speculatively executed." + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + "PublicDescription": "Counts procedure return operations (RET, RETAA and RETAB) which are speculatively executed." + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations and direct branch instructions. Some examples of the instructions counted by this event include BR Xn, RET, etc..." + }, + { + "ArchStdEvent": "ISB_SPEC", + "PublicDescription": "Counts ISB operations that are executed." + }, + { + "ArchStdEvent": "DSB_SPEC", + "PublicDescription": "Counts DSB operations that are speculatively issued to Load/Store unit in the CPU." + }, + { + "ArchStdEvent": "DMB_SPEC", + "PublicDescription": "Counts DMB operations that are speculatively issued to the Load/Store unit in the CPU. This event does not count implied barriers from load acquire/store release operations." + }, + { + "ArchStdEvent": "RC_LD_SPEC", + "PublicDescription": "Counts any load acquire operations that are speculatively executed. For example: LDAR, LDARH, LDARB" + }, + { + "ArchStdEvent": "RC_ST_SPEC", + "PublicDescription": "Counts any store release operations that are speculatively executed. For example: STLR, STLRH, STLRB" + }, + { + "ArchStdEvent": "SIMD_INST_SPEC", + "PublicDescription": "Counts speculatively executed operations that are SIMD or SVE vector operations or Advanced SIMD non-scalar operations." + }, + { + "ArchStdEvent": "ASE_INST_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations." + }, + { + "ArchStdEvent": "INT_SPEC", + "PublicDescription": "Counts speculatively executed integer arithmetic operations." + }, + { + "ArchStdEvent": "PRF_SPEC", + "PublicDescription": "Counts speculatively executed operations that prefetch memory. For example: Scalar: PRFM, SVE: PRFB, PRFD, PRFH, or PRFW." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/stall.json new file mode 100644 index 000000000000..cafa73508db6 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/stall.json @@ -0,0 +1,124 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. STALL_FRONTEND_SLOTS counts SLOTS during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL_BACKEND", + "PublicDescription": "Counts cycles whenever the rename unit is unable to send any micro-operations to the backend of the pipeline because of backend resource constraints. Backend resource constraints can include issue stage fullness, execution stage fullness, or other internal pipeline resource fullness. All the backend slots were empty during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL", + "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). This event is the sum of STALL_FRONTEND and STALL_BACKEND" + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints. STALL_BACKEND counts during the cycle when STALL_SLOT_BACKEND counts at least 1." + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend due to frontend resource constraints." + }, + { + "ArchStdEvent": "STALL_SLOT", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). STALL_SLOT is the sum of STALL_SLOT_FRONTEND and STALL_SLOT_BACKEND." + }, + { + "PublicDescription": "Counts cycles counted by STALL_BACKEND_BUSY when the backend could not accept any micro-operations\nbecause the simple integer issue queues are full to take any operations for execution.", + "EventCode": "0x15C", + "EventName": "DISPATCH_STALL_IQ_SX", + "BriefDescription": "Dispatch stalled due to IQ full,SX" + }, + { + "PublicDescription": "Counts cycles counted by STALL_BACKEND_BUSY when the backend could not accept any micro-operations\nbecause the complex integer issue queues are full and can not take any operations for execution.", + "EventCode": "0x15D", + "EventName": "DISPATCH_STALL_IQ_MX", + "BriefDescription": "Dispatch stalled due to IQ full,MX" + }, + { + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations\nbecause the load/store issue queues are full and can not take any operations for execution.", + "EventCode": "0x15E", + "EventName": "DISPATCH_STALL_IQ_LS", + "BriefDescription": "Dispatch stalled due to IQ full,LS" + }, + { + "PublicDescription": "Counts cycles counted by STALL_BACKEND_BUSY when the backend could not accept any micro-operations\nbecause the vector issue queues are full and can not take any operations for execution.", + "EventCode": "0x15F", + "EventName": "DISPATCH_STALL_IQ_VX", + "BriefDescription": "Dispatch stalled due to IQ full,VX" + }, + { + "PublicDescription": "Counts cycles counted by STALL_BACKEND_BUSY when the backend could not accept any micro-operations\nbecause the commit queue is full and can not take any operations for execution.", + "EventCode": "0x160", + "EventName": "DISPATCH_STALL_MCQ", + "BriefDescription": "Dispatch stalled due to MCQ full" + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM", + "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the last level core cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEMBOUND", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage due to resource constraints in the memory resources." + }, + { + "ArchStdEvent": "STALL_FRONTEND_L1I", + "PublicDescription": "Counts cycles when the frontend is stalled because there is an instruction fetch request pending in the level 1 instruction cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEM", + "PublicDescription": "Counts cycles when the frontend is stalled because there is an instruction fetch request pending in the last level core cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_TLB", + "PublicDescription": "Counts when the frontend is stalled on any TLB misses being handled. This event also counts the TLB accesses made by hardware prefetches." + }, + { + "ArchStdEvent": "STALL_FRONTEND_CPUBOUND", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage due to resource constraints in the CPU resources excluding memory resources." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLOW", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage due to resource constraints in the branch prediction unit." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLUSH", + "PublicDescription": "Counts cycles when the frontend could not send any micro-operations to the rename stage as the frontend is recovering from a machine flush or resteer. Example scenarios that cause a flush include branch mispredictions, taken exceptions, micro-architectural flush etc." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEMBOUND", + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations due to resource constraints in the memory resources." + }, + { + "ArchStdEvent": "STALL_BACKEND_L1D", + "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the level 1 data cache." + }, + { + "ArchStdEvent": "STALL_BACKEND_L2D", + "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the level 2 data cache." + }, + { + "ArchStdEvent": "STALL_BACKEND_TLB", + "PublicDescription": "Counts cycles when the backend is stalled on any demand TLB misses being handled." + }, + { + "ArchStdEvent": "STALL_BACKEND_ST", + "PublicDescription": "Counts cycles when the backend is stalled and there is a store that has not reached the pre-commit stage." + }, + { + "ArchStdEvent": "STALL_BACKEND_CPUBOUND", + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations due to any resource constraints in the CPU excluding memory resources." + }, + { + "ArchStdEvent": "STALL_BACKEND_BUSY", + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations because the issue queues are full to take any operations for execution." + }, + { + "ArchStdEvent": "STALL_BACKEND_ILOCK", + "PublicDescription": "Counts cycles when the backend could not accept any micro-operations due to resource constraints imposed by input dependency." + }, + { + "ArchStdEvent": "STALL_BACKEND_RENAME", + "PublicDescription": "Counts cycles when backend is stalled even when operations are available from the frontend but at least one is not ready to be sent to the backend because no rename register is available." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/sve.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/sve.json new file mode 100644 index 000000000000..51dab48cb2ba --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/sve.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "SVE_INST_SPEC", + "PublicDescription": "Counts speculatively executed operations that are SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_EMPTY_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with no active predicate elements." + }, + { + "ArchStdEvent": "SVE_PRED_FULL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with all predicate elements active." + }, + { + "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one but not all active predicate elements." + }, + { + "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one non active predicate elements." + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations." + }, + { + "ArchStdEvent": "SVE_LDFF_FAULT_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations that clear at least one bit in the FFR." + }, + { + "ArchStdEvent": "ASE_SVE_INT8_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type an 8-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT16_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 16-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT32_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 32-bit integer." + }, + { + "ArchStdEvent": "ASE_SVE_INT64_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD or SVE integer operations with the largest data type a 64-bit integer." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/tlb.json new file mode 100644 index 000000000000..41c5472c1def --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v3/tlb.json @@ -0,0 +1,138 @@ +[ + { + "ArchStdEvent": "L1I_TLB_REFILL", + "PublicDescription": "Counts level 1 instruction TLB refills from any Instruction fetch. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL", + "PublicDescription": "Counts level 1 data TLB accesses that resulted in TLB refills. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an AT(address translation) instruction." + }, + { + "ArchStdEvent": "L1D_TLB", + "PublicDescription": "Counts level 1 data TLB accesses caused by any memory load or store operation. Note that load or store instructions can be broken up into multiple memory operations. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1I_TLB", + "PublicDescription": "Counts level 1 instruction TLB accesses, whether the access hits or misses in the TLB. This event counts both demand accesses and prefetch or preload generated accesses." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL", + "PublicDescription": "Counts level 2 TLB refills caused by memory operations from both data and instruction fetch, except for those caused by TLB maintenance operations and hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB", + "PublicDescription": "Counts level 2 TLB accesses except those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK", + "PublicDescription": "Counts number of demand data translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK", + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD", + "PublicDescription": "Counts level 1 data TLB refills caused by memory read operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR", + "PublicDescription": "Counts level 1 data TLB refills caused by data side memory write operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count with an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_RD", + "PublicDescription": "Counts level 1 data TLB accesses caused by memory read operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_WR", + "PublicDescription": "Counts any L1 data side TLB accesses caused by memory write operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + "PublicDescription": "Counts level 2 TLB refills caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations or hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + "PublicDescription": "Counts level 2 TLB refills caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_RD", + "PublicDescription": "Counts level 2 TLB accesses caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_WR", + "PublicDescription": "Counts level 2 TLB accesses caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK_PERCYC", + "PublicDescription": "Counts the number of data translation table walks in progress per cycle." + }, + { + "ArchStdEvent": "ITLB_WALK_PERCYC", + "PublicDescription": "Counts the number of instruction translation table walks in progress per cycle." + }, + { + "ArchStdEvent": "L1D_TLB_RW", + "PublicDescription": "Counts level 1 data TLB demand accesses caused by memory read or write operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1I_TLB_RD", + "PublicDescription": "Counts level 1 instruction TLB demand accesses whether the access hits or misses in the TLB." + }, + { + "ArchStdEvent": "L1D_TLB_PRFM", + "PublicDescription": "Counts level 1 data TLB accesses generated by software prefetch or preload memory accesses. Load or store instructions can be broken into multiple memory operations. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1I_TLB_PRFM", + "PublicDescription": "Counts level 1 instruction TLB accesses generated by software preload or prefetch instructions. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_HWUPD", + "PublicDescription": "Counts number of memory accesses triggered by a data translation table walk and performing an update of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that this event counts accesses triggered by software preloads, but not accesses triggered by hardware prefetchers." + }, + { + "ArchStdEvent": "ITLB_HWUPD", + "PublicDescription": "Counts number of memory accesses triggered by an instruction translation table walk and performing an update of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD." + }, + { + "ArchStdEvent": "DTLB_STEP", + "PublicDescription": "Counts number of memory accesses triggered by a demand data translation table walk and performing a read of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that this event counts accesses triggered by software preloads, but not accesses triggered by hardware prefetchers." + }, + { + "ArchStdEvent": "ITLB_STEP", + "PublicDescription": "Counts number of memory accesses triggered by an instruction translation table walk and performing a read of a translation table entry. Memory accesses are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD." + }, + { + "ArchStdEvent": "DTLB_WALK_LARGE", + "PublicDescription": "Counts number of demand data translation table walks caused by a miss in the L2 TLB and yielding a large page. The set of large pages is defined as all pages with a final size higher than or equal to 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. If DTLB_WALK_BLOCK is implemented, then it is an alias for this event in this family. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK_LARGE", + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and yielding a large page. The set of large pages is defined as all pages with a final size higher than or equal to 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. In this family, this is equal to ITLB_WALK_BLOCK event. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK_SMALL", + "PublicDescription": "Counts number of data translation table walks caused by a miss in the L2 TLB and yielding a small page. The set of small pages is defined as all pages with a final size lower than 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. If DTLB_WALK_PAGE event is implemented, then it is an alias for this event in this family. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK_SMALL", + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and yielding a small page. The set of small pages is defined as all pages with a final size lower than 2MB. Translation table walks that end up taking a translation fault are not counted, as the page size would be undefined in that case. In this family, this is equal to ITLB_WALK_PAGE event. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK_RW", + "PublicDescription": "Counts number of demand data translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK_RD", + "PublicDescription": "Counts number of demand instruction translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK_PRFM", + "PublicDescription": "Counts number of software prefetches or preloads generated data translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK_PRFM", + "PublicDescription": "Counts number of software prefetches or preloads generated instruction translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json index dddecc946575..e40be37addf8 100644 --- a/tools/perf/pmu-events/arch/arm64/common-and-microarch.json +++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json @@ -228,6 +228,16 @@ "BriefDescription": "Attributable Level 1 instruction TLB access" }, { + "EventCode": "0x27", + "EventName": "L2I_CACHE", + "BriefDescription": "Level 2 instruction cache access" + }, + { + "EventCode": "0x28", + "EventName": "L2I_CACHE_REFILL", + "BriefDescription": "Level 2 instruction cache refill" + }, + { "PublicDescription": "Attributable Level 3 data cache allocation without refill", "EventCode": "0x29", "EventName": "L3D_CACHE_ALLOCATE", @@ -276,6 +286,16 @@ "BriefDescription": "Access to another socket in a multi-socket system" }, { + "EventCode": "0x32", + "EventName": "LL_CACHE", + "BriefDescription": "Last level cache access" + }, + { + "EventCode": "0x33", + "EventName": "LL_CACHE_MISS", + "BriefDescription": "Last level cache miss" + }, + { "PublicDescription": "Access to data TLB causes a translation table walk", "EventCode": "0x34", "EventName": "DTLB_WALK", @@ -396,6 +416,11 @@ "BriefDescription": "Level 2 data cache long-latency read miss" }, { + "EventCode": "0x400A", + "EventName": "L2I_CACHE_LMISS", + "BriefDescription": "Level 2 instruction cache long-latency miss" + }, + { "PublicDescription": "Level 3 data cache long-latency read miss. The counter counts each memory read access counted by L3D_CACHE that incurs additional latency because it returns data from outside the Level 3 data or unified cache of this processing element. The event indicates to software that the access missed in the Level 3 data or unified cache and might have a significant performance impact compared to the latency of an access that hits in the Level 3 data or unified cache.", "EventCode": "0x400B", "EventName": "L3D_CACHE_LMISS_RD", @@ -522,6 +547,11 @@ "BriefDescription": "Instruction architecturally executed, SVE." }, { + "EventCode": "0x8004", + "EventName": "SIMD_INST_SPEC", + "BriefDescription": "Operation speculatively executed, SIMD" + }, + { "PublicDescription": "ASE operations speculatively executed", "EventCode": "0x8005", "EventName": "ASE_INST_SPEC", @@ -1210,6 +1240,106 @@ "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE matrix multiply." }, { + "EventCode": "0x8108", + "EventName": "BR_IMMED_TAKEN_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, immediate, taken" + }, + { + "EventCode": "0x810C", + "EventName": "BR_INDNR_TAKEN_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, indirect excluding procedure return, taken" + }, + { + "EventCode": "0x8110", + "EventName": "BR_IMMED_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, predicted immediate" + }, + { + "EventCode": "0x8111", + "EventName": "BR_IMMED_MIS_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, mispredicted immediate" + }, + { + "EventCode": "0x8112", + "EventName": "BR_IND_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, predicted indirect" + }, + { + "EventCode": "0x8113", + "EventName": "BR_IND_MIS_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, mispredicted indirect" + }, + { + "EventCode": "0x8114", + "EventName": "BR_RETURN_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, predicted procedure return" + }, + { + "EventCode": "0x8115", + "EventName": "BR_RETURN_MIS_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, mispredicted procedure return" + }, + { + "EventCode": "0x8116", + "EventName": "BR_INDNR_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, predicted indirect excluding procedure return" + }, + { + "EventCode": "0x8117", + "EventName": "BR_INDNR_MIS_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, mispredicted indirect excluding procedure return" + }, + { + "EventCode": "0x8118", + "EventName": "BR_TAKEN_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, predicted branch, taken" + }, + { + "EventCode": "0x8119", + "EventName": "BR_TAKEN_MIS_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, mispredicted branch, taken" + }, + { + "EventCode": "0x811A", + "EventName": "BR_SKIP_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, predicted branch, not taken" + }, + { + "EventCode": "0x811B", + "EventName": "BR_SKIP_MIS_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, mispredicted branch, not taken" + }, + { + "EventCode": "0x811C", + "EventName": "BR_PRED_RETIRED", + "BriefDescription": "Branch instruction architecturally executed, predicted branch" + }, + { + "EventCode": "0x811D", + "EventName": "BR_IND_RETIRED", + "BriefDescription": "Instruction architecturally executed, indirect branch" + }, + { + "EventCode": "0x811F", + "EventName": "BRB_FILTRATE", + "BriefDescription": "Branch Record captured" + }, + { + "EventCode": "0x8120", + "EventName": "INST_FETCH_PERCYC", + "BriefDescription": "Event in progress, INST FETCH" + }, + { + "EventCode": "0x8121", + "EventName": "MEM_ACCESS_RD_PERCYC", + "BriefDescription": "Event in progress, MEM ACCESS RD" + }, + { + "EventCode": "0x8124", + "EventName": "INST_FETCH", + "BriefDescription": "Instruction memory access" + }, + { "EventCode": "0x8128", "EventName": "DTLB_WALK_PERCYC", "BriefDescription": "Data translation table walks in progress." @@ -1220,6 +1350,66 @@ "BriefDescription": "Instruction translation table walks in progress." }, { + "EventCode": "0x812A", + "EventName": "SAMPLE_FEED_BR", + "BriefDescription": "Statisical Profiling sample taken, branch" + }, + { + "EventCode": "0x812B", + "EventName": "SAMPLE_FEED_LD", + "BriefDescription": "Statisical Profiling sample taken, load" + }, + { + "EventCode": "0x812C", + "EventName": "SAMPLE_FEED_ST", + "BriefDescription": "Statisical Profiling sample taken, store" + }, + { + "EventCode": "0x812D", + "EventName": "SAMPLE_FEED_OP", + "BriefDescription": "Statisical Profiling sample taken, matching operation type" + }, + { + "EventCode": "0x812E", + "EventName": "SAMPLE_FEED_EVENT", + "BriefDescription": "Statisical Profiling sample taken, matching events" + }, + { + "EventCode": "0x812F", + "EventName": "SAMPLE_FEED_LAT", + "BriefDescription": "Statisical Profiling sample taken, exceeding minimum latency" + }, + { + "EventCode": "0x8130", + "EventName": "L1D_TLB_RW", + "BriefDescription": "Level 1 data TLB demand access" + }, + { + "EventCode": "0x8131", + "EventName": "L1I_TLB_RD", + "BriefDescription": "Level 1 instruction TLB demand access" + }, + { + "EventCode": "0x8132", + "EventName": "L1D_TLB_PRFM", + "BriefDescription": "Level 1 data TLB software preload" + }, + { + "EventCode": "0x8133", + "EventName": "L1I_TLB_PRFM", + "BriefDescription": "Level 1 instruction TLB software preload" + }, + { + "EventCode": "0x8134", + "EventName": "DTLB_HWUPD", + "BriefDescription": "Data TLB hardware update of translation table" + }, + { + "EventCode": "0x8135", + "EventName": "ITLB_HWUPD", + "BriefDescription": "Instruction TLB hardware update of translation table" + }, + { "EventCode": "0x8136", "EventName": "DTLB_STEP", "BriefDescription": "Data TLB translation table walk, step." @@ -1250,6 +1440,46 @@ "BriefDescription": "Instruction TLB small page translation table walk." }, { + "EventCode": "0x813C", + "EventName": "DTLB_WALK_RW", + "BriefDescription": "Data TLB demand access with at least one translation table walk" + }, + { + "EventCode": "0x813D", + "EventName": "ITLB_WALK_RD", + "BriefDescription": "Instruction TLB demand access with at least one translation table walk" + }, + { + "EventCode": "0x813E", + "EventName": "DTLB_WALK_PRFM", + "BriefDescription": "Data TLB software preload access with at least one translation table walk" + }, + { + "EventCode": "0x813F", + "EventName": "ITLB_WALK_PRFM", + "BriefDescription": "Instruction TLB software preload access with at least one translation table walk" + }, + { + "EventCode": "0x8140", + "EventName": "L1D_CACHE_RW", + "BriefDescription": "Level 1 data cache demand access" + }, + { + "EventCode": "0x8141", + "EventName": "L1I_CACHE_RD", + "BriefDescription": "Level 1 instruction cache demand fetch" + }, + { + "EventCode": "0x8142", + "EventName": "L1D_CACHE_PRFM", + "BriefDescription": "Level 1 data cache software preload" + }, + { + "EventCode": "0x8143", + "EventName": "L1I_CACHE_PRFM", + "BriefDescription": "Level 1 instruction cache software preload" + }, + { "EventCode": "0x8144", "EventName": "L1D_CACHE_MISS", "BriefDescription": "Level 1 data cache demand access miss." @@ -1260,11 +1490,46 @@ "BriefDescription": "Level 1 instruction cache hardware prefetch." }, { + "EventCode": "0x8146", + "EventName": "L1D_CACHE_REFILL_PRFM", + "BriefDescription": "Level 1 data cache refill, software preload" + }, + { + "EventCode": "0x8147", + "EventName": "L1I_CACHE_REFILL_PRFM", + "BriefDescription": "Level 1 instruction cache refill, software preload" + }, + { + "EventCode": "0x8148", + "EventName": "L2D_CACHE_RW", + "BriefDescription": "Level 2 data cache demand access" + }, + { + "EventCode": "0x8149", + "EventName": "L2I_CACHE_RD", + "BriefDescription": "Level 2 instruction cache demand fetch" + }, + { + "EventCode": "0x814A", + "EventName": "L2D_CACHE_PRFM", + "BriefDescription": "Level 2 data cache software preload" + }, + { "EventCode": "0x814C", "EventName": "L2D_CACHE_MISS", "BriefDescription": "Level 2 data cache demand access miss." }, { + "EventCode": "0x814E", + "EventName": "L2D_CACHE_REFILL_PRFM", + "BriefDescription": "Level 2 data cache refill, software preload" + }, + { + "EventCode": "0x8152", + "EventName": "L3D_CACHE_MISS", + "BriefDescription": "Level 3 data cache demand access miss" + }, + { "EventCode": "0x8154", "EventName": "L1D_CACHE_HWPRF", "BriefDescription": "Level 1 data cache hardware prefetch." @@ -1375,6 +1640,21 @@ "BriefDescription": "Backend stall cycles, Memory Copy or Set operation." }, { + "EventCode": "0x8171", + "EventName": "CAS_NEAR_PASS", + "BriefDescription": "Atomic memory Operation speculatively executed, Compare and Swap pass" + }, + { + "EventCode": "0x8172", + "EventName": "CAS_NEAR_SPEC", + "BriefDescription": "Atomic memory Operation speculatively executed, Compare and Swap near" + }, + { + "EventCode": "0x8173", + "EventName": "CAS_FAR_SPEC", + "BriefDescription": "Atomic memory Operation speculatively executed, Compare and Swap far" + }, + { "EventCode": "0x8186", "EventName": "UOP_RETIRED", "BriefDescription": "Micro-operation architecturally executed." @@ -1440,6 +1720,16 @@ "BriefDescription": "Level 2 data cache demand access hit, write." }, { + "EventCode": "0x81D0", + "EventName": "L1I_CACHE_HIT_RD_FPRFM", + "BriefDescription": "Level 1 instruction cache demand fetch first hit, fetched by software preload" + }, + { + "EventCode": "0x81E0", + "EventName": "L1I_CACHE_HIT_RD_FHWPRF", + "BriefDescription": "Level 1 instruction cache demand fetch first hit, fetched by hardware prefetcher" + }, + { "EventCode": "0x8200", "EventName": "L1I_CACHE_HIT", "BriefDescription": "Level 1 instruction cache hit." @@ -1455,6 +1745,11 @@ "BriefDescription": "Level 2 data cache hit." }, { + "EventCode": "0x8208", + "EventName": "L1I_CACHE_HIT_PRFM", + "BriefDescription": "Level 1 instruction cache software preload hit" + }, + { "EventCode": "0x8240", "EventName": "L1I_LFB_HIT_RD", "BriefDescription": "Level 1 instruction cache demand fetch line-fill buffer hit." @@ -1480,6 +1775,16 @@ "BriefDescription": "Level 2 data cache demand access line-fill buffer hit, write." }, { + "EventCode": "0x8250", + "EventName": "L1I_LFB_HIT_RD_FPRFM", + "BriefDescription": "Level 1 instruction cache demand fetch line-fill buffer first hit, recently fetched by software preload" + }, + { + "EventCode": "0x8260", + "EventName": "L1I_LFB_HIT_RD_FHWPRF", + "BriefDescription": "Level 1 instruction cache demand fetch line-fill buffer first hit, recently fetched by hardware prefetcher" + }, + { "EventCode": "0x8280", "EventName": "L1I_CACHE_PRF", "BriefDescription": "Level 1 instruction cache, preload or prefetch hit." @@ -1510,6 +1815,11 @@ "BriefDescription": "Level 2 data cache refill, preload or prefetch hit." }, { + "EventCode": "0x829A", + "EventName": "LL_CACHE_REFILL", + "BriefDescription": "Last level cache refill" + }, + { "EventCode": "0x8320", "EventName": "L1D_CACHE_REFILL_PERCYC", "BriefDescription": "Level 1 data or unified cache refills in progress." diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 5c846fe90513..bb3fa8a33496 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -36,6 +36,8 @@ 0x00000000410fd480,v1,arm/cortex-x2,core 0x00000000410fd490,v1,arm/neoverse-n2-v2,core 0x00000000410fd4f0,v1,arm/neoverse-n2-v2,core +0x00000000410fd830,v1,arm/neoverse-v3,core +0x00000000410fd8e0,v1,arm/neoverse-n3,core 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000460f0010,v1,fujitsu/a64fx,core diff --git a/tools/perf/pmu-events/arch/riscv/mapfile.csv b/tools/perf/pmu-events/arch/riscv/mapfile.csv index 3d3a809a5446..0a7e7dcc81be 100644 --- a/tools/perf/pmu-events/arch/riscv/mapfile.csv +++ b/tools/perf/pmu-events/arch/riscv/mapfile.csv @@ -14,7 +14,11 @@ # # #MVENDORID-MARCHID-MIMPID,Version,Filename,EventType -0x489-0x8000000000000007-0x[[:xdigit:]]+,v1,sifive/u74,core +0x489-0x8000000000000007-0x[[:xdigit:]]+,v1,sifive/bullet,core +0x489-0x8000000000000[1-9a-e]07-0x[78ac][[:xdigit:]]+,v1,sifive/bullet-07,core +0x489-0x8000000000000[1-9a-e]07-0xd[[:xdigit:]]+,v1,sifive/bullet-0d,core +0x489-0x8000000000000008-0x[[:xdigit:]]+,v1,sifive/p550,core +0x489-0x8000000000000[1-6]08-0x[9b][[:xdigit:]]+,v1,sifive/p650,core 0x5b7-0x0-0x0,v1,thead/c900-legacy,core 0x67e-0x80000000db0000[89]0-0x[[:xdigit:]]+,v1,starfive/dubhe-80,core 0x31e-0x8000000000008a45-0x[[:xdigit:]]+,v1,andes/ax45,core diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/cycle-and-instruction-count.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/cycle-and-instruction-count.json new file mode 100644 index 000000000000..5c8124cfe926 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/cycle-and-instruction-count.json @@ -0,0 +1,12 @@ +[ + { + "EventName": "CORE_CLOCK_CYCLES", + "EventCode": "0x165", + "BriefDescription": "Counts core clock cycles" + }, + { + "EventName": "INSTRUCTIONS_RETIRED", + "EventCode": "0x265", + "BriefDescription": "Counts instructions retired" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/firmware.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/firmware.json new file mode 120000 index 000000000000..34e5c2870eee --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/firmware.json @@ -0,0 +1 @@ +../bullet/firmware.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/instruction.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/instruction.json new file mode 120000 index 000000000000..62eacc2d7497 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/instruction.json @@ -0,0 +1 @@ +../bullet/instruction.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/memory.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/memory.json new file mode 120000 index 000000000000..df50fc47a5fe --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/memory.json @@ -0,0 +1 @@ +../bullet/memory.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/microarch.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/microarch.json new file mode 100644 index 000000000000..de8efd7b8b34 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/microarch.json @@ -0,0 +1,62 @@ +[ + { + "EventName": "ADDRESSGEN_INTERLOCK", + "EventCode": "0x101", + "BriefDescription": "Counts cycles with an address-generation interlock" + }, + { + "EventName": "LONGLATENCY_INTERLOCK", + "EventCode": "0x201", + "BriefDescription": "Counts cycles with a long-latency interlock" + }, + { + "EventName": "CSR_INTERLOCK", + "EventCode": "0x401", + "BriefDescription": "Counts cycles with a CSR interlock" + }, + { + "EventName": "ICACHE_BLOCKED", + "EventCode": "0x801", + "BriefDescription": "Counts cycles in which the instruction cache was not able to provide an instruction" + }, + { + "EventName": "DCACHE_BLOCKED", + "EventCode": "0x1001", + "BriefDescription": "Counts cycles in which the data cache blocked an instruction" + }, + { + "EventName": "BRANCH_DIRECTION_MISPREDICTION", + "EventCode": "0x2001", + "BriefDescription": "Counts mispredictions of conditional branch direction (taken/not taken)" + }, + { + "EventName": "BRANCH_TARGET_MISPREDICTION", + "EventCode": "0x4001", + "BriefDescription": "Counts mispredictions of the target PC of control-flow instructions" + }, + { + "EventName": "PIPELINE_FLUSH", + "EventCode": "0x8001", + "BriefDescription": "Counts flushes of the core pipeline. Common causes include fence.i and CSR accesses" + }, + { + "EventName": "REPLAY", + "EventCode": "0x10001", + "BriefDescription": "Counts instruction replays" + }, + { + "EventName": "INTEGER_MUL_DIV_INTERLOCK", + "EventCode": "0x20001", + "BriefDescription": "Counts cycles with a multiply or divide interlock" + }, + { + "EventName": "FP_INTERLOCK", + "EventCode": "0x40001", + "BriefDescription": "Counts cycles with a floating-point interlock" + }, + { + "EventName": "TRACE_STALL", + "EventCode": "0x80001", + "BriefDescription": "Counts cycles in which the core pipeline is stalled due to backpressure from the Trace Encoder" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/watchpoint.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/watchpoint.json new file mode 100644 index 000000000000..aa7a12818521 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-07/watchpoint.json @@ -0,0 +1,42 @@ +[ + { + "EventName": "WATCHPOINT_0", + "EventCode": "0x164", + "BriefDescription": "Counts occurrences of watchpoint 0 with action=8" + }, + { + "EventName": "WATCHPOINT_1", + "EventCode": "0x264", + "BriefDescription": "Counts occurrences of watchpoint 1 with action=8" + }, + { + "EventName": "WATCHPOINT_2", + "EventCode": "0x464", + "BriefDescription": "Counts occurrences of watchpoint 2 with action=8" + }, + { + "EventName": "WATCHPOINT_3", + "EventCode": "0x864", + "BriefDescription": "Counts occurrences of watchpoint 3 with action=8" + }, + { + "EventName": "WATCHPOINT_4", + "EventCode": "0x1064", + "BriefDescription": "Counts occurrences of watchpoint 4 with action=8" + }, + { + "EventName": "WATCHPOINT_5", + "EventCode": "0x2064", + "BriefDescription": "Counts occurrences of watchpoint 5 with action=8" + }, + { + "EventName": "WATCHPOINT_6", + "EventCode": "0x4064", + "BriefDescription": "Counts occurrences of watchpoint 6 with action=8" + }, + { + "EventName": "WATCHPOINT_7", + "EventCode": "0x8064", + "BriefDescription": "Counts occurrences of watchpoint 7 with action=8" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/cycle-and-instruction-count.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/cycle-and-instruction-count.json new file mode 120000 index 000000000000..ccd29278f61b --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/cycle-and-instruction-count.json @@ -0,0 +1 @@ +../bullet-07/cycle-and-instruction-count.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/firmware.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/firmware.json new file mode 120000 index 000000000000..34e5c2870eee --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/firmware.json @@ -0,0 +1 @@ +../bullet/firmware.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/instruction.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/instruction.json new file mode 120000 index 000000000000..62eacc2d7497 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/instruction.json @@ -0,0 +1 @@ +../bullet/instruction.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/memory.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/memory.json new file mode 120000 index 000000000000..df50fc47a5fe --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/memory.json @@ -0,0 +1 @@ +../bullet/memory.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/microarch.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/microarch.json new file mode 100644 index 000000000000..6573b24788eb --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/microarch.json @@ -0,0 +1,72 @@ +[ + { + "EventName": "ADDRESSGEN_INTERLOCK", + "EventCode": "0x101", + "BriefDescription": "Counts cycles with an address-generation interlock" + }, + { + "EventName": "LONGLATENCY_INTERLOCK", + "EventCode": "0x201", + "BriefDescription": "Counts cycles with a long-latency interlock" + }, + { + "EventName": "CSR_INTERLOCK", + "EventCode": "0x401", + "BriefDescription": "Counts cycles with a CSR interlock" + }, + { + "EventName": "ICACHE_BLOCKED", + "EventCode": "0x801", + "BriefDescription": "Counts cycles in which the instruction cache was not able to provide an instruction" + }, + { + "EventName": "DCACHE_BLOCKED", + "EventCode": "0x1001", + "BriefDescription": "Counts cycles in which the data cache blocked an instruction" + }, + { + "EventName": "BRANCH_DIRECTION_MISPREDICTION", + "EventCode": "0x2001", + "BriefDescription": "Counts mispredictions of conditional branch direction (taken/not taken)" + }, + { + "EventName": "BRANCH_TARGET_MISPREDICTION", + "EventCode": "0x4001", + "BriefDescription": "Counts mispredictions of the target PC of control-flow instructions" + }, + { + "EventName": "PIPELINE_FLUSH", + "EventCode": "0x8001", + "BriefDescription": "Counts flushes of the core pipeline. Common causes include fence.i and CSR accesses" + }, + { + "EventName": "REPLAY", + "EventCode": "0x10001", + "BriefDescription": "Counts instruction replays" + }, + { + "EventName": "INTEGER_MUL_DIV_INTERLOCK", + "EventCode": "0x20001", + "BriefDescription": "Counts cycles with a multiply or divide interlock" + }, + { + "EventName": "FP_INTERLOCK", + "EventCode": "0x40001", + "BriefDescription": "Counts cycles with a floating-point interlock" + }, + { + "EventName": "TRACE_STALL", + "EventCode": "0x80001", + "BriefDescription": "Counts cycles in which the core pipeline is stalled due to backpressure from the Trace Encoder" + }, + { + "EventName": "ITLB_MISS_STALL", + "EventCode": "0x100001", + "BriefDescription": "Counts cycles in which the core pipeline is stalled due to ITLB Miss" + }, + { + "EventName": "DTLB_MISS_STALL", + "EventCode": "0x200001", + "BriefDescription": "Counts cycles in which the core pipeline is stalled due to DTLB Miss" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/watchpoint.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/watchpoint.json new file mode 120000 index 000000000000..e88b98bfc5c8 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet-0d/watchpoint.json @@ -0,0 +1 @@ +../bullet-07/watchpoint.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet/firmware.json index 7149caec4f80..7149caec4f80 100644 --- a/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet/firmware.json diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet/instruction.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet/instruction.json new file mode 100644 index 000000000000..284e4c1566e0 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet/instruction.json @@ -0,0 +1,92 @@ +[ + { + "EventName": "EXCEPTION_TAKEN", + "EventCode": "0x100", + "BriefDescription": "Counts exceptions taken" + }, + { + "EventName": "INTEGER_LOAD_RETIRED", + "EventCode": "0x200", + "BriefDescription": "Counts integer load instructions retired" + }, + { + "EventName": "INTEGER_STORE_RETIRED", + "EventCode": "0x400", + "BriefDescription": "Counts integer store instructions retired" + }, + { + "EventName": "ATOMIC_MEMORY_RETIRED", + "EventCode": "0x800", + "BriefDescription": "Counts atomic memory instructions retired" + }, + { + "EventName": "SYSTEM_INSTRUCTION_RETIRED", + "EventCode": "0x1000", + "BriefDescription": "Counts system instructions retired (CSR, WFI, MRET, etc.)" + }, + { + "EventName": "INTEGER_ARITHMETIC_RETIRED", + "EventCode": "0x2000", + "BriefDescription": "Counts integer arithmetic instructions retired" + }, + { + "EventName": "CONDITIONAL_BRANCH_RETIRED", + "EventCode": "0x4000", + "BriefDescription": "Counts conditional branch instructions retired" + }, + { + "EventName": "JAL_INSTRUCTION_RETIRED", + "EventCode": "0x8000", + "BriefDescription": "Counts jump-and-link instructions retired" + }, + { + "EventName": "JALR_INSTRUCTION_RETIRED", + "EventCode": "0x10000", + "BriefDescription": "Counts indirect jump instructions (JALR) retired" + }, + { + "EventName": "INTEGER_MULTIPLICATION_RETIRED", + "EventCode": "0x20000", + "BriefDescription": "Counts integer multiplication instructions retired" + }, + { + "EventName": "INTEGER_DIVISION_RETIRED", + "EventCode": "0x40000", + "BriefDescription": "Counts integer division instructions retired" + }, + { + "EventName": "FP_LOAD_RETIRED", + "EventCode": "0x80000", + "BriefDescription": "Counts floating-point load instructions retired" + }, + { + "EventName": "FP_STORE_RETIRED", + "EventCode": "0x100000", + "BriefDescription": "Counts floating-point store instructions retired" + }, + { + "EventName": "FP_ADD_RETIRED", + "EventCode": "0x200000", + "BriefDescription": "Counts floating-point add instructions retired" + }, + { + "EventName": "FP_MUL_RETIRED", + "EventCode": "0x400000", + "BriefDescription": "Counts floating-point multiply instructions retired" + }, + { + "EventName": "FP_MULADD_RETIRED", + "EventCode": "0x800000", + "BriefDescription": "Counts floating-point fused multiply-add instructions retired" + }, + { + "EventName": "FP_DIV_SQRT_RETIRED", + "EventCode": "0x1000000", + "BriefDescription": "Counts floating point divide or square root instructions retired" + }, + { + "EventName": "OTHER_FP_RETIRED", + "EventCode": "0x2000000", + "BriefDescription": "Counts other floating-point instructions retired" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet/memory.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet/memory.json new file mode 100644 index 000000000000..70441a55dd66 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet/memory.json @@ -0,0 +1,32 @@ +[ + { + "EventName": "ICACHE_MISS", + "EventCode": "0x102", + "BriefDescription": "Counts instruction cache misses" + }, + { + "EventName": "DCACHE_MISS", + "EventCode": "0x202", + "BriefDescription": "Counts data cache misses" + }, + { + "EventName": "DCACHE_RELEASE", + "EventCode": "0x402", + "BriefDescription": "Counts writeback requests from the data cache" + }, + { + "EventName": "ITLB_MISS", + "EventCode": "0x802", + "BriefDescription": "Counts Instruction TLB misses caused by instruction address translation requests" + }, + { + "EventName": "DTLB_MISS", + "EventCode": "0x1002", + "BriefDescription": "Counts Data TLB misses caused by data address translation requests" + }, + { + "EventName": "UTLB_MISS", + "EventCode": "0x2002", + "BriefDescription": "Counts Unified TLB misses caused by address translation requests" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/bullet/microarch.json b/tools/perf/pmu-events/arch/riscv/sifive/bullet/microarch.json new file mode 100644 index 000000000000..d9cdb7d747ee --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/bullet/microarch.json @@ -0,0 +1,57 @@ +[ + { + "EventName": "ADDRESSGEN_INTERLOCK", + "EventCode": "0x101", + "BriefDescription": "Counts cycles with an address-generation interlock" + }, + { + "EventName": "LONGLATENCY_INTERLOCK", + "EventCode": "0x201", + "BriefDescription": "Counts cycles with a long-latency interlock" + }, + { + "EventName": "CSR_INTERLOCK", + "EventCode": "0x401", + "BriefDescription": "Counts cycles with a CSR interlock" + }, + { + "EventName": "ICACHE_BLOCKED", + "EventCode": "0x801", + "BriefDescription": "Counts cycles in which the instruction cache was not able to provide an instruction" + }, + { + "EventName": "DCACHE_BLOCKED", + "EventCode": "0x1001", + "BriefDescription": "Counts cycles in which the data cache blocked an instruction" + }, + { + "EventName": "BRANCH_DIRECTION_MISPREDICTION", + "EventCode": "0x2001", + "BriefDescription": "Counts mispredictions of conditional branch direction (taken/not taken)" + }, + { + "EventName": "BRANCH_TARGET_MISPREDICTION", + "EventCode": "0x4001", + "BriefDescription": "Counts mispredictions of the target PC of control-flow instructions" + }, + { + "EventName": "PIPELINE_FLUSH", + "EventCode": "0x8001", + "BriefDescription": "Counts flushes of the core pipeline. Common causes include fence.i and CSR accesses" + }, + { + "EventName": "REPLAY", + "EventCode": "0x10001", + "BriefDescription": "Counts instruction replays" + }, + { + "EventName": "INTEGER_MUL_DIV_INTERLOCK", + "EventCode": "0x20001", + "BriefDescription": "Counts cycles with a multiply or divide interlock" + }, + { + "EventName": "FP_INTERLOCK", + "EventCode": "0x40001", + "BriefDescription": "Counts cycles with a floating-point interlock" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p550/firmware.json b/tools/perf/pmu-events/arch/riscv/sifive/p550/firmware.json new file mode 120000 index 000000000000..34e5c2870eee --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p550/firmware.json @@ -0,0 +1 @@ +../bullet/firmware.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p550/instruction.json b/tools/perf/pmu-events/arch/riscv/sifive/p550/instruction.json new file mode 120000 index 000000000000..62eacc2d7497 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p550/instruction.json @@ -0,0 +1 @@ +../bullet/instruction.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p550/memory.json b/tools/perf/pmu-events/arch/riscv/sifive/p550/memory.json new file mode 100644 index 000000000000..8393f81b2cf0 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p550/memory.json @@ -0,0 +1,47 @@ +[ + { + "EventName": "ICACHE_MISS", + "EventCode": "0x102", + "BriefDescription": "Counts instruction cache misses" + }, + { + "EventName": "DCACHE_MISS", + "EventCode": "0x202", + "BriefDescription": "Counts data cache misses" + }, + { + "EventName": "DCACHE_RELEASE", + "EventCode": "0x402", + "BriefDescription": "Counts writeback requests from the data cache" + }, + { + "EventName": "ITLB_MISS", + "EventCode": "0x802", + "BriefDescription": "Counts Instruction TLB misses caused by instruction address translation requests" + }, + { + "EventName": "DTLB_MISS", + "EventCode": "0x1002", + "BriefDescription": "Counts Data TLB misses caused by data address translation requests" + }, + { + "EventName": "UTLB_MISS", + "EventCode": "0x2002", + "BriefDescription": "Counts Unified TLB misses caused by address translation requests" + }, + { + "EventName": "UTLB_HIT", + "EventCode": "0x4002", + "BriefDescription": "Counts Unified TLB hits for address translation requests" + }, + { + "EventName": "PTE_CACHE_MISS", + "EventCode": "0x8002", + "BriefDescription": "Counts Page Table Entry cache misses" + }, + { + "EventName": "PTE_CACHE_HIT", + "EventCode": "0x10002", + "BriefDescription": "Counts Page Table Entry cache hits" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p550/microarch.json b/tools/perf/pmu-events/arch/riscv/sifive/p550/microarch.json new file mode 120000 index 000000000000..ba5dd2960e9f --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p550/microarch.json @@ -0,0 +1 @@ +../bullet/microarch.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p650/cycle-and-instruction-count.json b/tools/perf/pmu-events/arch/riscv/sifive/p650/cycle-and-instruction-count.json new file mode 120000 index 000000000000..ccd29278f61b --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p650/cycle-and-instruction-count.json @@ -0,0 +1 @@ +../bullet-07/cycle-and-instruction-count.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p650/firmware.json b/tools/perf/pmu-events/arch/riscv/sifive/p650/firmware.json new file mode 120000 index 000000000000..34e5c2870eee --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p650/firmware.json @@ -0,0 +1 @@ +../bullet/firmware.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p650/instruction.json b/tools/perf/pmu-events/arch/riscv/sifive/p650/instruction.json new file mode 120000 index 000000000000..62eacc2d7497 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p650/instruction.json @@ -0,0 +1 @@ +../bullet/instruction.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p650/memory.json b/tools/perf/pmu-events/arch/riscv/sifive/p650/memory.json new file mode 100644 index 000000000000..f1431b339c7f --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p650/memory.json @@ -0,0 +1,57 @@ +[ + { + "EventName": "ICACHE_MISS", + "EventCode": "0x102", + "BriefDescription": "Counts instruction cache misses" + }, + { + "EventName": "DCACHE_MISS", + "EventCode": "0x202", + "BriefDescription": "Counts data cache misses" + }, + { + "EventName": "DCACHE_RELEASE", + "EventCode": "0x402", + "BriefDescription": "Counts writeback requests from the data cache" + }, + { + "EventName": "ITLB_MISS", + "EventCode": "0x802", + "BriefDescription": "Counts Instruction TLB misses caused by instruction address translation requests" + }, + { + "EventName": "DTLB_MISS", + "EventCode": "0x1002", + "BriefDescription": "Counts Data TLB misses caused by data address translation requests" + }, + { + "EventName": "UTLB_MISS", + "EventCode": "0x2002", + "BriefDescription": "Counts Unified TLB misses caused by address translation requests" + }, + { + "EventName": "UTLB_HIT", + "EventCode": "0x4002", + "BriefDescription": "Counts Unified TLB hits for address translation requests" + }, + { + "EventName": "PTE_CACHE_MISS", + "EventCode": "0x8002", + "BriefDescription": "Counts Page Table Entry cache misses" + }, + { + "EventName": "PTE_CACHE_HIT", + "EventCode": "0x10002", + "BriefDescription": "Counts Page Table Entry cache hits" + }, + { + "EventName": "ITLB_MULTI_HIT", + "EventCode": "0x20002", + "BriefDescription": "Counts Instruction TLB multi-hits" + }, + { + "EventName": "DTLB_MULTI_HIT", + "EventCode": "0x40002", + "BriefDescription": "Counts Data TLB multi-hits" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p650/microarch.json b/tools/perf/pmu-events/arch/riscv/sifive/p650/microarch.json new file mode 100644 index 000000000000..de8efd7b8b34 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p650/microarch.json @@ -0,0 +1,62 @@ +[ + { + "EventName": "ADDRESSGEN_INTERLOCK", + "EventCode": "0x101", + "BriefDescription": "Counts cycles with an address-generation interlock" + }, + { + "EventName": "LONGLATENCY_INTERLOCK", + "EventCode": "0x201", + "BriefDescription": "Counts cycles with a long-latency interlock" + }, + { + "EventName": "CSR_INTERLOCK", + "EventCode": "0x401", + "BriefDescription": "Counts cycles with a CSR interlock" + }, + { + "EventName": "ICACHE_BLOCKED", + "EventCode": "0x801", + "BriefDescription": "Counts cycles in which the instruction cache was not able to provide an instruction" + }, + { + "EventName": "DCACHE_BLOCKED", + "EventCode": "0x1001", + "BriefDescription": "Counts cycles in which the data cache blocked an instruction" + }, + { + "EventName": "BRANCH_DIRECTION_MISPREDICTION", + "EventCode": "0x2001", + "BriefDescription": "Counts mispredictions of conditional branch direction (taken/not taken)" + }, + { + "EventName": "BRANCH_TARGET_MISPREDICTION", + "EventCode": "0x4001", + "BriefDescription": "Counts mispredictions of the target PC of control-flow instructions" + }, + { + "EventName": "PIPELINE_FLUSH", + "EventCode": "0x8001", + "BriefDescription": "Counts flushes of the core pipeline. Common causes include fence.i and CSR accesses" + }, + { + "EventName": "REPLAY", + "EventCode": "0x10001", + "BriefDescription": "Counts instruction replays" + }, + { + "EventName": "INTEGER_MUL_DIV_INTERLOCK", + "EventCode": "0x20001", + "BriefDescription": "Counts cycles with a multiply or divide interlock" + }, + { + "EventName": "FP_INTERLOCK", + "EventCode": "0x40001", + "BriefDescription": "Counts cycles with a floating-point interlock" + }, + { + "EventName": "TRACE_STALL", + "EventCode": "0x80001", + "BriefDescription": "Counts cycles in which the core pipeline is stalled due to backpressure from the Trace Encoder" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/sifive/p650/watchpoint.json b/tools/perf/pmu-events/arch/riscv/sifive/p650/watchpoint.json new file mode 120000 index 000000000000..e88b98bfc5c8 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/sifive/p650/watchpoint.json @@ -0,0 +1 @@ +../bullet-07/watchpoint.json
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/u74/instructions.json b/tools/perf/pmu-events/arch/riscv/sifive/u74/instructions.json deleted file mode 100644 index 5eab718c9256..000000000000 --- a/tools/perf/pmu-events/arch/riscv/sifive/u74/instructions.json +++ /dev/null @@ -1,92 +0,0 @@ -[ - { - "EventName": "EXCEPTION_TAKEN", - "EventCode": "0x0000100", - "BriefDescription": "Exception taken" - }, - { - "EventName": "INTEGER_LOAD_RETIRED", - "EventCode": "0x0000200", - "BriefDescription": "Integer load instruction retired" - }, - { - "EventName": "INTEGER_STORE_RETIRED", - "EventCode": "0x0000400", - "BriefDescription": "Integer store instruction retired" - }, - { - "EventName": "ATOMIC_MEMORY_RETIRED", - "EventCode": "0x0000800", - "BriefDescription": "Atomic memory operation retired" - }, - { - "EventName": "SYSTEM_INSTRUCTION_RETIRED", - "EventCode": "0x0001000", - "BriefDescription": "System instruction retired" - }, - { - "EventName": "INTEGER_ARITHMETIC_RETIRED", - "EventCode": "0x0002000", - "BriefDescription": "Integer arithmetic instruction retired" - }, - { - "EventName": "CONDITIONAL_BRANCH_RETIRED", - "EventCode": "0x0004000", - "BriefDescription": "Conditional branch retired" - }, - { - "EventName": "JAL_INSTRUCTION_RETIRED", - "EventCode": "0x0008000", - "BriefDescription": "JAL instruction retired" - }, - { - "EventName": "JALR_INSTRUCTION_RETIRED", - "EventCode": "0x0010000", - "BriefDescription": "JALR instruction retired" - }, - { - "EventName": "INTEGER_MULTIPLICATION_RETIRED", - "EventCode": "0x0020000", - "BriefDescription": "Integer multiplication instruction retired" - }, - { - "EventName": "INTEGER_DIVISION_RETIRED", - "EventCode": "0x0040000", - "BriefDescription": "Integer division instruction retired" - }, - { - "EventName": "FP_LOAD_RETIRED", - "EventCode": "0x0080000", - "BriefDescription": "Floating-point load instruction retired" - }, - { - "EventName": "FP_STORE_RETIRED", - "EventCode": "0x0100000", - "BriefDescription": "Floating-point store instruction retired" - }, - { - "EventName": "FP_ADDITION_RETIRED", - "EventCode": "0x0200000", - "BriefDescription": "Floating-point addition retired" - }, - { - "EventName": "FP_MULTIPLICATION_RETIRED", - "EventCode": "0x0400000", - "BriefDescription": "Floating-point multiplication retired" - }, - { - "EventName": "FP_FUSEDMADD_RETIRED", - "EventCode": "0x0800000", - "BriefDescription": "Floating-point fused multiply-add retired" - }, - { - "EventName": "FP_DIV_SQRT_RETIRED", - "EventCode": "0x1000000", - "BriefDescription": "Floating-point division or square-root retired" - }, - { - "EventName": "OTHER_FP_RETIRED", - "EventCode": "0x2000000", - "BriefDescription": "Other floating-point instruction retired" - } -]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/u74/memory.json b/tools/perf/pmu-events/arch/riscv/sifive/u74/memory.json deleted file mode 100644 index be1a46312ac3..000000000000 --- a/tools/perf/pmu-events/arch/riscv/sifive/u74/memory.json +++ /dev/null @@ -1,32 +0,0 @@ -[ - { - "EventName": "ICACHE_RETIRED", - "EventCode": "0x0000102", - "BriefDescription": "Instruction cache miss" - }, - { - "EventName": "DCACHE_MISS_MMIO_ACCESSES", - "EventCode": "0x0000202", - "BriefDescription": "Data cache miss or memory-mapped I/O access" - }, - { - "EventName": "DCACHE_WRITEBACK", - "EventCode": "0x0000402", - "BriefDescription": "Data cache write-back" - }, - { - "EventName": "INST_TLB_MISS", - "EventCode": "0x0000802", - "BriefDescription": "Instruction TLB miss" - }, - { - "EventName": "DATA_TLB_MISS", - "EventCode": "0x0001002", - "BriefDescription": "Data TLB miss" - }, - { - "EventName": "UTLB_MISS", - "EventCode": "0x0002002", - "BriefDescription": "UTLB miss" - } -]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/riscv/sifive/u74/microarch.json b/tools/perf/pmu-events/arch/riscv/sifive/u74/microarch.json deleted file mode 100644 index 50ffa55418cb..000000000000 --- a/tools/perf/pmu-events/arch/riscv/sifive/u74/microarch.json +++ /dev/null @@ -1,57 +0,0 @@ -[ - { - "EventName": "ADDRESSGEN_INTERLOCK", - "EventCode": "0x0000101", - "BriefDescription": "Address-generation interlock" - }, - { - "EventName": "LONGLAT_INTERLOCK", - "EventCode": "0x0000201", - "BriefDescription": "Long-latency interlock" - }, - { - "EventName": "CSR_READ_INTERLOCK", - "EventCode": "0x0000401", - "BriefDescription": "CSR read interlock" - }, - { - "EventName": "ICACHE_ITIM_BUSY", - "EventCode": "0x0000801", - "BriefDescription": "Instruction cache/ITIM busy" - }, - { - "EventName": "DCACHE_DTIM_BUSY", - "EventCode": "0x0001001", - "BriefDescription": "Data cache/DTIM busy" - }, - { - "EventName": "BRANCH_DIRECTION_MISPREDICTION", - "EventCode": "0x0002001", - "BriefDescription": "Branch direction misprediction" - }, - { - "EventName": "BRANCH_TARGET_MISPREDICTION", - "EventCode": "0x0004001", - "BriefDescription": "Branch/jump target misprediction" - }, - { - "EventName": "PIPE_FLUSH_CSR_WRITE", - "EventCode": "0x0008001", - "BriefDescription": "Pipeline flush from CSR write" - }, - { - "EventName": "PIPE_FLUSH_OTHER_EVENT", - "EventCode": "0x0010001", - "BriefDescription": "Pipeline flush from other event" - }, - { - "EventName": "INTEGER_MULTIPLICATION_INTERLOCK", - "EventCode": "0x0020001", - "BriefDescription": "Integer multiplication interlock" - }, - { - "EventName": "FP_INTERLOCK", - "EventCode": "0x0040001", - "BriefDescription": "Floating-point interlock" - } -]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 8fdf4a4225de..147379cae37b 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -49,13 +49,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "C8 residency percent per package", "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", "MetricGroup": "Power", @@ -63,13 +56,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -117,7 +103,7 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -127,7 +113,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "tma_backend_bound > 0.1", + "MetricThreshold": "(tma_backend_bound >0.10)", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%", @@ -139,7 +125,7 @@ "MetricExpr": "(5 * cpu_atom@CPU_CLK_UNHALTED.CORE@ - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_bad_speculation >0.15)", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", @@ -150,7 +136,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -160,7 +146,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -170,7 +156,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -179,7 +165,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -188,7 +174,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", + "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -198,7 +184,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -207,7 +193,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", + "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -217,7 +203,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_frontend_bound >0.20)", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -227,7 +213,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -236,7 +222,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -246,7 +232,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -384,6 +370,12 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2", + "MetricExpr": "100 * (cpu_atom@MEM_BOUND_STALLS.IFETCH_LLC_HIT@ + cpu_atom@MEM_BOUND_STALLS.IFETCH_DRAM_HIT@) / cpu_atom@MEM_BOUND_STALLS.IFETCH@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@", "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit", @@ -403,6 +395,13 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2", + "MetricExpr": "100 * (cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ + cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@) / cpu_atom@MEM_BOUND_STALLS.LOAD@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "load_store_bound", @@ -548,7 +547,7 @@ { "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", "MetricExpr": "100 * cpu_atom@SERIALIZATION.C01_MS_SCB@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", - "MetricName": "tma_info_serialization _%_tpause_cycles", + "MetricName": "tma_info_serialization_%_tpause_cycles", "Unit": "cpu_atom" }, { @@ -565,6 +564,13 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@ / cpu_atom@CPU_CLK_UNHALTED.REF_TSC@", "MetricGroup": "Power", @@ -600,7 +606,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -609,7 +615,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -619,7 +625,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -628,7 +634,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -637,7 +643,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", + "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -646,7 +652,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -655,7 +661,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -664,7 +670,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -673,7 +679,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -682,7 +688,7 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", + "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -693,7 +699,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "tma_retiring > 0.75", + "MetricThreshold": "(tma_retiring >0.75)", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -703,7 +709,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -715,7 +721,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -728,13 +734,13 @@ "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -745,7 +751,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -762,18 +768,123 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%", "Unit": "cpu_core" }, { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20", + "Unit": "cpu_core" + }, + { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -782,26 +893,26 @@ "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -810,7 +921,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -820,18 +931,72 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD@ / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(25 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((28 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + (27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -842,26 +1007,26 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "24 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricExpr": "(27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -871,7 +1036,7 @@ "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -881,8 +1046,8 @@ "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -892,7 +1057,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -901,48 +1066,48 @@ "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "cpu_core@L1D_PEND_MISS.FB_FULL@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -953,28 +1118,28 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -984,7 +1149,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -994,7 +1159,16 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1003,8 +1177,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1013,8 +1187,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1023,8 +1197,8 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1033,41 +1207,41 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1076,21 +1250,21 @@ "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / 100", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 6 / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", @@ -1098,7 +1272,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", @@ -1106,15 +1280,15 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -1130,7 +1304,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "cpu_core@INT_MISC.CLEARS_COUNT@ / (cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ + cpu_core@MACHINE_CLEARS.COUNT@)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio", @@ -1146,8 +1320,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", @@ -1155,7 +1329,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -1164,116 +1338,10 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY\\,umask\\=1@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20", "Unit": "cpu_core" }, { @@ -1344,12 +1412,12 @@ "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", "Unit": "cpu_core" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" @@ -1364,22 +1432,22 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost", "Unit": "cpu_core" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency", "Unit": "cpu_core" @@ -1421,15 +1489,22 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc", + "Unit": "cpu_core" + }, + { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch", @@ -1449,7 +1524,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", "Unit": "cpu_core" }, { @@ -1458,7 +1533,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1467,7 +1542,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1476,7 +1551,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1485,7 +1560,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1537,7 +1612,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.ANY@", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100", @@ -1548,7 +1623,7 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 13", + "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", "Unit": "cpu_core" }, @@ -1589,7 +1664,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw", "Unit": "cpu_core" @@ -1610,7 +1685,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw", "Unit": "cpu_core" @@ -1659,14 +1734,14 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw", "Unit": "cpu_core" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw", "Unit": "cpu_core" @@ -1688,13 +1763,13 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS.DEMAND_DATA_RD@", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency", "Unit": "cpu_core" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp", "Unit": "cpu_core" @@ -1736,6 +1811,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "cpu_core@L2_LINES_OUT.USELESS_HWPF@ / (cpu_core@L2_LINES_OUT.SILENT@ + cpu_core@L2_LINES_OUT.NON_SILENT@)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15", + "Unit": "cpu_core" + }, + { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", "MetricGroup": "Fed;MemoryTLB", @@ -1765,8 +1848,8 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "BriefDescription": "", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute", "Unit": "cpu_core" @@ -1797,20 +1880,20 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire", "Unit": "cpu_core" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", @@ -1826,7 +1909,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency", "Unit": "cpu_core" @@ -1847,15 +1930,15 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / duration_time", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", @@ -1863,22 +1946,23 @@ }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", "Unit": "cpu_core" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", @@ -1902,6 +1986,21 @@ "Unit": "cpu_core" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@ / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power", + "Unit": "cpu_core" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - cpu_core@CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE@ / cpu_core@CPU_CLK_UNHALTED.REF_DISTRIBUTED@ if #SMT_on else 0)", "MetricGroup": "SMT", @@ -1916,6 +2015,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / cpu_core@CPU_CLK_UNHALTED.REF_TSC@", "MetricGroup": "Power", @@ -1923,7 +2030,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks", @@ -1934,6 +2041,7 @@ "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { @@ -1941,7 +2049,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", "Unit": "cpu_core" }, { @@ -1953,14 +2061,14 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "cpu_core@TOPDOWN.SLOTS@", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization", "Unit": "cpu_core" @@ -1978,7 +2086,16 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 9", + "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { @@ -1987,7 +2104,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1996,8 +2113,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2006,8 +2123,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2016,28 +2133,28 @@ "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2046,8 +2163,18 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "3 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2056,18 +2183,18 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "9 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks", + "MetricExpr": "(12 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2076,19 +2203,19 @@ "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2107,7 +2234,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2116,16 +2243,43 @@ "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2136,7 +2290,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2147,17 +2301,17 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2166,34 +2320,34 @@ "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -2207,7 +2361,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2216,8 +2370,8 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2232,22 +2386,31 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", + "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2257,7 +2420,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2266,7 +2429,7 @@ "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2282,20 +2445,20 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2305,7 +2468,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2315,7 +2478,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2325,7 +2488,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2335,27 +2498,27 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_thread_clks)", + "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY\\,umask\\=1@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks", + "MetricExpr": "(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY_RESOURCE@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2364,7 +2527,7 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2375,8 +2538,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2386,7 +2549,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2394,7 +2557,7 @@ { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2408,7 +2571,7 @@ "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2418,8 +2581,8 @@ "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", + "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2429,7 +2592,7 @@ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2439,8 +2602,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu_core@LD_BLOCKS.NO_SR@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2449,18 +2612,18 @@ "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2469,8 +2632,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2479,18 +2642,18 @@ "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2509,7 +2672,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2518,7 +2681,34 @@ "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2527,7 +2717,7 @@ "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2537,7 +2727,7 @@ "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2547,8 +2737,8 @@ "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%", "Unit": "cpu_core" } diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json index 3f51686fe7a8..a20e19738046 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json @@ -92,6 +92,26 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", "Counter": "0,1,2,3", "EventCode": "0x26", @@ -102,6 +122,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the total number of L2 Cache accesses. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PublicDescription": "Counts the total number of L2 Cache Accesses, includes hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only. Counts on a per core basis.", + "SampleAfterValue": "200003", + "Unit": "cpu_atom" + }, + { "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES]", "Counter": "0,1,2,3", "EventCode": "0x24", @@ -112,6 +141,26 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of L2 Cache accesses that resulted in a hit. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "PublicDescription": "Counts the number of L2 Cache accesses that resulted in a hit from a front door request only (does not include rejects or recycles), Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of L2 Cache accesses that resulted in a miss. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "PublicDescription": "Counts the number of L2 Cache accesses that resulted in a miss from a front door request only (does not include rejects or recycles). Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Read requests with true-miss in L2 cache. [This event is alias to L2_RQSTS.MISS]", "Counter": "0,1,2,3", "EventCode": "0x24", @@ -412,7 +461,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81", @@ -424,7 +472,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82", @@ -436,7 +483,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83", @@ -448,7 +494,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21", @@ -460,7 +505,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41", @@ -472,7 +516,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42", @@ -484,7 +527,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11", @@ -496,7 +538,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12", @@ -518,7 +559,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4", @@ -530,7 +570,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2", @@ -542,7 +581,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4", @@ -554,7 +592,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1", @@ -566,7 +603,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8", @@ -578,7 +614,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2", @@ -590,7 +625,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PEBS": "1", "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -602,7 +636,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4", @@ -614,7 +647,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40", @@ -626,7 +658,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1", @@ -638,7 +669,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8", @@ -650,7 +680,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2", @@ -662,7 +691,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10", @@ -674,7 +702,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4", @@ -686,7 +713,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20", @@ -698,34 +724,91 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x80", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", + "SampleAfterValue": "200003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load uops retired that hit in the L1 data cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the L1 data cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "SampleAfterValue": "200003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of load uops retired that hit in the L2 cache.", "Counter": "0,1,2,3,4,5", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of load uops retired that miss in the L2 cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of load uops retired that hit in the L3 cache.", "Counter": "0,1,2,3,4,5", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the L3 cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", "Counter": "0,1,2,3,4,5", "EventCode": "0x04", @@ -776,7 +859,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts the total number of load uops retired.", "SampleAfterValue": "200003", "UMask": "0x81", @@ -788,7 +870,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts the total number of store uops retired.", "SampleAfterValue": "200003", "UMask": "0x82", @@ -802,7 +883,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -816,7 +896,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -830,7 +909,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -844,7 +922,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -858,7 +935,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -872,7 +948,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -886,7 +961,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -900,7 +974,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5", @@ -912,7 +985,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x21", "Unit": "cpu_atom" @@ -923,18 +995,46 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x41", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the total number of load and store uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the second Level TLB.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of store ops retired that miss in the second level TLB.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled.", "Counter": "0,1,2,3,4,5", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", - "PEBS": "2", "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x6", @@ -951,12 +1051,56 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F803C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0001", + "MSRValue": "0x1F803C0001", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1022,7 +1166,7 @@ "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0002", + "MSRValue": "0x1F803C0002", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1050,6 +1194,72 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F803C4000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C4000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C4000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C4000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "OFFCORE_REQUESTS.ALL_REQUESTS", "Counter": "0,1,2,3", "EventCode": "0x21", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json index b4621c221f58..62fd70f220e5 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json @@ -1,5 +1,14 @@ [ { + "BriefDescription": "Counts the number of cycles the floating point divider is in the loop stage.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { "BriefDescription": "ARITH.FPDIV_ACTIVE", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", @@ -10,6 +19,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of floating point divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts all microcode FP assists.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", @@ -187,7 +205,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_atom" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json index 66735a612ebd..c5b3818ad479 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json @@ -55,7 +55,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -68,7 +67,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -81,7 +79,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -94,7 +91,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -107,7 +103,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -120,7 +115,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -133,7 +127,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -146,7 +139,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -159,7 +151,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -172,7 +163,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -185,7 +175,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -198,7 +187,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -211,7 +199,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -224,7 +211,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -237,7 +223,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -250,7 +235,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -263,7 +247,6 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -275,7 +258,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -288,7 +270,6 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json index 81a03f53aadc..fa15f5797bed 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json @@ -133,7 +133,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1", @@ -147,7 +146,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1", @@ -161,7 +159,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1", @@ -175,7 +172,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1", @@ -189,7 +185,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -203,7 +198,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1", @@ -217,7 +211,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1", @@ -231,7 +224,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1", @@ -245,7 +237,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1", @@ -257,13 +248,23 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PEBS": "2", "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F84400004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -330,6 +331,17 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F84404000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data read requests that miss the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0x21", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json index b54a5fc0861f..855585fe6fae 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json @@ -41,6 +41,7 @@ "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Load_Store_Miss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -89,7 +90,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -99,6 +102,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_ifetch_bandwidth_group": "Metrics contributing to tma_ifetch_bandwidth category", "tma_ifetch_latency_group": "Metrics contributing to tma_ifetch_latency category", "tma_int_operations_group": "Metrics contributing to tma_int_operations category", @@ -121,10 +125,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -138,5 +145,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/alderlake/other.json b/tools/perf/pmu-events/arch/x86/alderlake/other.json index f95e093f8fcf..a8b23e92408c 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/other.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/other.json @@ -1,9 +1,10 @@ [ { - "BriefDescription": "ASSISTS.HARDWARE", + "BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. the event also counts for Machine Ordering count.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.HARDWARE", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", "SampleAfterValue": "100003", "UMask": "0x4", "Unit": "cpu_core" @@ -50,7 +51,6 @@ "Deprecated": "1", "EventCode": "0xe4", "EventName": "LBR_INSERTS.ANY", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -67,6 +67,28 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -90,6 +112,17 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", @@ -122,6 +155,39 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -144,6 +210,28 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x14000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784004000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json index b7656f77dee9..f5bf0816f190 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json @@ -11,6 +11,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", + "Counter": "0,1,2,3,4,5", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", @@ -22,6 +32,24 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of active floating point and integer dividers per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_OCCUPANCY", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point and integer divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_atom" + }, + { "BriefDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", @@ -33,6 +61,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of cycles any of the two integer dividers are active.", + "Counter": "0,1,2,3,4,5", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "This event counts the cycles the integer divider is busy.", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", @@ -43,6 +81,24 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of active integer dividers per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_OCCUPANCY", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of integer divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", @@ -68,7 +124,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", "SampleAfterValue": "200003", "Unit": "cpu_atom" @@ -78,7 +133,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009", "Unit": "cpu_core" @@ -89,7 +143,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf9", "Unit": "cpu_atom" @@ -99,7 +152,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -109,7 +161,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11", @@ -120,7 +171,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10", @@ -131,7 +181,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -141,7 +190,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1", @@ -152,7 +200,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xbf", "Unit": "cpu_atom" @@ -162,7 +209,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40", @@ -173,7 +219,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -183,7 +228,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80", @@ -194,7 +238,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -205,7 +248,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -216,7 +258,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -226,7 +267,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf9", "Unit": "cpu_atom" @@ -236,7 +276,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2", @@ -247,7 +286,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" @@ -257,7 +295,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8", @@ -268,7 +305,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xc0", "Unit": "cpu_atom" @@ -278,7 +314,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20", @@ -290,7 +325,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NON_RETURN_IND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -300,7 +334,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.REL_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfd", "Unit": "cpu_atom" @@ -311,7 +344,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" @@ -322,7 +354,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.TAKEN_JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -332,7 +363,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", "SampleAfterValue": "200003", "Unit": "cpu_atom" @@ -342,7 +372,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "400009", "Unit": "cpu_core" @@ -352,7 +381,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -362,7 +390,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11", @@ -373,7 +400,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "400009", "UMask": "0x10", @@ -384,7 +410,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -394,7 +419,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1", @@ -405,7 +429,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -415,7 +438,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80", @@ -426,7 +448,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -436,7 +457,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "400009", "UMask": "0x2", @@ -448,7 +468,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.IND_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" @@ -459,7 +478,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" @@ -469,7 +487,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x80", "Unit": "cpu_atom" @@ -479,7 +496,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "UMask": "0x20", @@ -491,7 +507,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NON_RETURN_IND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" @@ -501,7 +516,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8", @@ -512,7 +526,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" @@ -523,7 +536,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.TAKEN_JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" @@ -617,6 +629,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "This event is deprecated. Refer to new event CPU_CLK_UNHALTED.REF_TSC_P", + "Counter": "0,1,2,3,4,5", + "Deprecated": "1", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Core crystal clock cycles. Cycle counts are evenly distributed between active threads in the Core.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", @@ -854,7 +876,6 @@ "BriefDescription": "Counts the total number of instructions retired. (Fixed event)", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1", @@ -864,7 +885,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1", @@ -875,7 +895,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.", "SampleAfterValue": "2000003", "Unit": "cpu_atom" @@ -885,7 +904,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "Unit": "cpu_core" @@ -895,7 +913,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -905,7 +922,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2", @@ -915,7 +931,6 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1", @@ -926,7 +941,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PEBS": "1", "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8", @@ -1065,7 +1079,6 @@ "Deprecated": "1", "EventCode": "0x03", "EventName": "LD_BLOCKS.4K_ALIAS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_atom" @@ -1075,7 +1088,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_atom" @@ -1095,7 +1107,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -1244,7 +1255,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PEBS": "1", "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]", "SampleAfterValue": "1000003", "UMask": "0x1", @@ -1551,7 +1561,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL", - "PEBS": "1", "SampleAfterValue": "1000003", "Unit": "cpu_atom" }, @@ -1799,7 +1808,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.ALL", - "PEBS": "1", "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, @@ -1829,7 +1837,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.IDIV", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_atom" @@ -1839,7 +1846,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", - "PEBS": "1", "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "SampleAfterValue": "2000003", "UMask": "0x1", @@ -1895,7 +1901,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.X87", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_atom" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json index e0d8f3070778..132ce48af6d9 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json @@ -258,5 +258,38 @@ "SampleAfterValue": "1000003", "UMask": "0x90", "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "Deprecated": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "Deprecated": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "Deprecated": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 447596f924ab..ad04b1e3881e 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -49,13 +49,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "C8 residency percent per package", "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", "MetricGroup": "Power", @@ -63,13 +56,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -89,7 +75,7 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%" }, { @@ -98,7 +84,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "tma_backend_bound > 0.1", + "MetricThreshold": "(tma_backend_bound >0.10)", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%" @@ -109,7 +95,7 @@ "MetricExpr": "(5 * CPU_CLK_UNHALTED.CORE - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_bad_speculation >0.15)", "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" @@ -119,7 +105,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%" }, @@ -128,7 +114,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -137,7 +123,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%" }, { @@ -145,7 +131,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%" }, { @@ -153,7 +139,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", + "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -162,7 +148,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%" }, { @@ -170,7 +156,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", + "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", "ScaleUnit": "100%" }, { @@ -179,7 +165,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_frontend_bound >0.20)", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%" }, @@ -188,7 +174,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%" }, { @@ -196,7 +182,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -205,7 +191,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -321,6 +307,11 @@ "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit" }, { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2", + "MetricExpr": "100 * (MEM_BOUND_STALLS.IFETCH_LLC_HIT + MEM_BOUND_STALLS.IFETCH_DRAM_HIT) / MEM_BOUND_STALLS.IFETCH", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss" + }, + { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH", "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit" @@ -337,6 +328,12 @@ "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit" }, { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2", + "MetricExpr": "100 * (MEM_BOUND_STALLS.LOAD_LLC_HIT + MEM_BOUND_STALLS.LOAD_DRAM_HIT) / MEM_BOUND_STALLS.LOAD", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss" + }, + { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", "MetricExpr": "100 * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "load_store_bound", @@ -459,7 +456,7 @@ { "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (5 * CPU_CLK_UNHALTED.CORE)", - "MetricName": "tma_info_serialization _%_tpause_cycles" + "MetricName": "tma_info_serialization_%_tpause_cycles" }, { "BriefDescription": "Average CPU Utilization", @@ -473,6 +470,12 @@ "MetricName": "tma_info_system_kernel_utilization" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -503,7 +506,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%" }, { @@ -511,7 +514,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -520,7 +523,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%" }, { @@ -528,7 +531,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%" }, { @@ -536,7 +539,7 @@ "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", + "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", "ScaleUnit": "100%" }, { @@ -544,7 +547,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%" }, { @@ -552,7 +555,7 @@ "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%" }, { @@ -560,7 +563,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%" }, { @@ -568,7 +571,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%" }, { @@ -576,7 +579,7 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", + "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -586,7 +589,7 @@ "MetricExpr": "TOPDOWN_RETIRING.ALL / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "tma_retiring > 0.75", + "MetricThreshold": "(tma_retiring >0.75)", "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%" }, @@ -595,7 +598,7 @@ "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (5 * CPU_CLK_UNHALTED.CORE)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json index 1500033ee19f..fd9ed58c2f90 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json @@ -1,5 +1,31 @@ [ { + "BriefDescription": "Counts the total number of L2 Cache accesses. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PublicDescription": "Counts the total number of L2 Cache Accesses, includes hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only. Counts on a per core basis.", + "SampleAfterValue": "200003" + }, + { + "BriefDescription": "Counts the number of L2 Cache accesses that resulted in a hit. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "PublicDescription": "Counts the number of L2 Cache accesses that resulted in a hit from a front door request only (does not include rejects or recycles), Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of L2 Cache accesses that resulted in a miss. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "PublicDescription": "Counts the number of L2 Cache accesses that resulted in a miss from a front door request only (does not include rejects or recycles). Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", "Counter": "0,1,2,3,4,5", "EventCode": "0x2e", @@ -92,31 +118,82 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x80" }, { + "BriefDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.HITM", + "SampleAfterValue": "200003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts the number of load uops retired that hit in the L1 data cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the L1 data cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { "BriefDescription": "Counts the number of load uops retired that hit in the L2 cache.", "Counter": "0,1,2,3,4,5", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x2" }, { + "BriefDescription": "Counts the number of load uops retired that miss in the L2 cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "SampleAfterValue": "200003", + "UMask": "0x10" + }, + { "BriefDescription": "Counts the number of load uops retired that hit in the L3 cache.", "Counter": "0,1,2,3,4,5", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x4" }, { + "BriefDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the L3 cache.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", "Counter": "0,1,2,3,4,5", "EventCode": "0x04", @@ -154,7 +231,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts the total number of load uops retired.", "SampleAfterValue": "200003", "UMask": "0x81" @@ -165,7 +241,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts the total number of store uops retired.", "SampleAfterValue": "200003", "UMask": "0x82" @@ -178,7 +253,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -191,7 +265,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -204,7 +277,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -217,7 +289,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -230,7 +301,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -243,7 +313,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -256,7 +325,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -269,7 +337,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x5" @@ -280,7 +347,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x21" }, @@ -290,28 +356,93 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x41" }, { + "BriefDescription": "Counts the total number of load and store uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the second Level TLB.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11" + }, + { + "BriefDescription": "Counts the number of store ops retired that miss in the second level TLB.", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12" + }, + { "BriefDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled.", "Counter": "0,1,2,3,4,5", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", - "PEBS": "2", "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.", "SampleAfterValue": "1000003", "UMask": "0x6" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F803C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0001", + "MSRValue": "0x1F803C0001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -351,7 +482,7 @@ "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0002", + "MSRValue": "0x1F803C0002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -366,6 +497,66 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F803C4000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C4000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C4000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C4000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to instruction cache misses.", "Counter": "0,1,2,3,4,5", "EventCode": "0x71", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json index 484d8b3167f0..ed963fcb6485 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json @@ -1,5 +1,21 @@ [ { + "BriefDescription": "Counts the number of cycles the floating point divider is in the loop stage.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of floating point divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", "Counter": "0,1,2,3,4,5", "EventCode": "0xc3", @@ -13,7 +29,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x8" } diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json index 619488d42a4a..3b46b048dfb2 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json @@ -57,6 +57,16 @@ "UMask": "0x2" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F84400004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -95,5 +105,15 @@ "MSRValue": "0x3F84400002", "SampleAfterValue": "100003", "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F84404000", + "SampleAfterValue": "100003", + "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/other.json b/tools/perf/pmu-events/arch/x86/alderlaken/other.json index 54ddbe2b3b9b..f8c21b7f8f40 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/other.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/other.json @@ -5,7 +5,6 @@ "Deprecated": "1", "EventCode": "0xe4", "EventName": "LBR_INSERTS.ANY", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -20,6 +19,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -30,6 +49,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -40,6 +69,36 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800000010000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400000010000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3,4,5", "EventCode": "0xB7", @@ -50,6 +109,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x14000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xB7", + "EventName": "OCR.SWPF_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x784004000", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)", "Counter": "0,1,2,3,4,5", "EventCode": "0x75", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json index f05db45578ff..713ebc21cec0 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json @@ -1,10 +1,59 @@ [ { + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", + "Counter": "0,1,2,3,4,5", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts the number of active floating point and integer dividers per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_OCCUPANCY", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts the number of floating point and integer divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Counts the number of cycles any of the two integer dividers are active.", + "Counter": "0,1,2,3,4,5", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of active integer dividers per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_OCCUPANCY", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of integer divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", "SampleAfterValue": "200003" }, @@ -14,7 +63,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf9" }, @@ -23,7 +71,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -32,7 +79,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -41,7 +87,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xbf" }, @@ -50,7 +95,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -59,7 +103,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -69,7 +112,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -79,7 +121,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -88,7 +129,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf9" }, @@ -97,7 +137,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -106,7 +145,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xc0" }, @@ -116,7 +154,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NON_RETURN_IND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -125,7 +162,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.REL_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfd" }, @@ -135,7 +171,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -145,7 +180,6 @@ "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.TAKEN_JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -154,7 +188,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", "SampleAfterValue": "200003" }, @@ -163,7 +196,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -172,7 +204,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -181,7 +212,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -190,7 +220,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -200,7 +229,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.IND_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb" }, @@ -210,7 +238,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e" }, @@ -219,7 +246,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x80" }, @@ -229,7 +255,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NON_RETURN_IND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb" }, @@ -238,7 +263,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7" }, @@ -248,7 +272,6 @@ "Deprecated": "1", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.TAKEN_JCC", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe" }, @@ -269,6 +292,15 @@ "SampleAfterValue": "2000003" }, { + "BriefDescription": "This event is deprecated. Refer to new event CPU_CLK_UNHALTED.REF_TSC_P", + "Counter": "0,1,2,3,4,5", + "Deprecated": "1", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency. (Fixed event)", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -305,7 +337,6 @@ "BriefDescription": "Counts the total number of instructions retired. (Fixed event)", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -315,7 +346,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.", "SampleAfterValue": "2000003" }, @@ -325,7 +355,6 @@ "Deprecated": "1", "EventCode": "0x03", "EventName": "LD_BLOCKS.4K_ALIAS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -334,7 +363,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -343,7 +371,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -392,7 +419,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PEBS": "1", "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -588,7 +614,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL", - "PEBS": "1", "SampleAfterValue": "1000003" }, { @@ -604,7 +629,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.ALL", - "PEBS": "1", "SampleAfterValue": "2000003" }, { @@ -612,7 +636,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.IDIV", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -621,7 +644,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", - "PEBS": "1", "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -631,7 +653,6 @@ "Counter": "0,1,2,3,4,5", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.X87", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json index ad2b1349bab4..d9c737a17df0 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json @@ -49,5 +49,35 @@ "EventName": "LD_HEAD.DTLB_MISS_AT_RET", "SampleAfterValue": "1000003", "UMask": "0x90" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "Deprecated": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.DTLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "Deprecated": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES", + "Counter": "0,1,2,3,4,5", + "Data_LA": "1", + "Deprecated": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12" } ] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json new file mode 100644 index 000000000000..7ddb89dd1871 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json @@ -0,0 +1,2749 @@ +[ + { + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions", + "MetricExpr": "tma_core_bound", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_allocation_restriction", + "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_branch_detect", + "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_branch_resteer", + "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_cisc", + "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_decode", + "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_fast_nuke", + "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricgroupNoGroup": "TopdownL1;Default", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_ifetch_bandwidth", + "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_ifetch_latency", + "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_FLOPS_RETIRED.ALL@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipflop", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.ALL@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@FP_INST_RETIRED.128B_DP@ + cpu_atom@FP_INST_RETIRED.128B_SP@)", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_avx128", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX 256-bit instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@FP_INST_RETIRED.256B_DP@ + cpu_atom@FP_INST_RETIRED.256B_SP@)", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_avx256", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.64B_DP@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_scalar_dp", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.32B_SP@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_scalar_sp", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", + "MetricExpr": "100 * (cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ + cpu_atom@LD_HEAD.PGWALK_AT_RET@) / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Ifetch", + "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles", + "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Load_Store_Miss", + "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall", + "MetricExpr": "100 * cpu_atom@LD_HEAD.ANY_AT_RET@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Mem_Exec", + "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricName": "tma_info_br_inst_mix_ipbranch", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.NEAR_CALL@", + "MetricName": "tma_info_br_inst_mix_ipcall", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.FAR_BRANCH@u", + "MetricName": "tma_info_br_inst_mix_ipfarbranch", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)", + "MetricName": "tma_info_br_inst_mix_ipmisp_cond_ntaken", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.COND_TAKEN@", + "MetricName": "tma_info_br_inst_mix_ipmisp_cond_taken", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.INDIRECT@", + "MetricName": "tma_info_br_inst_mix_ipmisp_indirect", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired return Branch Misprediction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.RETURN@", + "MetricName": "tma_info_br_inst_mix_ipmisp_ret", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired Branch Misprediction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@", + "MetricName": "tma_info_br_inst_mix_ipmispredict", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Ratio of all branches which mispredict", + "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / cpu_atom@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricName": "tma_info_br_mispredict_bound_branch_mispredict_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Ratio between Mispredicted branches and unknown branches", + "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / cpu_atom@BACLEARS.ANY@", + "MetricName": "tma_info_br_mispredict_bound_branch_mispredict_to_unknown_branch_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", + "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.LD_BUF@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full", + "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.RSV@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full", + "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles Per Instruction", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_core_cpi", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "cpu_atom@FP_FLOPS_RETIRED.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Flops", + "MetricName": "tma_info_core_flopc", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions Per Cycle", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_core_ipc", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_core_upi", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.L2_HIT@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.L2_MISS@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3", + "MetricExpr": "100 * (cpu_atom@MEM_BOUND_STALLS_IFETCH.L2_MISS@ - cpu_atom@MEM_BOUND_STALLS_IFETCH.LLC_HIT@) / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.L2_HIT@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.L2_MISS@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3", + "MetricExpr": "100 * (cpu_atom@MEM_BOUND_STALLS_LOAD.L2_MISS@ - cpu_atom@MEM_BOUND_STALLS_LOAD.LLC_HIT@) / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block", + "MetricExpr": "100 * cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_store_bound_l1_bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement", + "MetricExpr": "100 * (cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ + cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@) / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_store_bound_load_bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full", + "MetricExpr": "100 * (cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@MEM_SCHEDULER_BLOCK.ALL@) * tma_mem_scheduler", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_store_bound_store_bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory disambiguation", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.DISAMBIGUATION@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_disamb_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to floating point assists", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.FP_ASSIST@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_fp_assist_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory ordering", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_monuke_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory renaming", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.MRN_NUKE@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_mrn_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to page faults", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.PAGE_FAULT@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_page_fault_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", + "MetricExpr": "100 * cpu_atom@LD_BLOCKS.ADDRESS_ALIAS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", + "MetricExpr": "100 * cpu_atom@LD_BLOCKS.DATA_UNKNOWN@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", + "MetricExpr": "100 * cpu_atom@LD_HEAD.L1_MISS_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc", + "MetricExpr": "100 * cpu_atom@LD_HEAD.OTHER_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk", + "MetricExpr": "100 * cpu_atom@LD_HEAD.PGWALK_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss", + "MetricExpr": "100 * cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match", + "MetricExpr": "100 * cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Load", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_mix_ipload", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Store", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@MEM_UOPS_RETIRED.ALL_STORES@", + "MetricName": "tma_info_mem_mix_ipstore", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads that perform one or more locks", + "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.LOCK_LOADS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_mix_load_locks_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads that are splits", + "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.SPLIT_LOADS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_mix_load_splits_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Ratio of mem load uops to all uops", + "MetricExpr": "1e3 * cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_mem_mix_memload_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", + "MetricExpr": "100 * cpu_atom@SERIALIZATION.C01_MS_SCB@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricName": "tma_info_serialization_%_tpause_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricName": "tma_info_system_cpu_utilization", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "cpu_atom@FP_FLOPS_RETIRED.ALL@ / (duration_time * 1e9)", + "MetricGroup": "Flops", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@k / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_kernel_utilization", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@ / cpu_atom@CPU_CLK_UNHALTED.REF_TSC@", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are FPDiv uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.FPDIV@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_fpdiv_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are IDiv uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.IDIV@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_idiv_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are microcode ops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.MS@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_microcode_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are x87 uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.X87@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_x87_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_machine_clears", + "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_mem_scheduler", + "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_non_mem_scheduler", + "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_nuke", + "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_other_fb", + "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_predecode", + "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_register", + "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_reorder_buffer", + "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation", + "MetricExpr": "tma_backend_bound - tma_core_bound", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_resource_bound", + "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that result in retirement slots", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "(tma_retiring >0.75)", + "MetricgroupNoGroup": "TopdownL1;Default", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_serialization", + "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.4", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", + "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_avx_assists", + "MetricThreshold": "tma_avx_assists > 0.1", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "(tma_bottleneck_cache_memory_latency > 20)", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "(tma_bottleneck_memory_data_tlbs > 20)", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "(tma_bottleneck_memory_synchronization > 10)", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "(tma_bottleneck_other_bottlenecks > 20)", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", + "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_c01_wait", + "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", + "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_c02_wait", + "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_nt_mispredicts", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@br_misp_retired.cond_taken_bwd_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_tk_bwd_mispredicts", + "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@br_misp_retired.cond_taken_fwd_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_tk_fwd_mispredicts", + "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_machine_clears", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_machine_clears", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricExpr": "cpu_core@MEMORY_STALLS.MEM@ / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(cpu_core@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ + cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "(tma_false_sharing > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "cpu_core@L1D_MISS.FB_FULL@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", + "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", + "MetricExpr": "30 * cpu_core@ASSISTS.FP@ / tma_info_thread_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_fp_assists", + "MetricThreshold": "tma_fp_assists > 0.1", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_call_mispredicts", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", + "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_jump_mispredicts", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 8 / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / 100", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", + "MetricExpr": "cpu_core@INT_MISC.CLEARS_COUNT@ / (cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ + cpu_core@MACHINE_CLEARS.COUNT@)", + "MetricGroup": "BrMispredicts", + "MetricName": "tma_info_bad_spec_spec_clears_ratio", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", + "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@BR_INST_RETIRED.NEAR_RETURN@) / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_NTAKEN@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_nt", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are forward taken conditionals", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN_BWD@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_tk_bwd", + "MetricThreshold": "tma_info_branches_cond_tk_bwd > 0.3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are forward taken conditionals", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN_FWD@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_tk_fwd", + "MetricThreshold": "tma_info_branches_cond_tk_fwd > 0.2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ - cpu_core@BR_INST_RETIRED.COND_TAKEN_BWD@ - cpu_core@BR_INST_RETIRED.COND_TAKEN_FWD@ - 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@) / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk_bwd + tma_info_branches_cond_tk_fwd + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches", + "Unit": "cpu_core" + }, + { + "BriefDescription": "uops Executed per Cycle", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / tma_info_thread_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_core_epc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_thread_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.V0@ + cpu_core@FP_ARITH_DISPATCHED.V1@ + cpu_core@FP_ARITH_DISPATCHED.V2@ + cpu_core@FP_ARITH_DISPATCHED.V3@) / (4 * tma_info_thread_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 8 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_frontend_dsb_switch_cost", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks", + "MetricGroup": "DSBmiss;Fed;FetchLat", + "MetricName": "tma_info_frontend_dsb_switches_ret", + "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_frontend_fetch_upc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALL_PERIODS@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / cpu_core@BACLEARS.ANY@", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * cpu_core@FRONTEND_RETIRED.L2_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.CODE_RD_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_frontend_lsd_coverage", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_frontend_ms_latency_ret", + "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_unknown_branch_cost", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat", + "MetricName": "tma_info_frontend_unknown_branches_ret", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Branch instructions per taken branch", + "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_inst_mix_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_CALL@", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@MEM_INST_RETIRED.ALL_LOADS@", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per PAUSE (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / cpu_core@CPU_CLK_UNHALTED.PAUSE_INST@", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_ippause", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@MEM_INST_RETIRED.ALL_SWPF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per taken branch", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1", + "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_fb_hpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the Level 0 within L1D cache [GB / sec]", + "MetricExpr": "64 * cpu_core@L1D.L0_REPLACEMENT@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1dl0_cache_fill_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.ALL_DEMAND_DATA_RD@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1mpki_load", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l2_cache_fill_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (cpu_core@L2_RQSTS.REFERENCES@ - cpu_core@L2_RQSTS.MISS@) / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2hpki_all", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_HIT@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2hpki_load", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L2_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Backend;CacheHits;Mem", + "MetricName": "tma_info_memory_l2mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem;Offcore", + "MetricName": "tma_info_memory_l2mpki_all", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2mpki_load", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore requests (L2 cache miss) per kilo instruction for demand RFOs", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.RFO_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheMisses;Offcore", + "MetricName": "tma_info_memory_l2mpki_rfo", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_l3_cache_access_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l3_cache_fill_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L3_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_l3mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_latency_data_l2_mlp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS.DEMAND_DATA_RD@", + "MetricGroup": "LockCont;Memory_Lat;Offcore", + "MetricName": "tma_info_memory_latency_load_l2_miss_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_latency_load_l2_mlp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD@", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_latency_load_l3_miss_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "cpu_core@L1D_PENDING.LOAD@ / cpu_core@L1D_MISS.LOAD@", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "\"Bus lock\" per kilo instruction", + "MetricExpr": "1e3 * cpu_core@SQ_MISC.BUS_LOCK@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_mix_bus_lock_pki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Un-cacheable retired load per kilo instruction", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_MISC_RETIRED.UC@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_mix_uc_load_pki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "cpu_core@L1D_PENDING.LOAD@ / cpu_core@L1D_PENDING.LOAD_CYCLES@", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "cpu_core@L2_LINES_OUT.USELESS_HWPF@ / (cpu_core@L2_LINES_OUT.SILENT@ + cpu_core@L2_LINES_OUT.NON_SILENT@)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15", + "Unit": "cpu_core" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(cpu_core@ITLB_MISSES.WALK_PENDING@ + cpu_core@DTLB_LOAD_MISSES.WALK_PENDING@ + cpu_core@DTLB_STORE_MISSES.WALK_PENDING@) / (4 * tma_info_thread_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of uops fetched from DSB per cycle", + "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@IDQ.DSB_CYCLES_ANY@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_dsb", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of uops fetched from LSD per cycle", + "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@LSD.CYCLES_ACTIVE@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_lsd", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of uops fetched from MITE per cycle", + "MetricExpr": "cpu_core@IDQ.MITE_UOPS@ / cpu_core@IDQ.MITE_CYCLES_ANY@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_mite", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per a microcode Assist invocation", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", + "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", + "MetricName": "tma_info_pipeline_ipassist", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricGroup": "MicroSeq;Pipeline;Ret", + "MetricName": "tma_info_pipeline_strings_cycles", + "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of cycles the processor is waiting yet unhalted; covering legacy PAUSE instruction, as well as C0.1 / C0.2 power-performance optimized states", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C0_WAIT@ / tma_info_thread_clks", + "MetricGroup": "C0Wait", + "MetricName": "tma_info_system_c0_wait", + "MetricThreshold": "tma_info_system_c0_wait > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_core_frequency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average CPU Utilization (percentage)", + "MetricExpr": "tma_info_system_cpus_utilized / #num_cpus_online", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of utilized CPUs", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_cpus_utilized", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@ / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_socket_clks", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / cpu_core@CPU_CLK_UNHALTED.REF_TSC@", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr", + "Unit": "cpu_core" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "slots", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops per taken branch", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_int_operations", + "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "cpu_core@INT_VEC_RETIRED.128BIT@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_128b", + "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "cpu_core@INT_VEC_RETIRED.256BIT@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_256b", + "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", + "MetricExpr": "cpu_core@MEMORY_STALLS.L1@ / tma_info_thread_clks", + "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * cpu_core@mem_load_retired.l1_hit_l1@R, cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) if 0 < cpu_core@mem_load_retired.l1_hit_l1@R else cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_l1_latency_capacity", + "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "cpu_core@MEMORY_STALLS.L2@ / tma_info_thread_clks", + "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "cpu_core@MEMORY_STALLS.L3@ / tma_info_thread_clks", + "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.LOAD@ / (3 * tma_info_thread_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", + "MetricExpr": "cpu_core@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_lsd", + "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", + "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_memory_fence", + "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "cpu_core@UOPS_RETIRED.MS@ / tma_info_thread_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * cpu_core@IDQ.MS_SWITCHES@ / tma_info_thread_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ - cpu_core@INST_RETIRED.BR_FUSED@) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@) / (tma_retiring * tma_info_thread_slots) + (cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@ + cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", + "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_other_mispredicts", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", + "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_other_nukes", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", + "MetricExpr": "99 * cpu_core@ASSISTS.PAGE_FAULT@ / tma_info_thread_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_page_faults", + "MetricThreshold": "tma_page_faults > 0.05", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", + "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ret_mispredicts", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "(cpu_core@BE_STALLS.SCOREBOARD@ + cpu_core@CPU_CLK_UNHALTED.C02@) / tma_info_thread_clks", + "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer)", + "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", + "MetricName": "tma_shuffles_256b", + "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(cpu_core@XQ.FULL@ + cpu_core@L1D_MISS.L2_STALLS@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(cpu_core@UOPS_DISPATCHED.STD@ + cpu_core@UOPS_DISPATCHED.STA@) / (7 * tma_info_thread_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "ScaleUnit": "100%", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json new file mode 100644 index 000000000000..f63594b2cca8 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json @@ -0,0 +1,1491 @@ +[ + { + "BriefDescription": "Counts the number of request that were not accepted into the L2Q because the L2Q is FULL.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x31", + "EventName": "CORE_REJECT_L2Q.ANY", + "PublicDescription": "Counts the number of (demand and L1 prefetchers) core requests rejected by the L2Q due to a full or nearly full w condition which likely indicates back pressure from L2Q. It also counts requests that would have gone directly to the XQ, but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link. The L2Q may also reject transactions from a core to insure fairness between cores, or to delay a cores dirty eviction when the address conflicts incoming external snoops. (Note that L2 prefetcher requests that are dropped are not counted by this event.)", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines replaced in L0 data cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.L0_REPLACEMENT", + "PublicDescription": "Counts L0 data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.FB_FULL", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.L2_STALLS", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of demand requests that missed L1D cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.LOAD", + "PublicDescription": "Count occurrences (rising-edge) of DCACHE_PENDING sub-event0. Impl. sends per-port binary inc-bit the occupancy increases* (at FB alloc or promotion).", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of L1D misses that are outstanding", + "Counter": "2", + "EventCode": "0x48", + "EventName": "L1D_PENDING.LOAD", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PENDING.LOAD_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x30", + "EventName": "L2_REJECT_XQ.ANY", + "PublicDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition which likely indicates back pressure from the IDI link. The XQ may reject transactions from the L2Q (non-cacheable requests), BBL (L2 misses) and WOB (L2 write-back victims).", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read access L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0xe1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ANY", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0x44", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read miss L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_REQUEST.MISS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when L1D is locked", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x42", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "PublicDescription": "This event counts the number of cycles when the L1D is locked.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x4f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x4f", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.L2_HIT", + "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or Translation Lookaside Buffer (TLB) miss which hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.L2_HIT", + "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or Translation Lookaside Buffer (TLB) miss which hit in the L2 cache.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7f", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT", + "PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT", + "PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts all retired load instructions.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.", + "SampleAfterValue": "1000003", + "UMask": "0x81", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "PublicDescription": "Counts all retired store instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x82", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired software prefetch instructions.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_SWPF", + "PublicDescription": "Counts all retired software prefetch instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x84", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All retired memory instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ANY", + "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "SampleAfterValue": "1000003", + "UMask": "0x87", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with locked access.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PublicDescription": "Counts retired load instructions with locked access.", + "SampleAfterValue": "100007", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0xa", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x11", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x12", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", + "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", + "SampleAfterValue": "20011", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.", + "SampleAfterValue": "20011", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "SampleAfterValue": "100007", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache.", + "Counter": "0,1,2,3", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1", + "SampleAfterValue": "1000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "200003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "100021", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "100021", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "SampleAfterValue": "200003", + "UMask": "0x40", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit in the L2 cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "PublicDescription": "Counts the number of load ops retired that hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L2 cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "SampleAfterValue": "200003", + "UMask": "0x80", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x1c", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", + "SampleAfterValue": "200003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ALL", + "SampleAfterValue": "20003", + "UMask": "0x7", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to load buffer full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.LD_BUF", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to a load buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.LD_BUF", + "SampleAfterValue": "20003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to RSV full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.RSV", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to an RSV full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.RSV", + "SampleAfterValue": "20003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to store buffer full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ST_BUF", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to a store buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ST_BUF", + "SampleAfterValue": "20003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.L2_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of load uops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x81", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x81", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of store uops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "SampleAfterValue": "200003", + "UMask": "0x82", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of store ops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "SampleAfterValue": "200003", + "UMask": "0x82", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "SampleAfterValue": "200003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of load uops retired that performed one or more locks", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x21", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load uops retired that performed one or more locks", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x21", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of memory uops retired that were splits.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x43", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory uops retired that were splits.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x43", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retired split load uops.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x41", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired split load uops.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x41", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retired split store uops.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "SampleAfterValue": "200003", + "UMask": "0x42", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired split store uops.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "SampleAfterValue": "200003", + "UMask": "0x42", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the second Level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of store uops retired that miss in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "SampleAfterValue": "200003", + "UMask": "0x6", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Retired memory uops for any access", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe5", + "EventName": "MEM_UOP_RETIRED.ANY", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "SampleAfterValue": "1000003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x40001E00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001E00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x40001E00002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Any memory transaction that reached the SQ.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cacheable and Non-Cacheable code read requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2c", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.ANY", + "SampleAfterValue": "100003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ICACHE", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ICACHE", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/floating-point.json b/tools/perf/pmu-events/arch/x86/arrowlake/floating-point.json new file mode 100644 index 000000000000..23a80c526aa1 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/floating-point.json @@ -0,0 +1,532 @@ +[ + { + "BriefDescription": "Cycles when floating-point divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for floating-point operations only.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cycles when any of the floating point dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts all microcode FP assists.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.FP", + "PublicDescription": "Counts all microcode Floating Point assists.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ASSISTS.SSE_AVX_MIX", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.SSE_AVX_MIX", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 1st VEC port (port 0). FP-arith-uops are of type ADD* / SUB* / MUL / FMA* / DPP.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V0", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 2nd VEC port (port 1)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V1", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 3rd VEC port (port 5)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V2", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 4th VEC port", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V3", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.4_FLOPS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "SampleAfterValue": "100003", + "UMask": "0x18", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_SINGLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.VECTOR", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "1000003", + "UMask": "0x3c", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_128B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_128B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR_128B", + "SampleAfterValue": "100003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_256B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_256B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR_256B", + "SampleAfterValue": "100003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_SINGLE", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3c", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_128B [This event is alias to FP_ARITH_INST_RETIRED.VECTOR_128B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_128B", + "SampleAfterValue": "100003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_256B [This event is alias to FP_ARITH_INST_RETIRED.VECTOR_256B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_256B", + "SampleAfterValue": "100003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to FP_FLOPS_RETIRED.FP64]", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.DP", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP32", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results [This event is alias to FP_FLOPS_RETIRED.SP]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP32", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP64", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results [This event is alias to FP_FLOPS_RETIRED.DP]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP64", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to FP_FLOPS_RETIRED.FP32]", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.SP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit double precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of floating point retired instructions.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit single precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.32B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.32B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.64B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.64B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the total number of floating point retired instructions.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x3f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 0, 1, 2, 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.PRIMARY", + "SampleAfterValue": "1000003", + "UMask": "0x1e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer store data port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.STD", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.FP_ASSIST", + "PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.", + "SampleAfterValue": "20003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.FP_ASSIST", + "PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.", + "SampleAfterValue": "20003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt)", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.FPDIV", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.FPDIV", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_lowpower" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json new file mode 100644 index 000000000000..fc5f4dd50fe6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json @@ -0,0 +1,609 @@ +[ + { + "BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Clears due to Unknown Branches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x60", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x87", + "EventName": "DECODE.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles the Microcode Sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x87", + "EventName": "DECODE.MS_BUSY", + "SampleAfterValue": "500009", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x61", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_ANT", + "MSRIndex": "0x3F7", + "MSRValue": "0x9", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to icache miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ICACHE", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x608006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x601006", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x600206", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "MSRValue": "0x610006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x602006", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x600406", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x620006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x604006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x600806", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MISP_ANT", + "MSRIndex": "0x3F7", + "MSRValue": "0x9", + "PublicDescription": "ANT retired branches that got just mispredicted", + "SampleAfterValue": "100007", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts flows delivered by the Microcode Sequencer", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MS_FLOWS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that caused clears due to being Unknown Branches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "MSRIndex": "0x3F7", + "MSRValue": "0x17", + "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ICACHE_L2_HIT", + "PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ICACHE_L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0xe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ICACHE_L3_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that hit in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that also missed the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.ACCESSES", + "SampleAfterValue": "200003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.ACCESSES", + "SampleAfterValue": "200003", + "UMask": "0x3", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are present.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALLS", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "SampleAfterValue": "500009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ICACHE_DATA.STALL_PERIODS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALL_PERIODS", + "SampleAfterValue": "500009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x83", + "EventName": "ICACHE_TAG.STALLS", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES_ANY", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of switches from DSB or MITE to the MS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CORE", + "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to IDQ_BUBBLES.STARVATION_CYCLES]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "Deprecated": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when no uops are delivered by the IDQ for 2 or more cycles when backend of the machine is not stalled - normally indicating a Fetch Latency issue", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.FETCH_LATENCY", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls for 2 or more cycles - normally indicating a Fetch Latency issue.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.STARVATION_CYCLES", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "MS_DECODED.MS_BUSY", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json new file mode 100644 index 000000000000..08f01fc66fef --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json @@ -0,0 +1,387 @@ +[ + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ANY_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xff", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ANY_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xff", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_BOUND_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xf4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_BOUND_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xf4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DL1 miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x81", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x81", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.OTHER_AT_RET", + "PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases such as pipeline conflicts, fences, etc.", + "SampleAfterValue": "1000003", + "UMask": "0xc0", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.OTHER_AT_RET", + "PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases such as pipeline conflicts, fences, etc.", + "SampleAfterValue": "1000003", + "UMask": "0xc0", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a pagewalk.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.PGWALK_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xa0", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a pagewalk.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.PGWALK_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xa0", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a store address match.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ST_ADDR_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x84", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a store address match.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ST_ADDR_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x84", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to request buffers full or lock in progress.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.WCB_FULL_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x82", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory ordering machine clears triggered due to a snoop from an external agent. Does not count internally generated machine clears such as those due to disambiguations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "20003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of machine clears due to memory ordering conflicts.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "20003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "53", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "23", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Counter": "2,3,4,5,6,7,8,9", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.", + "Counter": "0,1", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts misaligned loads that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts misaligned loads that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts misaligned stores that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts misaligned stores that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFE7F8000001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFE7F8000002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data read requests that miss the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/arrowlake/metricgroups.json new file mode 100644 index 000000000000..855585fe6fae --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/metricgroups.json @@ -0,0 +1,150 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "C0Wait": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ifetch": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Load_Store_Miss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemOffcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem_Exec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "load_store_bound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_assists_group": "Metrics contributing to tma_assists category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", + "tma_ifetch_bandwidth_group": "Metrics contributing to tma_ifetch_bandwidth category", + "tma_ifetch_latency_group": "Metrics contributing to tma_ifetch_latency category", + "tma_int_operations_group": "Metrics contributing to tma_int_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueComp": "Metrics related by the issue $issueComp", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", + "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_other_light_ops_group": "Metrics contributing to tma_other_light_ops category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_resource_bound_group": "Metrics contributing to tma_resource_bound category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" +} diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/other.json b/tools/perf/pmu-events/arch/x86/arrowlake/other.json new file mode 100644 index 000000000000..0175b2193201 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/other.json @@ -0,0 +1,279 @@ +[ + { + "BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.HARDWARE", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ASSISTS.PAGE_FAULT", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.PAGE_FAULT", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa2", + "EventName": "BE_STALLS.SCOREBOARD", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x02", + "EventName": "DEPENDENT_LOADS.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops executed on secondary integer ports 0,1,2,3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.2ND", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a load port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.LD", + "PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.PRIMARY", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a Store address port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STA", + "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STD_JMP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS]", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xe4", + "EventName": "LBR_INSERTS.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L2", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L3", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.MEM", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1E780000001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.IQ_JEU_SCB", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles the uncore cannot take further requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x2d", + "EventName": "XQ.FULL", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json new file mode 100644 index 000000000000..6dbde51e7ead --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json @@ -0,0 +1,2308 @@ +[ + { + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.DIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "SampleAfterValue": "1000003", + "UMask": "0x9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles when integer divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer operations only.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.ANY", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "SampleAfterValue": "100003", + "UMask": "0x1f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "SampleAfterValue": "200003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "All branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all branch instructions retired.", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "SampleAfterValue": "200003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts retired JCC (Jump on Conditional Code) branch instructions retired includes both taken and not taken branches", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "SampleAfterValue": "200003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "Counts conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x111", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "SampleAfterValue": "200003", + "UMask": "0x7e", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of taken JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xfe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PublicDescription": "Counts taken conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x101", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xfe", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Taken backward conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD", + "PublicDescription": "Counts taken backward conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken forward conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD", + "PublicDescription": "Counts taken forward conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x102", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and Interrupt call and return", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "SampleAfterValue": "200003", + "UMask": "0xbf", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Far branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PublicDescription": "Counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "SampleAfterValue": "200003", + "UMask": "0xbf", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "SampleAfterValue": "200003", + "UMask": "0xeb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Indirect near branch instructions retired (excluding returns)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "SampleAfterValue": "200003", + "UMask": "0xeb", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfb", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of near CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "SampleAfterValue": "200003", + "UMask": "0xf9", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "SampleAfterValue": "200003", + "UMask": "0xf9", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of near RET branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "SampleAfterValue": "200003", + "UMask": "0xf7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PublicDescription": "Counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near RET branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "SampleAfterValue": "200003", + "UMask": "0xf7", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xc0", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of near relative CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfd", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of near relative CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfd", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of near relative JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_JMP", + "SampleAfterValue": "200003", + "UMask": "0xdf", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "SampleAfterValue": "200003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "All mispredicted branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "SampleAfterValue": "200003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", + "SampleAfterValue": "400009", + "UMask": "0x44", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "SampleAfterValue": "200003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x111", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "SampleAfterValue": "200003", + "UMask": "0x7e", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_COST", + "SampleAfterValue": "400009", + "UMask": "0x151", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "SampleAfterValue": "400009", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", + "SampleAfterValue": "400009", + "UMask": "0x50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted taken JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xfe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x101", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xfe", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD", + "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST", + "SampleAfterValue": "400009", + "UMask": "0x8001", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", + "SampleAfterValue": "400009", + "UMask": "0x141", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD", + "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST", + "SampleAfterValue": "400009", + "UMask": "0x8002", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "SampleAfterValue": "200003", + "UMask": "0xeb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "SampleAfterValue": "200003", + "UMask": "0xeb", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfb", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", + "SampleAfterValue": "400009", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_COST", + "SampleAfterValue": "100003", + "UMask": "0xc0", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0x80", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", + "SampleAfterValue": "400009", + "UMask": "0x60", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RETURN", + "SampleAfterValue": "200003", + "UMask": "0xf7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RETURN", + "SampleAfterValue": "200003", + "UMask": "0xf7", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET_COST", + "SampleAfterValue": "100007", + "UMask": "0x48", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C01", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C02", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C0_WAIT", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x70", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Core cycles when the core is not in a halt state.", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.CORE", + "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "SampleAfterValue": "2000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Core clocks when a PAUSE is pending.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Pause instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles.", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "UMask": "0x3", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of unhalted reference clock cycles", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Core cycles when the thread is not in a halt state.", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "SampleAfterValue": "2000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "16", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "4", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "SampleAfterValue": "2000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "5", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "SampleAfterValue": "2000003", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "2", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instruction decoders utilized in a cycle", + "Counter": "2", + "EventCode": "0x75", + "EventName": "INST_DECODED.DECODERS", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of instructions retired.", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of instructions retired", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.BR_FUSED", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INST_RETIRED.MACRO_FUSED", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.MACRO_FUSED", + "SampleAfterValue": "2000003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired NOP instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.NOP", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Precise instruction retired with PEBS precise-distribution", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.PREC_DIST", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Iterations of Repeat string retired instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.REP_ITERATION", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Bubble cycles of BPClear.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.BPCLEAR_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0xB", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Clears speculative count", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "SampleAfterValue": "500009", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0x7", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots where uops got dropped", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.UOP_DROPPING", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.128BIT", + "SampleAfterValue": "1000003", + "UMask": "0x13", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of vector integer instructions retired of 256-bit vector-width.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.256BIT", + "SampleAfterValue": "1000003", + "UMask": "0xac", + "Unit": "cpu_core" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 128-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_128", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 256-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_256", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.MUL_256", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.MUL_256", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.SHUFFLES", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.SHUFFLES", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_128", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_128", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_256", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_256", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address exactly matches an older store whose data is not ready (a.k.a. unknown). unready_fwd", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x88", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x82", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_OK", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa8", + "EventName": "LSD.UOPS", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts all machine clears for any reason including, but not limited to memory ordering, SMC, and FP assist.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.ANY", + "SampleAfterValue": "20003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.COUNT", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of memory ordering machine clears triggered due to an internal load passing an older store within the same CPU.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.DISAMBIGUATION", + "SampleAfterValue": "20003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears due to memory ordering in which an internal load passes an older store within the same CPU.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.DISAMBIGUATION", + "SampleAfterValue": "20003", + "UMask": "0x8", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of nukes due to memory renaming", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MRN_NUKE", + "SampleAfterValue": "20003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of times that the machine clears due to a page fault. Covers both I-Side and D-Side (Loads/Stores) page faults. A page fault occurs when either the page is not present, or an access violation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.PAGE_FAULT", + "SampleAfterValue": "20003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears due to a page fault. Counts both I-Side and D-Side (Loads/Stores) page faults. A page fault occurs when either the page is not present, or an access violation occurs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.PAGE_FAULT", + "SampleAfterValue": "20003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "This event is deprecated.", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SLOW", + "SampleAfterValue": "20003", + "UMask": "0x6e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SLOW", + "SampleAfterValue": "20003", + "UMask": "0x6f", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of machine clears due to program modifying data (self modifying code) within 1K of a recently fetched code page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "SampleAfterValue": "20003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "LFENCE instructions retired", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe0", + "EventName": "MISC2_RETIRED.LFENCE", + "PublicDescription": "number of LFENCE retired instructions", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "LBR record is inserted", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe4", + "EventName": "MISC_RETIRED.LBR_INSERTS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of Last Branch Record (LBR) entries. Requires LBRs to be enabled and configured in IA32_LBR_CTL. [This event is alias to LBR_INSERTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe4", + "EventName": "MISC_RETIRED.LBR_INSERTS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.NON_C01_MS_SCB", + "PublicDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires. The most commonly executed instruction with an MS scoreboard is PAUSE.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "10000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculations.", + "Counter": "0", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BAD_SPEC_SLOTS", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "SampleAfterValue": "10000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", + "Counter": "0", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "SampleAfterValue": "10000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TOPDOWN.MEMORY_BOUND_SLOTS", + "Counter": "3", + "EventCode": "0xa4", + "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "SampleAfterValue": "10000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "Counter": "Fixed counter 3", + "EventName": "TOPDOWN.SLOTS", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", + "SampleAfterValue": "10000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa4", + "EventName": "TOPDOWN.SLOTS_P", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "10000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "SampleAfterValue": "1000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Fast Nukes such as Memory Ordering Machine clears and MRN nukes", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.FASTNUKE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Fast Nukes such as Memory Ordering Machine clears and MRN nukes", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.FASTNUKE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to a machine clear (nuke).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.NUKE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to a machine clear (nuke).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.NUKE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa4", + "EventName": "TOPDOWN_BE_BOUND.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to due to certain allocation restrictions", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to due to certain allocation restrictions", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa4", + "EventName": "TOPDOWN_BE_BOUND.ALL_P", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALL_P", + "SampleAfterValue": "1000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC and FPC RAT stalls - which can be due to the FIQ and IEC reservation station stall (integer, FP and SIMD scheduler not being able to accept another uop. )", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC and FPC RAT stalls - which can be due to the FIQ and IEC reservation station stall (integer, FP and SIMD scheduler not being able to accept another uop. )", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to mrbl stall. A 'marble' refers to a physical register file entry, also known as the physical destination (PDST).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REGISTER", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to mrbl stall. A 'marble' refers to a physical register file entry, also known as the physical destination (PDST).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REGISTER", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.SERIALIZATION", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.SERIALIZATION", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls.", + "Counter": "37", + "EventName": "TOPDOWN_FE_BOUND.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x9c", + "EventName": "TOPDOWN_FE_BOUND.ALL_P", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ALL_P", + "SampleAfterValue": "1000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTClear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.BRANCH_RESTEER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTClear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.BRANCH_RESTEER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to ms", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.CISC", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to ms", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.CISC", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to decode stall", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.DECODE", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to decode stall", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.DECODE", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH", + "SampleAfterValue": "1000003", + "UMask": "0x8d", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH", + "SampleAfterValue": "1000003", + "UMask": "0x8d", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to latency related stalls including BACLEARs, BTCLEARs, ITLB misses, and ICache misses.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY", + "SampleAfterValue": "1000003", + "UMask": "0x72", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to latency related stalls including BACLEARs, BTCLEARs, ITLB misses, and ICache misses.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY", + "SampleAfterValue": "1000003", + "UMask": "0x72", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to TOPDOWN_FE_BOUND.ITLB_MISS]", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ITLB", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to itlb miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ITLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to itlb miss [This event is alias to TOPDOWN_FE_BOUND.ITLB]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ITLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend that do not categorize into any other common frontend stall", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.OTHER", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend that do not categorize into any other common frontend stall", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.OTHER", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to predecode wrong", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.PREDECODE", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to predecode wrong", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.PREDECODE", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.", + "Counter": "38", + "EventName": "TOPDOWN_RETIRING.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of consumed retirement slots.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "TOPDOWN_RETIRING.ALL_P", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of consumed retirement slots.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x72", + "EventName": "TOPDOWN_RETIRING.ALL_P", + "SampleAfterValue": "1000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Number of non dec-by-all uops decoded by decoder", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x76", + "EventName": "UOPS_DECODED.DEC0_UOPS", + "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on INT EU ALU ports.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.ALU", + "PublicDescription": "Number of ALU integer uops dispatch to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on any INT EU ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.INT_EU_ALL", + "PublicDescription": "Number of integer uops dispatched to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched/executed by any of the 3 JEUs (all ups that hold the JEU including macro; micro jumps; fetch-from-eip)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.JMP", + "PublicDescription": "Number of jump uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on Load ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.LOAD", + "PublicDescription": "Number of Load uops dispatched to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of (shift) 1-cycle Uops dispatched/executed by any of the Shift Eus", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.SHIFT", + "PublicDescription": "Number of SHIFT integer uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched/executed by Slow EU (e.g. 3+ cycles LEA, >1 cycles shift, iDIVs, CR; *H operation)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.SLOW", + "PublicDescription": "Number of Slow integer uops dispatch to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched on STA ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.STA", + "PublicDescription": "Number of STA (Store Address) uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on STD ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.STD", + "PublicDescription": "Number of STD (Store Data) uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "3", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "Counter": "3", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "Counter": "3", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "3", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "3", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALLS", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of x87 uops dispatched.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "When 4-uops are requested and only 2-uops are delivered, the event counts 2. Uops_issued correlates to the number of ROB entries. If uop takes 2 ROB slots it counts as 2 uops_issued.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x0e", + "EventName": "UOPS_ISSUED.ANY", + "SampleAfterValue": "200003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Uops that RAT issues to RS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops issued by the front end every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x0e", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops issued by the front end every cycle. When 4-uops are requested and only 2-uops are delivered, the event counts 2. Uops_issued correlates to the number of ROB entries. If uop takes 2 ROB slots it counts as 2 uops_issued.", + "SampleAfterValue": "1000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "UOPS_ISSUED.CYCLES", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the total number of uops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.ALL", + "SampleAfterValue": "2000003", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles with retired uop(s).", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.CYCLES", + "PublicDescription": "Counts cycles where at least one uop has retired.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired uops except the last uop of each instruction.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.HEAVY", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of integer divide uops retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.IDIV", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of integer divide uops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.IDIV", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "UOPS_RETIRED.MS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Number of non-speculative switches to the Microcode Sequencer (MS)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS_SWITCHES", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "PublicDescription": "Switches to the Microcode Sequencer", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALLS", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of x87 uops retired, includes those in ms flows", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.X87", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of x87 uops retired, includes those in ms flows", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.X87", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/uncore-cache.json b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-cache.json new file mode 100644 index 000000000000..f294852dfbe6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-cache.json @@ -0,0 +1,20 @@ +[ + { + "BriefDescription": "Number of all entries allocated. Includes also retries.", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_HAC_CBO_TOR_ALLOCATION.ALL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HAC_CBO" + }, + { + "BriefDescription": "Asserted on coherent DRD + DRdPref allocations into the queue. Cacheable only", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_HAC_CBO_TOR_ALLOCATION.DRD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HAC_CBO" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-interconnect.json new file mode 100644 index 000000000000..15971f0c71db --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-interconnect.json @@ -0,0 +1,47 @@ +[ + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", + "Counter": "0,1", + "EventCode": "0x81", + "EventName": "UNC_HAC_ARB_REQ_TRK_REQUEST.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HAC_ARB" + }, + { + "BriefDescription": "Number of all CMI transactions", + "Counter": "0,1", + "EventCode": "0x8A", + "EventName": "UNC_HAC_ARB_TRANSACTIONS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HAC_ARB" + }, + { + "BriefDescription": "Number of all CMI reads", + "Counter": "0,1", + "EventCode": "0x8A", + "EventName": "UNC_HAC_ARB_TRANSACTIONS.READS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HAC_ARB" + }, + { + "BriefDescription": "Number of all CMI writes not including Mflush", + "Counter": "0,1", + "EventCode": "0x8A", + "EventName": "UNC_HAC_ARB_TRANSACTIONS.WRITES", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HAC_ARB" + }, + { + "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", + "EventCode": "0x81", + "EventName": "UNC_HAC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HAC_ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-memory.json new file mode 100644 index 000000000000..ceb8839f0767 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-memory.json @@ -0,0 +1,160 @@ +[ + { + "BriefDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels).", + "Counter": "0", + "EventCode": "0xff", + "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN", + "PerPkg": "1", + "PublicDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.", + "UMask": "0x20", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every read and write request entering the Memory Controller 0.", + "Counter": "2", + "EventCode": "0xff", + "EventName": "UNC_MC0_TOTAL_REQCOUNT_FREERUN", + "PerPkg": "1", + "PublicDescription": "Counts every read and write request entering the Memory Controller 0 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW.", + "UMask": "0x10", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels).", + "Counter": "1", + "EventCode": "0xff", + "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN", + "PerPkg": "1", + "PublicDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.", + "UMask": "0x30", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels).", + "Counter": "3", + "EventCode": "0xff", + "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN", + "PerPkg": "1", + "PublicDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.", + "UMask": "0x20", + "Unit": "imc_free_running_1" + }, + { + "BriefDescription": "Counts every read and write request entering the Memory Controller 1.", + "Counter": "5", + "EventCode": "0xff", + "EventName": "UNC_MC1_TOTAL_REQCOUNT_FREERUN", + "PerPkg": "1", + "PublicDescription": "Counts every read and write request entering the Memory Controller 1 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW.", + "UMask": "0x10", + "Unit": "imc_free_running_1" + }, + { + "BriefDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels).", + "Counter": "4", + "EventCode": "0xff", + "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN", + "PerPkg": "1", + "PublicDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.", + "UMask": "0x30", + "Unit": "imc_free_running_1" + }, + { + "BriefDescription": "ACT command for a read request sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x24", + "EventName": "UNC_M_ACT_COUNT_RD", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "ACT command sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x26", + "EventName": "UNC_M_ACT_COUNT_TOTAL", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "ACT command for a write request sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x25", + "EventName": "UNC_M_ACT_COUNT_WR", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS command sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x22", + "EventName": "UNC_M_CAS_COUNT_RD", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Write CAS command sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x23", + "EventName": "UNC_M_CAS_COUNT_WR", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Any Rank at Hot state", + "Counter": "0,1,2,3,4", + "EventCode": "0x19", + "EventName": "UNC_M_DRAM_THERMAL_HOT", + "Experimental": "1", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Any Rank at Warm state", + "Counter": "0,1,2,3,4", + "EventCode": "0x1A", + "EventName": "UNC_M_DRAM_THERMAL_WARM", + "Experimental": "1", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "PRE command sent to DRAM due to page table idle timer expiration", + "Counter": "0,1,2,3,4", + "EventCode": "0x28", + "EventName": "UNC_M_PRE_COUNT_IDLE", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "PRE command sent to DRAM for a read/write request", + "Counter": "0,1,2,3,4", + "EventCode": "0x27", + "EventName": "UNC_M_PRE_COUNT_PAGE_MISS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of bytes read from DRAM, in 32B chunks. Counter increments by 1 after receiving 32B chunk data.", + "Counter": "0,1,2,3,4", + "EventCode": "0x3A", + "EventName": "UNC_M_RD_DATA", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Total number of read and write byte transfers to/from DRAM, in 32B chunks. Counter increments by 1 after sending or receiving 32B chunk data.", + "Counter": "0,1,2,3,4", + "EventCode": "0x3C", + "EventName": "UNC_M_TOTAL_DATA", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of bytes written to DRAM, in 32B chunks. Counter increments by 1 after sending 32B chunk data.", + "Counter": "0,1,2,3,4", + "EventCode": "0x3B", + "EventName": "UNC_M_WR_DATA", + "PerPkg": "1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-other.json index 1ac5b5ef8094..b3f9c588b410 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/arrowlake/uncore-other.json @@ -5,6 +5,6 @@ "EventCode": "0xff", "EventName": "UNC_CLOCK.SOCKET", "PerPkg": "1", - "Unit": "CLOCK" + "Unit": "CNCU" } ] diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/arrowlake/virtual-memory.json new file mode 100644 index 000000000000..a3e4a4f3ab45 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/arrowlake/virtual-memory.json @@ -0,0 +1,522 @@ +[ + { + "BriefDescription": "Counts the number of page walks initiated by a demand load that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "200003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x320", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "200003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "SampleAfterValue": "200003", + "UMask": "0xe", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks initiated by a store that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x320", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all pages sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "SampleAfterValue": "2000003", + "UMask": "0xe", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x120", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0xe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0xe", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_lowpower" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DTLB miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.DTLB_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x90", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DTLB miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.DTLB_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x90", + "Unit": "cpu_lowpower" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index af620553f958..40970fa5566c 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -74,12 +74,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -92,8 +92,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", "ScaleUnit": "100%" }, { @@ -104,7 +104,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", "ScaleUnit": "100%" }, { @@ -114,7 +114,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { @@ -125,7 +125,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -133,8 +133,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -143,8 +143,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -152,7 +152,7 @@ "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -160,10 +160,10 @@ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -174,7 +174,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { @@ -183,8 +183,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -192,8 +192,8 @@ "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE", "ScaleUnit": "100%" }, { @@ -202,8 +202,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -212,7 +212,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -220,45 +220,45 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", "ScaleUnit": "100%" }, { @@ -287,7 +287,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -295,8 +295,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -304,8 +304,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -313,8 +313,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -322,8 +322,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -333,33 +333,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -370,7 +370,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -391,11 +391,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -414,7 +414,13 @@ "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -432,7 +438,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -440,7 +446,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -448,7 +454,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -456,7 +462,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -464,7 +470,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -506,7 +512,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -529,7 +535,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -541,7 +547,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -583,7 +589,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -602,7 +608,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -628,26 +634,26 @@ }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", + "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_page_walks_utilization", "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -665,14 +671,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -682,13 +688,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -698,6 +705,19 @@ "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -710,13 +730,20 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -725,14 +752,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -758,24 +786,24 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -783,8 +811,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -793,8 +821,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { @@ -803,8 +831,8 @@ "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -812,18 +840,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -840,10 +868,10 @@ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -854,15 +882,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -871,7 +899,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -883,7 +911,7 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { @@ -900,8 +928,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts", "ScaleUnit": "100%" }, { @@ -910,7 +938,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", "ScaleUnit": "100%" }, { @@ -918,8 +946,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", "ScaleUnit": "100%" }, { @@ -928,7 +956,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -937,7 +965,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -973,7 +1001,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -982,7 +1010,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1000,43 +1028,43 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1055,8 +1083,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1064,16 +1092,16 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1082,8 +1110,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1091,18 +1119,18 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1118,7 +1146,7 @@ "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1127,8 +1155,8 @@ "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json index 063ec8c2b2a1..fd3df87318c5 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json @@ -22,7 +22,7 @@ "Counter": "2", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -401,7 +401,7 @@ "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", "PEBS": "1", - "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", + "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready. Note: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -412,7 +412,7 @@ "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1", - "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache. Note: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -601,7 +601,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb2", "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", - "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.\nNote: Writeback pending FIFO has six entries.", + "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full. Note: Writeback pending FIFO has six entries.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -664,7 +664,7 @@ "Errata": "BDM76", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.\nNote: A prefetch promoted to Demand is counted from the promotion point.", + "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS. Note: A prefetch promoted to Demand is counted from the promotion point.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json index db3488abf9fc..018020a51436 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json @@ -12,7 +12,7 @@ "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs. Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -212,7 +212,7 @@ "Counter": "0,1,2,3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.", + "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread; b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json index 77fbfe99a522..bbc5d7deea6b 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc8", "EventName": "HLE_RETIRED.START", - "PublicDescription": "Number of times we entered an HLE region\n does not count nested transactions.", + "PublicDescription": "Number of times we entered an HLE region does not count nested transactions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -77,7 +77,7 @@ "Counter": "0,1,2,3", "EventCode": "0xC3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:\n1. memory disambiguation,\n2. external snoop, or\n3. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following: 1. memory disambiguation, 2. external snoop, or 3. cross SMT-HW-thread snoop (stores) hitting load buffer.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -2226,7 +2226,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "2", + "PEBS": "1", "PublicDescription": "Number of times RTM abort was triggered .", "SampleAfterValue": "2000003", "UMask": "0x4" @@ -2290,7 +2290,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Number of times we entered an RTM region\n does not count nested transactions.", + "PublicDescription": "Number of times we entered an RTM region does not count nested transactions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json b/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json index 4193c90c3459..0863375bdead 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -34,6 +35,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -51,6 +53,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -78,6 +81,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -103,6 +107,7 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json index c03f77539362..962cd07eb307 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json @@ -379,7 +379,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x3" }, @@ -579,7 +579,7 @@ "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -654,7 +654,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:\n - preceding store conflicts with the load (incomplete overlap);\n - store forwarding is impossible due to u-arch limitations;\n - preceding lock RMW operations are not forwarded;\n - store has the no-forward bit set (uncacheable/page-split/masked stores);\n - all-blocking stores are used (mostly, fences and port I/O);\nand others.\nThe most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events.\nSee the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when: - preceding store conflicts with the load (incomplete overlap); - store forwarding is impossible due to u-arch limitations; - preceding lock RMW operations are not forwarded; - store has the no-forward bit set (uncacheable/page-split/masked stores); - all-blocking stores are used (mostly, fences and port I/O); and others. The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -822,7 +822,7 @@ "Counter": "0,1,2,3", "EventCode": "0x5E", "EventName": "RS_EVENTS.EMPTY_CYCLES", - "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread.\nNote: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread. Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1177,7 +1177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x0E", "EventName": "UOPS_ISSUED.FLAGS_MERGE", - "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive\n added by GSR u-arch.", + "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive added by GSR u-arch.", "SampleAfterValue": "2000003", "UMask": "0x10" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index 2e1380248684..b03a5f2bcd82 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -74,7 +74,7 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_4k_aliasing > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, @@ -84,7 +84,7 @@ "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", - "MetricThreshold": "tma_alu_op_utilization > 0.4", + "MetricThreshold": "(tma_alu_op_utilization > 0.4)", "ScaleUnit": "100%" }, { @@ -92,7 +92,7 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "(tma_assists > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -102,7 +102,7 @@ "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "tma_backend_bound > 0.2", + "MetricThreshold": "(tma_backend_bound > 0.2)", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" @@ -112,7 +112,7 @@ "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_bad_speculation > 0.15)", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" @@ -123,7 +123,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_branch_mispredicts > 0.1) & ((tma_bad_speculation > 0.15))", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" @@ -133,7 +133,7 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "(tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, @@ -143,7 +143,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "(tma_cisc > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, @@ -152,7 +152,7 @@ "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "(tma_clears_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -160,9 +160,9 @@ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_contested_accesses > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -172,7 +172,7 @@ "MetricExpr": "tma_backend_bound - tma_memory_bound", "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricThreshold": "(tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" @@ -183,7 +183,7 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_data_sharing > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, @@ -192,8 +192,8 @@ "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "MetricThreshold": "(tma_divider > 0.2) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%" }, { @@ -202,8 +202,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "(tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -211,7 +211,7 @@ "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "(tma_dsb > 0.15) & ((tma_fetch_bandwidth > 0.2))", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, @@ -220,7 +220,7 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "(tma_dsb_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -229,7 +229,7 @@ "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_dtlb_load > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, @@ -238,7 +238,7 @@ "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_dtlb_store > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, @@ -246,9 +246,9 @@ "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", - "MetricThreshold": "tma_fb_full > 0.3", + "MetricThreshold": "(tma_fb_full > 0.3)", "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, @@ -257,9 +257,9 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.2", + "MetricThreshold": "(tma_fetch_bandwidth > 0.2)", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -267,7 +267,7 @@ "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", - "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricThreshold": "(tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" @@ -277,7 +277,7 @@ "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", - "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "MetricThreshold": "(tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))", "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, @@ -286,7 +286,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "(tma_fp_scalar > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -295,7 +295,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "(tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -304,8 +304,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "(tma_fp_vector_128b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -313,8 +313,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "(tma_fp_vector_256b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -322,7 +322,7 @@ "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricThreshold": "(tma_frontend_bound > 0.15)", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" @@ -332,9 +332,9 @@ "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", - "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricThreshold": "(tma_heavy_operations > 0.1)", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, { @@ -342,23 +342,23 @@ "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "(tma_icache_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "(tma_info_bad_spec_ipmisp_indirect < 1000)" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BadSpec;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmispredict", - "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + "MetricThreshold": "(tma_info_bad_spec_ipmispredict < 200)" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", @@ -396,7 +396,7 @@ "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_frontend_dsb_coverage", - "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "MetricThreshold": "(tma_info_frontend_dsb_coverage < 0.7) & ((tma_info_thread_ipc / 4) > 0.35)", "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { @@ -406,6 +406,12 @@ "MetricName": "tma_info_frontend_ipunknown_branch" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { "BriefDescription": "Branch instructions per taken branch.", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", @@ -423,7 +429,7 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", - "MetricThreshold": "tma_info_inst_mix_iparith < 10", + "MetricThreshold": "(tma_info_inst_mix_iparith < 10)", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." }, { @@ -431,7 +437,7 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", - "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", + "MetricThreshold": "(tma_info_inst_mix_iparith_avx128 < 10)", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -439,7 +445,7 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", - "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", + "MetricThreshold": "(tma_info_inst_mix_iparith_avx256 < 10)", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -447,7 +453,7 @@ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", - "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", + "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_dp < 10)", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -455,7 +461,7 @@ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", - "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", + "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_sp < 10)", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." }, { @@ -463,42 +469,42 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", "MetricName": "tma_info_inst_mix_ipbranch", - "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" + "MetricThreshold": "(tma_info_inst_mix_ipbranch < 8)" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_ipcall", - "MetricThreshold": "tma_info_inst_mix_ipcall < 200" + "MetricThreshold": "(tma_info_inst_mix_ipcall < 200)" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_ipflop", - "MetricThreshold": "tma_info_inst_mix_ipflop < 10" + "MetricThreshold": "(tma_info_inst_mix_ipflop < 10)" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", "MetricName": "tma_info_inst_mix_ipload", - "MetricThreshold": "tma_info_inst_mix_ipload < 3" + "MetricThreshold": "(tma_info_inst_mix_ipload < 3)" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", "MetricName": "tma_info_inst_mix_ipstore", - "MetricThreshold": "tma_info_inst_mix_ipstore < 8" + "MetricThreshold": "(tma_info_inst_mix_ipstore < 8)" }, { "BriefDescription": "Instructions per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "(tma_info_inst_mix_iptb < 4 * 2 + 1)", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -521,7 +527,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -533,7 +539,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -575,7 +581,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -594,7 +600,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -623,10 +629,10 @@ "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", "MetricName": "tma_info_memory_tlb_page_walks_utilization", - "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + "MetricThreshold": "(tma_info_memory_tlb_page_walks_utilization > 0.5)" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", + "BriefDescription": "", "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" @@ -639,7 +645,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -657,14 +663,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -674,7 +680,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "(tma_info_system_ipfarbranch < 1000000)" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", @@ -687,7 +693,20 @@ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", - "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + "MetricThreshold": "(tma_info_system_kernel_utilization > 0.05)" + }, + { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -702,6 +721,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "(tma_info_system_time < 1)" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -743,31 +769,31 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", "MetricName": "tma_info_thread_uoppi", - "MetricThreshold": "tma_info_thread_uoppi > 1.05" + "MetricThreshold": "(tma_info_thread_uoppi > 1.05)" }, { "BriefDescription": "Uops per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "(tma_info_thread_uptb < 4 * 1.5)" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "(tma_itlb_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "(tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -775,8 +801,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "(tma_l2_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -785,7 +811,7 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "MetricThreshold": "(tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, @@ -795,7 +821,7 @@ "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_l3_hit_latency > 0.1) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, @@ -804,7 +830,7 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "(tma_lcp > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, @@ -813,7 +839,7 @@ "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", - "MetricThreshold": "tma_light_operations > 0.6", + "MetricThreshold": "(tma_light_operations > 0.6)", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" @@ -824,7 +850,7 @@ "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", - "MetricThreshold": "tma_load_op_utilization > 0.6", + "MetricThreshold": "(tma_load_op_utilization > 0.6)", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10", "ScaleUnit": "100%" }, @@ -832,9 +858,9 @@ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_lock_latency > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -844,7 +870,7 @@ "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", - "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_machine_clears > 0.1) & ((tma_bad_speculation > 0.15))", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" @@ -852,9 +878,9 @@ { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_mem_bandwidth > 0.2) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -863,7 +889,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_mem_latency > 0.1) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -873,7 +899,7 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", - "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricThreshold": "(tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))", "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" @@ -883,7 +909,7 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", - "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "MetricThreshold": "(tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1))", "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, @@ -892,7 +918,7 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "(tma_mispredicts_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, @@ -901,7 +927,7 @@ "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "MetricThreshold": "(tma_mite > 0.1) & ((tma_fetch_bandwidth > 0.2))", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, @@ -910,7 +936,7 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "(tma_ms_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))", "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, @@ -919,8 +945,8 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", - "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "(tma_port_0 > 0.6)", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -928,8 +954,8 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", - "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "(tma_port_1 > 0.6)", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -937,7 +963,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", - "MetricThreshold": "tma_port_2 > 0.6", + "MetricThreshold": "(tma_port_2 > 0.6)", "ScaleUnit": "100%" }, { @@ -945,7 +971,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", - "MetricThreshold": "tma_port_3 > 0.6", + "MetricThreshold": "(tma_port_3 > 0.6)", "ScaleUnit": "100%" }, { @@ -953,7 +979,7 @@ "MetricExpr": "tma_store_op_utilization", "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", "MetricName": "tma_port_4", - "MetricThreshold": "tma_port_4 > 0.6", + "MetricThreshold": "(tma_port_4 > 0.6)", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Related metrics: tma_split_stores", "ScaleUnit": "100%" }, @@ -962,7 +988,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", - "MetricThreshold": "tma_port_5 > 0.6", + "MetricThreshold": "(tma_port_5 > 0.6)", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -971,8 +997,8 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", - "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "MetricThreshold": "(tma_port_6 > 0.6)", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -980,7 +1006,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", - "MetricThreshold": "tma_port_7 > 0.6", + "MetricThreshold": "(tma_port_7 > 0.6)", "ScaleUnit": "100%" }, { @@ -989,7 +1015,7 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "(tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, @@ -998,7 +1024,7 @@ "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_ports_utilized_0 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, @@ -1007,7 +1033,7 @@ "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_ports_utilized_1 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1016,7 +1042,7 @@ "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_ports_utilized_2 > 0.15) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1025,7 +1051,7 @@ "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_ports_utilized_3m > 0.4) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, @@ -1034,7 +1060,7 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricThreshold": "((tma_retiring > 0.7)|(tma_heavy_operations > 0.1))", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" @@ -1045,7 +1071,7 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_split_loads > 0.3)", "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, @@ -1054,16 +1080,16 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_split_stores > 0.2) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_sq_full > 0.3) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1072,7 +1098,7 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "MetricThreshold": "(tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))", "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, @@ -1081,7 +1107,7 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_store_fwd_blk > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, @@ -1089,9 +1115,9 @@ "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "(tma_store_latency > 0.1) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))", "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, @@ -1100,7 +1126,7 @@ "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", - "MetricThreshold": "tma_store_op_utilization > 0.6", + "MetricThreshold": "(tma_store_op_utilization > 0.6)", "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", "ScaleUnit": "100%" }, @@ -1109,7 +1135,7 @@ "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "(tma_unknown_branches > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, @@ -1118,7 +1144,7 @@ "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "(tma_x87_use > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))", "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json index 315d7f041731..49d8de8f1b51 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json @@ -22,7 +22,7 @@ "Counter": "2", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -434,7 +434,7 @@ "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", "PEBS": "1", - "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", + "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready. Note: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -445,7 +445,7 @@ "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1", - "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache. Note: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -634,7 +634,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb2", "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", - "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.\nNote: Writeback pending FIFO has six entries.", + "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full. Note: Writeback pending FIFO has six entries.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -697,7 +697,7 @@ "Errata": "BDM76", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.\nNote: A prefetch promoted to Demand is counted from the promotion point.", + "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS. Note: A prefetch promoted to Demand is counted from the promotion point.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json b/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json index db3488abf9fc..018020a51436 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json @@ -12,7 +12,7 @@ "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs. Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -212,7 +212,7 @@ "Counter": "0,1,2,3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.", + "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread; b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/memory.json index 31a74eed2f7d..9fca9a4eeb48 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/memory.json @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc8", "EventName": "HLE_RETIRED.START", - "PublicDescription": "Number of times we entered an HLE region\n does not count nested transactions.", + "PublicDescription": "Number of times we entered an HLE region does not count nested transactions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -77,7 +77,7 @@ "Counter": "0,1,2,3", "EventCode": "0xC3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:\n1. memory disambiguation,\n2. external snoop, or\n3. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following: 1. memory disambiguation, 2. external snoop, or 3. cross SMT-HW-thread snoop (stores) hitting load buffer.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -280,7 +280,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Number of times we entered an RTM region\n does not count nested transactions.", + "PublicDescription": "Number of times we entered an RTM region does not count nested transactions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/metricgroups.json b/tools/perf/pmu-events/arch/x86/broadwellde/metricgroups.json index 4193c90c3459..0863375bdead 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -34,6 +35,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -51,6 +53,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -78,6 +81,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -103,6 +107,7 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json index c03f77539362..962cd07eb307 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json @@ -379,7 +379,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x3" }, @@ -579,7 +579,7 @@ "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -654,7 +654,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:\n - preceding store conflicts with the load (incomplete overlap);\n - store forwarding is impossible due to u-arch limitations;\n - preceding lock RMW operations are not forwarded;\n - store has the no-forward bit set (uncacheable/page-split/masked stores);\n - all-blocking stores are used (mostly, fences and port I/O);\nand others.\nThe most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events.\nSee the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when: - preceding store conflicts with the load (incomplete overlap); - store forwarding is impossible due to u-arch limitations; - preceding lock RMW operations are not forwarded; - store has the no-forward bit set (uncacheable/page-split/masked stores); - all-blocking stores are used (mostly, fences and port I/O); and others. The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -822,7 +822,7 @@ "Counter": "0,1,2,3", "EventCode": "0x5E", "EventName": "RS_EVENTS.EMPTY_CYCLES", - "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread.\nNote: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread. Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1177,7 +1177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x0E", "EventName": "UOPS_ISSUED.FLAGS_MERGE", - "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive\n added by GSR u-arch.", + "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive added by GSR u-arch.", "SampleAfterValue": "2000003", "UMask": "0x10" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json index f5b5ae1150c3..bfc499fdfdeb 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json @@ -608,7 +608,7 @@ "EventCode": "0x12", "EventName": "UNC_C_RxR_EXT_STARVED.IPQ", "PerPkg": "1", - "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", + "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally starved and therefore we are blocking the IRQ.", "UMask": "0x2", "Unit": "CBOX" }, @@ -1654,7 +1654,7 @@ "EventCode": "0x14", "EventName": "UNC_H_BYPASS_IMC.NOT_TAKEN", "PerPkg": "1", - "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.", "UMask": "0x2", "Unit": "HA" }, @@ -1664,7 +1664,7 @@ "EventCode": "0x14", "EventName": "UNC_H_BYPASS_IMC.TAKEN", "PerPkg": "1", - "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.", "UMask": "0x1", "Unit": "HA" }, @@ -2679,7 +2679,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN0", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", "UMask": "0x1", "Unit": "HA" }, @@ -2689,7 +2689,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN1", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", "UMask": "0x2", "Unit": "HA" }, @@ -2699,7 +2699,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN2", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", "UMask": "0x4", "Unit": "HA" }, @@ -2709,7 +2709,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN3", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", "UMask": "0x8", "Unit": "HA" }, @@ -3239,7 +3239,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.", "UMask": "0x3", "Unit": "HA" }, @@ -3249,7 +3249,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.", "UMask": "0x1", "Unit": "HA" }, @@ -3259,7 +3259,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.", "UMask": "0x2", "Unit": "HA" }, @@ -3679,7 +3679,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN0", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", "UMask": "0x1", "Unit": "HA" }, @@ -3689,7 +3689,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN1", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", "UMask": "0x2", "Unit": "HA" }, @@ -3699,7 +3699,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN2", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", "UMask": "0x4", "Unit": "HA" }, @@ -3709,7 +3709,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN3", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", "UMask": "0x8", "Unit": "HA" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json index 58031f397168..5ccc49cb66a6 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json @@ -33,7 +33,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x80", "Unit": "IRP" }, @@ -43,7 +43,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x2", "Unit": "IRP" }, @@ -53,7 +53,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.DRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x4", "Unit": "IRP" }, @@ -63,7 +63,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x20", "Unit": "IRP" }, @@ -73,7 +73,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x1", "Unit": "IRP" }, @@ -83,7 +83,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCITOM", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x10", "Unit": "IRP" }, @@ -93,7 +93,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.RFO", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x8", "Unit": "IRP" }, @@ -103,7 +103,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x40", "Unit": "IRP" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 0577d7460082..8016202bad1f 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -55,7 +55,7 @@ "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -76,24 +76,24 @@ "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ + cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x180\\,filter_tid\\=0x3e@) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" @@ -102,14 +102,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -209,13 +209,13 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -276,12 +276,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -294,8 +294,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", "ScaleUnit": "100%" }, { @@ -306,7 +306,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", "ScaleUnit": "100%" }, { @@ -316,7 +316,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { @@ -327,7 +327,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -335,8 +335,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -345,8 +345,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -354,7 +354,7 @@ "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, @@ -362,10 +362,10 @@ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -376,7 +376,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { @@ -385,8 +385,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -394,8 +394,8 @@ "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE", "ScaleUnit": "100%" }, { @@ -404,8 +404,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -414,7 +414,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -422,45 +422,45 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", "ScaleUnit": "100%" }, { @@ -489,7 +489,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -497,8 +497,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -506,8 +506,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -515,8 +515,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -524,8 +524,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -535,33 +535,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -572,7 +572,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -593,11 +593,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -616,7 +616,13 @@ "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -634,7 +640,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -642,7 +648,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -650,7 +656,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -658,7 +664,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -666,7 +672,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -708,7 +714,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -731,7 +737,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -743,7 +749,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -785,7 +791,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -804,7 +810,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -837,19 +843,19 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -867,14 +873,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -884,13 +890,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -901,19 +908,32 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -926,6 +946,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -933,12 +960,12 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -947,14 +974,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -980,24 +1008,24 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -1005,8 +1033,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1015,8 +1043,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { @@ -1025,8 +1053,8 @@ "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1034,18 +1062,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1063,18 +1091,18 @@ "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -1090,10 +1118,10 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -1102,7 +1130,7 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, @@ -1114,7 +1142,7 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { @@ -1131,8 +1159,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts", "ScaleUnit": "100%" }, { @@ -1141,7 +1169,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", "ScaleUnit": "100%" }, { @@ -1149,8 +1177,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", "ScaleUnit": "100%" }, { @@ -1159,7 +1187,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1168,7 +1196,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1204,7 +1232,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1213,7 +1241,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1231,43 +1259,43 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1276,8 +1304,8 @@ "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -1285,8 +1313,8 @@ "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM", "ScaleUnit": "100%" }, { @@ -1305,8 +1333,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1314,16 +1342,16 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1332,8 +1360,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1341,18 +1369,18 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1368,7 +1396,7 @@ "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1377,8 +1405,8 @@ "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json index beeda41b428a..59bc8c71487e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json @@ -22,7 +22,7 @@ "Counter": "2", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -434,7 +434,7 @@ "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", "PEBS": "1", - "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", + "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready. Note: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", "SampleAfterValue": "100003", "UMask": "0x40" }, @@ -445,7 +445,7 @@ "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1", - "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache. Note: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -634,7 +634,7 @@ "Counter": "0,1,2,3", "EventCode": "0xb2", "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", - "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.\nNote: Writeback pending FIFO has six entries.", + "PublicDescription": "This event counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full. Note: Writeback pending FIFO has six entries.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -697,7 +697,7 @@ "Errata": "BDM76", "EventCode": "0x60", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.\nNote: A prefetch promoted to Demand is counted from the promotion point.", + "PublicDescription": "This event counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS. Note: A prefetch promoted to Demand is counted from the promotion point.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json index db3488abf9fc..018020a51436 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json @@ -12,7 +12,7 @@ "Counter": "0,1,2,3", "EventCode": "0xAB", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs. Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -212,7 +212,7 @@ "Counter": "0,1,2,3", "EventCode": "0x9C", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.", + "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread; b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json index 86246f632d79..093c8b564fc0 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json @@ -68,7 +68,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc8", "EventName": "HLE_RETIRED.START", - "PublicDescription": "Number of times we entered an HLE region\n does not count nested transactions.", + "PublicDescription": "Number of times we entered an HLE region does not count nested transactions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -77,7 +77,7 @@ "Counter": "0,1,2,3", "EventCode": "0xC3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:\n1. memory disambiguation,\n2. external snoop, or\n3. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following: 1. memory disambiguation, 2. external snoop, or 3. cross SMT-HW-thread snoop (stores) hitting load buffer.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -470,7 +470,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc9", "EventName": "RTM_RETIRED.START", - "PublicDescription": "Number of times we entered an RTM region\n does not count nested transactions.", + "PublicDescription": "Number of times we entered an RTM region does not count nested transactions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json b/tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json index 4193c90c3459..0863375bdead 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -34,6 +35,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -51,6 +53,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -78,6 +81,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -103,6 +107,7 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json index c03f77539362..962cd07eb307 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json @@ -379,7 +379,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", - "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x3" }, @@ -579,7 +579,7 @@ "BriefDescription": "Instructions retired from execution.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -654,7 +654,7 @@ "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:\n - preceding store conflicts with the load (incomplete overlap);\n - store forwarding is impossible due to u-arch limitations;\n - preceding lock RMW operations are not forwarded;\n - store has the no-forward bit set (uncacheable/page-split/masked stores);\n - all-blocking stores are used (mostly, fences and port I/O);\nand others.\nThe most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events.\nSee the table of not supported store forwards in the Optimization Guide.", + "PublicDescription": "This event counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when: - preceding store conflicts with the load (incomplete overlap); - store forwarding is impossible due to u-arch limitations; - preceding lock RMW operations are not forwarded; - store has the no-forward bit set (uncacheable/page-split/masked stores); - all-blocking stores are used (mostly, fences and port I/O); and others. The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -822,7 +822,7 @@ "Counter": "0,1,2,3", "EventCode": "0x5E", "EventName": "RS_EVENTS.EMPTY_CYCLES", - "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread.\nNote: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "PublicDescription": "This event counts cycles during which the reservation station (RS) is empty for the thread. Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -1177,7 +1177,7 @@ "Counter": "0,1,2,3", "EventCode": "0x0E", "EventName": "UOPS_ISSUED.FLAGS_MERGE", - "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive\n added by GSR u-arch.", + "PublicDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive added by GSR u-arch.", "SampleAfterValue": "2000003", "UMask": "0x10" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json index b55b305aecaa..8f6955615bfd 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json @@ -802,7 +802,7 @@ "EventCode": "0x12", "EventName": "UNC_C_RxR_EXT_STARVED.IPQ", "PerPkg": "1", - "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", + "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally starved and therefore we are blocking the IRQ.", "UMask": "0x2", "Unit": "CBOX" }, @@ -1859,7 +1859,7 @@ "EventCode": "0x14", "EventName": "UNC_H_BYPASS_IMC.NOT_TAKEN", "PerPkg": "1", - "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.", "UMask": "0x2", "Unit": "HA" }, @@ -1869,7 +1869,7 @@ "EventCode": "0x14", "EventName": "UNC_H_BYPASS_IMC.TAKEN", "PerPkg": "1", - "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.", "UMask": "0x1", "Unit": "HA" }, @@ -2884,7 +2884,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN0", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", "UMask": "0x1", "Unit": "HA" }, @@ -2894,7 +2894,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN1", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", "UMask": "0x2", "Unit": "HA" }, @@ -2904,7 +2904,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN2", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", "UMask": "0x4", "Unit": "HA" }, @@ -2914,7 +2914,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN3", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", "UMask": "0x8", "Unit": "HA" }, @@ -3448,7 +3448,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.", "UMask": "0x3", "Unit": "HA" }, @@ -3458,7 +3458,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.", "UMask": "0x1", "Unit": "HA" }, @@ -3468,7 +3468,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.", "UMask": "0x2", "Unit": "HA" }, @@ -3888,7 +3888,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN0", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", "UMask": "0x1", "Unit": "HA" }, @@ -3898,7 +3898,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN1", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", "UMask": "0x2", "Unit": "HA" }, @@ -3908,7 +3908,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN2", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", "UMask": "0x4", "Unit": "HA" }, @@ -3918,7 +3918,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN3", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", "UMask": "0x8", "Unit": "HA" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json index 765d44012bba..56d729c8e946 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -1,25 +1,5 @@ [ { - "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", - "Counter": "0,1,2,3", - "EventName": "QPI_CTL_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", - "ScaleUnit": "8Bytes", - "UMask": "0x4", - "Unit": "QPI" - }, - { - "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", - "Counter": "0,1,2,3", - "EventName": "QPI_DATA_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", - "ScaleUnit": "8Bytes", - "UMask": "0x2", - "Unit": "QPI" - }, - { "BriefDescription": "Total Write Cache Occupancy; Any Source", "Counter": "0,1", "EventCode": "0x12", @@ -53,7 +33,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x80", "Unit": "IRP" }, @@ -63,7 +43,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x2", "Unit": "IRP" }, @@ -73,7 +53,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.DRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x4", "Unit": "IRP" }, @@ -83,7 +63,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x20", "Unit": "IRP" }, @@ -93,7 +73,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x1", "Unit": "IRP" }, @@ -103,7 +83,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCITOM", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x10", "Unit": "IRP" }, @@ -113,7 +93,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.RFO", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x8", "Unit": "IRP" }, @@ -123,7 +103,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x40", "Unit": "IRP" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json index 45555316f8ea..ca09c1286485 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json @@ -184,6 +184,7 @@ { "BriefDescription": "This event is deprecated. Refer to new event UNC_M_CLOCKTICKS_P", "Counter": "0,1,2,3", + "Deprecated": "1", "EventName": "UNC_M_DCLOCKTICKS", "PerPkg": "1", "Unit": "iMC" diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index b02a89e14c5d..5729b93a9c68 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -55,7 +55,7 @@ "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -76,31 +76,31 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "dtlb_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3) * 4 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" @@ -109,14 +109,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -192,25 +192,25 @@ "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_write", "ScaleUnit": "1MB/s" @@ -240,13 +240,13 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -313,12 +313,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -330,7 +330,7 @@ "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -341,7 +341,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", "ScaleUnit": "100%" }, { @@ -351,10 +351,103 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", @@ -362,7 +455,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -370,8 +463,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -379,8 +472,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -388,18 +481,50 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -410,25 +535,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -437,18 +562,18 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound)", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -457,7 +582,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -465,47 +590,47 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(110 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", "ScaleUnit": "100%" }, { @@ -515,7 +640,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -525,17 +650,17 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -545,7 +670,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -554,7 +679,7 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", "ScaleUnit": "100%" }, { @@ -562,17 +687,17 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -581,8 +706,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -590,8 +715,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -599,7 +724,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -610,50 +735,50 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 4 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -663,7 +788,7 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" @@ -678,8 +803,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" @@ -687,7 +812,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -695,108 +820,10 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -825,7 +852,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -850,14 +877,14 @@ }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -870,20 +897,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -913,7 +940,13 @@ "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -928,11 +961,11 @@ { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -940,7 +973,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -948,7 +981,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -956,7 +989,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -964,7 +997,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -972,7 +1005,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1018,7 +1051,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -1028,7 +1061,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1075,7 +1108,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -1093,7 +1126,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -1135,13 +1168,13 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -1160,7 +1193,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -1216,7 +1249,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1237,18 +1270,18 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1266,29 +1299,29 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_read_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_write_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU" @@ -1298,13 +1331,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1322,43 +1356,37 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", - "MetricExpr": "(1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@ if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", - "MetricName": "tma_info_system_mem_pmm_read_latency", - "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" - }, - { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_read_bw" + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_write_bw" + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1366,7 +1394,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1374,7 +1402,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1389,6 +1417,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -1396,12 +1431,12 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1410,14 +1445,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1443,43 +1479,52 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1487,17 +1532,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1505,18 +1550,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1534,7 +1579,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1542,24 +1587,48 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1571,16 +1640,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1588,8 +1657,8 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1600,11 +1669,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1618,7 +1687,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1626,8 +1695,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1640,12 +1709,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1653,8 +1722,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1663,7 +1732,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", "ScaleUnit": "100%" }, { @@ -1671,7 +1740,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1685,29 +1754,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", - "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_pmm_bound", - "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1761,7 +1820,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1770,7 +1829,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1787,8 +1846,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { @@ -1796,8 +1855,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1805,7 +1864,7 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1814,35 +1873,35 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", "ScaleUnit": "100%" }, { @@ -1860,7 +1919,7 @@ "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1869,8 +1928,8 @@ "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: ROB_MISC_EVENTS.PAUSE_INST", "ScaleUnit": "100%" }, { @@ -1879,8 +1938,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1888,17 +1947,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1906,8 +1965,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1915,18 +1974,18 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1942,7 +2001,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1950,7 +2009,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1958,7 +2041,7 @@ "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1967,8 +2050,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json b/tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json index cccfcab3425e..a579603f720b 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json @@ -38,6 +38,7 @@ "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -84,7 +85,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -113,10 +116,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -129,5 +135,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json index 6347eba48810..c9596e18ec09 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json @@ -4577,7 +4577,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4588,7 +4588,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4599,7 +4599,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -4609,7 +4609,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -4619,7 +4619,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4630,7 +4630,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4651,7 +4651,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4662,7 +4662,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4673,7 +4673,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -4683,7 +4683,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -4693,7 +4693,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4704,7 +4704,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4747,7 +4747,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", "Experimental": "1", - "Filter": "config1=0x4903300000000", + "Filter": "config1=0x49033", "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM request is used by IIO to request a data write without first reading the data for ownership.", "UMask": "0x24", @@ -4759,7 +4759,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RDCUR", "Experimental": "1", - "Filter": "config1=0x43c3300000000", + "Filter": "config1=0x43C33", "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RdCur requests and miss the LLC. A RdCur request is used by IIO to read data without changing state.", "UMask": "0x24", @@ -4771,7 +4771,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", "Experimental": "1", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests a cache line to be cached in E state with the intent to modify.", "UMask": "0x24", @@ -4999,7 +4999,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -5010,7 +5010,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -5021,7 +5021,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -5031,7 +5031,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -5041,7 +5041,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -5052,7 +5052,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -5073,7 +5073,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -5084,7 +5084,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -5095,7 +5095,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -5105,7 +5105,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -5115,7 +5115,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -5126,7 +5126,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -5171,7 +5171,7 @@ "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", "Experimental": "1", - "Filter": "config1=0x4903300000000", + "Filter": "config1=0x49033", "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM is used by IIO to request a data write without first reading the data for ownership.", "UMask": "0x24", @@ -5183,7 +5183,7 @@ "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RDCUR", "Experimental": "1", - "Filter": "config1=0x43c3300000000", + "Filter": "config1=0x43C33", "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RdCur requests that miss the LLC. A RdCur request is used by IIO to read data without changing state.", "UMask": "0x24", @@ -5195,7 +5195,7 @@ "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", "Experimental": "1", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests data to be cached in E state with the intent to modify.", "UMask": "0x24", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json index 91889e447bd1..4efbfeb338a6 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json @@ -13855,16 +13855,5 @@ "PerPkg": "1", "PublicDescription": "Number outstanding register requests within message channel tracker", "Unit": "UBOX" - }, - { - "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", - "Counter": "0,1,2,3", - "EventCode": "0x2", - "EventName": "UPI_DATA_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", - "ScaleUnit": "7.11E-06Bytes", - "UMask": "0xf", - "Unit": "UPI" } ] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json new file mode 100644 index 000000000000..875361b30f1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json @@ -0,0 +1,144 @@ +[ + { + "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x41" + }, + { + "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Counts the number of load ops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "SampleAfterValue": "1000003", + "UMask": "0x81" + }, + { + "BriefDescription": "Counts the number of store ops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "SampleAfterValue": "1000003", + "UMask": "0x82" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "SampleAfterValue": "1000003", + "UMask": "0x6" + } +] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json new file mode 100644 index 000000000000..a0eaf5b6f2bc --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json @@ -0,0 +1,7 @@ +[ + { + "Unit": "core", + "CountersNumFixed": "3", + "CountersNumGeneric": "39" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json new file mode 100644 index 000000000000..7a9250e5c8f2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json @@ -0,0 +1,18 @@ +[ + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.ACCESSES", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "1000003", + "UMask": "0x2" + } +] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json new file mode 100644 index 000000000000..f5007e56f39b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json @@ -0,0 +1,22 @@ +[ + { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x33FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x33FBFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json new file mode 100644 index 000000000000..80454e497f83 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json @@ -0,0 +1,22 @@ +[ + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json new file mode 100644 index 000000000000..6a5faa704b85 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json @@ -0,0 +1,113 @@ +[ + { + "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.CORE", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles.", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of instructions retired.", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "Counter": "36", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls. [This event is alias to TOPDOWN_BE_BOUND.ALL_P]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa4", + "EventName": "TOPDOWN_BE_BOUND.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls. [This event is alias to TOPDOWN_BE_BOUND.ALL]", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa4", + "EventName": "TOPDOWN_BE_BOUND.ALL_P", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls.", + "Counter": "37", + "EventName": "TOPDOWN_FE_BOUND.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.", + "Counter": "38", + "EventName": "TOPDOWN_RETIRING.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7" + } +] diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json new file mode 100644 index 000000000000..78f2b835c1fa --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json @@ -0,0 +1,29 @@ +[ + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "1000003", + "UMask": "0xe" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "1000003", + "UMask": "0xe" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "1000003", + "UMask": "0xe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json index 21d5d96b8a6d..3b0581151d63 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json @@ -92,11 +92,11 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -311,7 +311,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81" @@ -322,7 +321,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82" @@ -333,7 +331,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83" @@ -344,7 +341,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21" @@ -355,7 +351,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41" @@ -366,7 +361,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42" @@ -377,7 +371,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11" @@ -388,7 +381,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12" @@ -408,7 +400,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4" @@ -419,7 +410,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -430,7 +420,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" @@ -441,7 +430,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2" @@ -452,7 +440,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PEBS": "1", "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -463,7 +450,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -473,7 +459,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "PEBS": "1", "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -484,7 +469,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -494,7 +478,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4" @@ -505,7 +488,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -516,7 +498,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -527,7 +508,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8" @@ -538,7 +518,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2" @@ -549,7 +528,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10" @@ -560,7 +538,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4" @@ -571,7 +548,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20" diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json index ee288099a8d3..d3b51fa6ec1c 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json @@ -34,7 +34,7 @@ "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -55,85 +55,73 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS * 4 / 1e6 / duration_time", - "MetricName": "iio_bandwidth_read", - "ScaleUnit": "1MB/s" - }, - { - "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU.", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS * 4 / 1e6 / duration_time", - "MetricName": "iio_bandwidth_write", - "ScaleUnit": "1MB/s" - }, - { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_remote", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_remote", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache.", + "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM / UNC_CHA_TOR_INSERTS.IO_ITOM", "MetricName": "io_percent_of_inbound_full_writes_that_miss_l3", "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache.", + "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_RFO) / (UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_RFO)", "MetricName": "io_percent_of_inbound_partial_writes_that_miss_l3", "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache.", + "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR / UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", "MetricName": "io_percent_of_inbound_reads_that_miss_l3", "ScaleUnit": "100%" @@ -142,14 +130,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -231,36 +219,6 @@ "ScaleUnit": "1ns" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_to_pmem_latency", - "ScaleUnit": "1ns" - }, - { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_read", - "ScaleUnit": "1MB/s" - }, - { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_write", - "ScaleUnit": "1MB/s" - }, - { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_read", - "ScaleUnit": "1MB/s" - }, - { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_write", - "ScaleUnit": "1MB/s" - }, - { "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", "MetricName": "loads_per_instr", @@ -285,19 +243,19 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM).", + "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM)", "MetricExpr": "(UNC_CHA_DIR_UPDATE.HA + UNC_CHA_DIR_UPDATE.TOR + UNC_M2M_DIRECTORY_UPDATE.ANY) * 64 / 1e6 / duration_time", "MetricName": "memory_extra_write_bw_due_to_directory_updates", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -321,24 +279,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_read", - "ScaleUnit": "1MB/s" - }, - { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_total", - "ScaleUnit": "1MB/s" - }, - { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_write", - "ScaleUnit": "1MB/s" - }, - { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -360,7 +300,7 @@ "ScaleUnit": "1per_instr" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -372,7 +312,7 @@ "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks", "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_amx_busy", - "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -380,12 +320,12 @@ "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -395,7 +335,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -411,18 +351,111 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -430,24 +463,24 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -455,8 +488,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", "ScaleUnit": "100%" }, { @@ -464,17 +497,65 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -485,24 +566,24 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -511,17 +592,17 @@ "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "( MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks )", + "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -530,7 +611,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -538,44 +619,44 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -586,7 +667,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -597,16 +678,16 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -615,7 +696,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -624,7 +705,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -632,8 +721,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -641,8 +730,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -650,8 +739,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -659,8 +748,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -668,8 +757,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -680,27 +769,27 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, { @@ -708,40 +797,40 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 6 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -755,7 +844,7 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" @@ -769,15 +858,15 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -785,104 +874,10 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * ( ( tma_memory_bound * ( tma_dram_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_mem_bandwidth / ( tma_mem_bandwidth + tma_mem_latency ) ) ) + ( tma_memory_bound * ( tma_l3_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_sq_full / ( tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full ) ) ) + ( tma_memory_bound * ( tma_l1_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_fb_full / ( tma_dtlb_load + tma_store_fwd_blk + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_fb_full ) ) ) )", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * ( ( tma_memory_bound * ( tma_dram_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_mem_latency / ( tma_mem_bandwidth + tma_mem_latency ) ) ) + ( tma_memory_bound * ( tma_l3_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_l3_hit_latency / ( tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full ) ) ) + ( tma_memory_bound * tma_l2_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) + ( tma_memory_bound * ( tma_store_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_store_latency / ( tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store ) ) ) + ( tma_memory_bound * ( tma_l1_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_l1_hit_latency / ( tma_dtlb_load + tma_store_fwd_blk + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_fb_full ) ) ) )", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu@RS.EMPTY\\,umask\\=1@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * ( tma_memory_bound * ( tma_l1_bound / max( tma_memory_bound , ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) ) * ( tma_dtlb_load / max( tma_l1_bound , ( tma_dtlb_load + tma_store_fwd_blk + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_fb_full ) ) ) + ( tma_memory_bound * ( tma_store_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_dtlb_store / ( tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store ) ) ) )", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * ( tma_memory_bound * ( ( tma_dram_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_mem_latency / ( tma_mem_bandwidth + tma_mem_latency ) ) * tma_remote_cache / ( tma_local_mem + tma_remote_mem + tma_remote_cache ) + ( tma_l3_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * ( tma_contested_accesses + tma_data_sharing ) / ( tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full ) + ( tma_store_bound / ( tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound ) ) * tma_false_sharing / ( ( tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store ) - tma_store_latency ) ) + tma_machine_clears * ( 1 - tma_other_nukes / ( tma_other_nukes ) ) )", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -943,11 +938,11 @@ "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -960,20 +955,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -1003,14 +998,20 @@ "MetricName": "tma_info_frontend_l2mpki_code_all" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node." + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -1028,7 +1029,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -1036,7 +1037,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -1044,7 +1045,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -1052,7 +1053,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -1060,7 +1061,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)", @@ -1068,7 +1069,7 @@ "MetricGroup": "Flops;FpScalar;InsType;Server", "MetricName": "tma_info_inst_mix_iparith_scalar_hp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -1076,7 +1077,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1121,7 +1122,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -1131,7 +1132,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 13", + "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1178,7 +1179,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -1196,7 +1197,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -1238,13 +1239,13 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -1263,12 +1264,12 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1322,25 +1323,32 @@ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15" + }, + { "BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket", - "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / duration_time", + "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_dram_bw", - "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." + "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW" }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", - "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / duration_time", + "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", - "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." + "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW" }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", - "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / duration_time", + "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", - "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." + "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches" }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1369,7 +1377,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1390,18 +1398,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1" @@ -1415,7 +1423,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1433,28 +1441,28 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.8_FLOPS) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.8_FLOPS) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_read_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e9 / duration_time", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_write_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU" @@ -1464,13 +1472,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1481,44 +1490,45 @@ }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { + "BriefDescription": "Fraction of Uncore cycles where requests got rejected due to duplicate address already in IRQ ingress queue in the cache homing agent", + "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS", + "MetricGroup": "LockCont;MemOffcore;Server;SoC", + "MetricName": "tma_info_system_mem_irq_duplicate_address", + "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)" + }, + { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", - "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@ if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", - "MetricName": "tma_info_system_mem_pmm_read_latency", - "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" - }, - { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_read_bw" + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_write_bw" + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1528,11 +1538,18 @@ }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "uncore_cha_0@event\\=0x1@", + "MetricExpr": "cha_0@event\\=0x0@", "MetricGroup": "SoC", "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -1540,7 +1557,7 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, @@ -1551,7 +1568,7 @@ "MetricName": "tma_info_system_upi_data_transmit_bw" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1560,14 +1577,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1577,13 +1595,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1599,7 +1617,15 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 9" + "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", @@ -1607,7 +1633,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", "ScaleUnit": "100%" }, { @@ -1615,8 +1641,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1624,8 +1650,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1633,26 +1659,26 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1660,8 +1686,17 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1669,17 +1704,17 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1687,19 +1722,19 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "DefaultMetricgroupName": "TopdownL2", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1716,7 +1751,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1724,24 +1759,48 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1753,24 +1812,24 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)", "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", "MetricName": "tma_mba_stalls", - "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1778,32 +1837,32 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1816,7 +1875,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1824,8 +1883,8 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1838,21 +1897,29 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1861,7 +1928,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", "ScaleUnit": "100%" }, { @@ -1869,7 +1936,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1883,19 +1950,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1904,7 +1971,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", "ScaleUnit": "100%" }, { @@ -1913,7 +1980,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1922,7 +1989,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1931,25 +1998,25 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_thread_clks)", + "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(cpu@RS.EMPTY\\,umask\\=1@ - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", + "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1957,7 +2024,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1967,8 +2034,8 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", "ScaleUnit": "100%" }, { @@ -1977,32 +2044,32 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2015,7 +2082,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -2024,8 +2091,8 @@ "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", + "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", "ScaleUnit": "100%" }, { @@ -2034,7 +2101,7 @@ "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -2043,8 +2110,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -2052,17 +2119,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -2070,8 +2137,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -2079,17 +2146,17 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -2106,7 +2173,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -2114,7 +2181,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -2122,7 +2213,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -2131,7 +2222,7 @@ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, @@ -2140,29 +2231,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "Percentage of cycles in aborted transactions.", - "MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)", - "MetricGroup": "transaction", - "MetricName": "tsx_aborted_cycles", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", - "MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)", - "MetricGroup": "transaction", - "MetricName": "tsx_cycles_per_transaction", - "ScaleUnit": "1cycles / transaction" - }, - { - "BriefDescription": "Percentage of cycles within a transaction region.", - "MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)", - "MetricGroup": "transaction", - "MetricName": "tsx_transactional_cycles", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { @@ -2172,12 +2242,6 @@ "ScaleUnit": "1GHz" }, { - "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)", - "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", - "MetricName": "upi_data_receive_bw", - "ScaleUnit": "1MB/s" - }, - { "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", "MetricName": "upi_data_transmit_bw", diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json index f6e3e40a3b20..bf68493d4509 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json @@ -41,7 +41,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -53,7 +52,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -65,7 +63,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -77,7 +74,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -89,7 +85,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -101,7 +96,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -113,7 +107,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -125,7 +118,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -137,7 +129,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -149,7 +140,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -161,7 +151,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -173,7 +162,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -185,7 +173,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -197,7 +184,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -209,7 +195,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -221,7 +206,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -233,7 +217,6 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -244,7 +227,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -256,7 +238,6 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json index 2ea19539291b..41d4120d4dae 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json @@ -63,7 +63,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1" @@ -76,7 +75,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1" @@ -89,7 +87,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -102,7 +99,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1" @@ -115,7 +111,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -128,7 +123,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1" @@ -141,7 +135,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1" @@ -154,7 +147,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1" @@ -167,7 +159,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -178,7 +169,6 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PEBS": "2", "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", "SampleAfterValue": "1000003", "UMask": "0x2" @@ -305,17 +295,16 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4" }, { - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/metricgroups.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/metricgroups.json index e1de6c2675c4..9129fb7b7ce4 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/metricgroups.json @@ -40,6 +40,7 @@ "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -86,7 +87,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -96,6 +99,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_int_operations_group": "Metrics contributing to tma_int_operations category", "tma_issue2P": "Metrics related by the issue $issue2P", "tma_issueBM": "Metrics related by the issue $issueBM", @@ -116,10 +120,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_bandwidth_group": "Metrics contributing to tma_mem_bandwidth category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", @@ -133,5 +140,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json index 5d5811f26151..50cacfbbc7cf 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json @@ -62,7 +62,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009" }, @@ -71,7 +70,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -81,7 +79,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -91,7 +88,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -101,7 +97,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -111,7 +106,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -121,7 +115,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" @@ -131,7 +124,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -141,7 +133,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -151,7 +142,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "400009" }, @@ -160,7 +150,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -170,7 +159,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -180,7 +168,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -190,7 +177,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -200,7 +186,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "400009", "UMask": "0x2" @@ -210,7 +195,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -220,7 +204,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -469,7 +452,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -479,7 +461,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003" }, @@ -488,7 +469,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -497,7 +477,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2" @@ -506,7 +485,6 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -516,7 +494,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PEBS": "1", "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8" diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json index 91013ced74aa..94340dee1c9c 100644 --- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json @@ -80,86 +80,6 @@ "Unit": "iio_free_running" }, { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "9", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART0_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x30", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "10", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART1_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "11", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART2_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x32", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "12", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART3_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x33", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "13", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART4_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x34", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "14", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART5_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x35", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "15", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART6_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x36", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "Counter": "16", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART7_FREERUN", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "iio_free_running" - }, - { "BriefDescription": "IIO Clockticks", "Counter": "0,1,2,3", "EventCode": "0x01", @@ -201,7 +121,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -214,7 +134,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -227,7 +147,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -240,7 +160,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -253,7 +173,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -266,7 +186,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -279,7 +199,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -292,7 +212,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -316,7 +236,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7000001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -329,7 +249,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 1", - "UMask": "0x7000002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -342,7 +262,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7000004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -355,7 +275,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 3", - "UMask": "0x7000008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -368,7 +288,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7000010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -381,7 +301,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 1", - "UMask": "0x7000020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -394,7 +314,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7000040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -407,7 +327,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 3", - "UMask": "0x7000080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -431,7 +351,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -443,7 +363,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -455,7 +375,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -467,7 +387,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -479,7 +399,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -491,7 +411,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -503,7 +423,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -515,7 +435,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -662,7 +582,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -675,7 +595,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -688,7 +608,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7004008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -701,7 +621,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -714,7 +634,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7010008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -727,7 +647,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7020008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -740,7 +660,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7040008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -753,7 +673,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7080008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -766,7 +686,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -779,7 +699,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -792,7 +712,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -805,7 +725,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -818,7 +738,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -831,7 +751,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -844,7 +764,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -857,7 +777,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -974,7 +894,6 @@ "Counter": "0,1", "EventCode": "0x83", "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS", - "Experimental": "1", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x00ff", @@ -1082,7 +1001,6 @@ "Counter": "0,1", "EventCode": "0x83", "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS", - "Experimental": "1", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x00ff", @@ -1299,7 +1217,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1351,7 +1269,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1364,7 +1282,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1377,7 +1295,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1390,7 +1308,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1403,7 +1321,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1416,7 +1334,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1429,7 +1347,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1442,7 +1360,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1962,7 +1880,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : PCIe Request complete : Only for posted requests : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1975,7 +1893,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : Writing line : Only for posted requests : Only for posted requests", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1988,7 +1906,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : Issuing final read or write of line : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -2001,7 +1919,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : Passing data to be written : Only for posted requests : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -2014,7 +1932,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Processing response from IOMMU : Passing data to be written : Only for posted requests", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -2026,7 +1944,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x00FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2039,7 +1957,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Processing response from IOMMU : Request Ownership : Only for posted requests", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -2052,7 +1970,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Processing response from IOMMU : Writing line : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -2065,7 +1983,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -2091,7 +2009,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -2104,7 +2022,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -2309,7 +2227,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2322,7 +2240,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2335,7 +2253,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2348,7 +2266,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2361,7 +2279,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2374,7 +2292,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2387,7 +2305,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2400,7 +2318,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" }, { diff --git a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json index 07e542297e93..2f9959c61718 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json @@ -1,5 +1,12 @@ [ { + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", + "ScaleUnit": "100%" + }, + { "BriefDescription": "C1 residency percent per core", "MetricExpr": "cstate_core@c1\\-residency@ / TSC", "MetricGroup": "Power", @@ -7,17 +14,24 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per module", - "MetricExpr": "cstate_module@c6\\-residency@ / TSC", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C6_Module_Residency", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { @@ -28,7 +42,21 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -49,31 +77,31 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" @@ -82,14 +110,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -188,17 +216,15 @@ { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions", "MetricExpr": "tma_core_bound", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%" @@ -206,104 +232,92 @@ { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", - "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)", "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation", "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls", "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming", "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls", "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses", "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -333,32 +347,6 @@ }, { "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", - "MetricExpr": "tma_info_bottleneck_dtlb_miss_bound_cycles", - "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss", - "MetricExpr": "tma_info_bottleneck_ifetch_miss_bound_cycles", - "MetricGroup": "Ifetch", - "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles", - "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound" - }, - { - "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss", - "MetricExpr": "tma_info_bottleneck_load_miss_bound_cycles", - "MetricGroup": "Load_Store_Miss", - "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound" - }, - { - "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall", - "MetricExpr": "tma_info_bottleneck_mem_exec_bound_cycles", - "MetricGroup": "Mem_Exec", - "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound" - }, - { - "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE", "MetricGroup": "Cycles", "MetricName": "tma_info_bottleneck_dtlb_miss_bound_cycles", @@ -440,21 +428,6 @@ }, { "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", - "MetricExpr": "tma_info_buffer_stalls_load_buffer_stall_cycles", - "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full", - "MetricExpr": "tma_info_buffer_stalls_mem_rsv_stall_cycles", - "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full", - "MetricExpr": "tma_info_buffer_stalls_store_buffer_stall_cycles", - "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE", "MetricName": "tma_info_buffer_stalls_load_buffer_stall_cycles", "ScaleUnit": "100%" @@ -474,7 +447,8 @@ { "BriefDescription": "Cycles Per Instruction", "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY", - "MetricName": "tma_info_core_cpi" + "MetricName": "tma_info_core_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Floating Point Operations Per Cycle", @@ -494,21 +468,6 @@ }, { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", - "MetricExpr": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit", - "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit" - }, - { - "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", - "MetricExpr": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit", - "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit" - }, - { - "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3", - "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL", - "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss" - }, - { - "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL", "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit", "ScaleUnit": "100%" @@ -521,24 +480,6 @@ }, { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", - "MetricExpr": "tma_info_load_miss_bound_loadmissbound_with_l2hit", - "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit" - }, - { - "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", - "MetricExpr": "tma_info_load_miss_bound_loadmissbound_with_l3hit", - "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit" - }, - { - "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3", - "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL", - "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss" - }, - { - "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL", "MetricGroup": "load_store_bound", "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l2hit", @@ -586,16 +527,6 @@ }, { "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", - "MetricExpr": "tma_info_mem_exec_blocks_loads_with_adressaliasing", - "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing" - }, - { - "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", - "MetricExpr": "tma_info_mem_exec_blocks_loads_with_storefwdblk", - "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk" - }, - { - "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", "MetricName": "tma_info_mem_exec_blocks_loads_with_adressaliasing", "ScaleUnit": "100%" @@ -608,31 +539,6 @@ }, { "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_l1miss", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_pagewalk", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_stlbhit", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_storefwding", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET", "MetricName": "tma_info_mem_exec_bound_loadhead_with_l1miss", "ScaleUnit": "100%" @@ -688,11 +594,6 @@ }, { "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", - "MetricExpr": "tma_info_serialization_tpause_cycles", - "MetricName": "tma_info_serialization _%_tpause_cycles" - }, - { - "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)", "MetricName": "tma_info_serialization_tpause_cycles", "ScaleUnit": "100%" @@ -711,14 +612,17 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Summary", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE", "MetricName": "tma_info_system_kernel_utilization" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE", + "MetricName": "tma_info_system_mux" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { @@ -742,102 +646,90 @@ "MetricName": "tma_info_uop_mix_x87_uop_ratio" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses", "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)", "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized", "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes", "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation", "MetricExpr": "tma_backend_bound - tma_core_bound", - "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that result in retirement slots", "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)", "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json index b67c0c89054d..40fa4f5ae261 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "Counts the number of cycles when any of the dividers are active.", + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xcd", @@ -185,7 +185,6 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json index 1eaf796601b1..6a80cf6cbd36 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json @@ -573,7 +573,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Code read from local IA that miss the cache", + "BriefDescription": "Code read from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", @@ -593,7 +593,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read opt from local IA that miss the cache", + "BriefDescription": "Data read opt from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-interconnect.json index 6aaca4039107..2c18767511f3 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-interconnect.json @@ -184,6 +184,26 @@ "Unit": "IRP" }, { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "Counter": "0,1,2,3", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REJ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "Counter": "0,1,2,3", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { "BriefDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", "Counter": "0,1,2,3", "EventCode": "0x1F", @@ -194,6 +214,46 @@ "Unit": "IRP" }, { + "BriefDescription": "Snoop Hit E/S responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Hit I responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Hit M responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop miss responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x71", + "Unit": "IRP" + }, + { "BriefDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", "Counter": "0,1,2,3", "EventCode": "0x11", diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-io.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-io.json index 33fc7b835abf..c5b05c71c56d 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-io.json @@ -17,7 +17,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -29,7 +29,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -41,7 +41,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -53,7 +53,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -65,7 +65,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -77,7 +77,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -89,7 +89,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -101,7 +101,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -113,7 +113,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -125,7 +125,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff0ff", + "UMask": "0xff", "Unit": "IIO" }, { @@ -137,7 +137,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -149,7 +149,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -161,7 +161,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -173,7 +173,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -185,7 +185,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -197,7 +197,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -209,7 +209,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -221,7 +221,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -232,7 +232,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -244,7 +244,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -256,7 +256,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -268,7 +268,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -280,7 +280,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -292,7 +292,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -304,7 +304,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -316,7 +316,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -328,7 +328,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -339,7 +339,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -350,7 +350,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -361,7 +361,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -372,7 +372,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -383,7 +383,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -394,7 +394,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -405,7 +405,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -416,7 +416,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -427,7 +427,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -438,7 +438,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -449,7 +449,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -460,7 +460,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -471,7 +471,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -482,7 +482,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x10", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -493,7 +493,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x20", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -504,7 +504,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x40", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -515,7 +515,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x80", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -526,7 +526,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -537,7 +537,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -548,7 +548,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -559,7 +559,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -570,7 +570,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x10", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -581,7 +581,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x20", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -592,7 +592,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x40", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -603,7 +603,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x80", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -615,7 +615,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -627,7 +627,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -639,7 +639,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -651,7 +651,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -663,7 +663,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -675,7 +675,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -687,7 +687,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -699,7 +699,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -832,7 +832,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -844,7 +844,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -856,7 +856,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -868,7 +868,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -880,7 +880,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -892,7 +892,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -904,7 +904,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -925,7 +925,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -936,7 +936,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -947,7 +947,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -958,7 +958,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -969,7 +969,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -980,7 +980,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -991,7 +991,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1002,7 +1002,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1013,7 +1013,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1024,7 +1024,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1035,7 +1035,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1046,7 +1046,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1057,7 +1057,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1068,7 +1068,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1079,7 +1079,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1090,7 +1090,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1101,7 +1101,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1112,7 +1112,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1123,7 +1123,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1134,7 +1134,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1145,7 +1145,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1156,7 +1156,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1167,7 +1167,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1178,7 +1178,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1189,7 +1189,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1200,7 +1200,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1211,7 +1211,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1222,7 +1222,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1233,7 +1233,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1244,7 +1244,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1255,7 +1255,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1266,7 +1266,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1278,7 +1278,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1290,7 +1290,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1302,7 +1302,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1314,7 +1314,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1326,7 +1326,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1338,7 +1338,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1350,7 +1350,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1362,7 +1362,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" } ] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json index 7e6e6764f181..e75b3050ccd5 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json @@ -169,7 +169,7 @@ "Unit": "IMC" }, { - "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled", + "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled. DCLK is 1/4 of DRAM data rate.", "Counter": "0,1,2,3", "EventCode": "0x01", "EventName": "UNC_M_CLOCKTICKS", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json index b56066274813..d155da8610d8 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json @@ -83,11 +83,11 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -320,7 +320,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81" @@ -331,7 +330,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82" @@ -342,7 +340,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83" @@ -353,7 +350,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21" @@ -364,7 +360,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41" @@ -375,7 +370,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42" @@ -386,7 +380,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x9" @@ -397,7 +390,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0xa" @@ -408,7 +400,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11" @@ -419,7 +410,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12" @@ -439,7 +429,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4" @@ -450,7 +439,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -461,7 +449,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" @@ -472,7 +459,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2" @@ -483,7 +469,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PEBS": "1", "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -494,7 +479,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -504,7 +488,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "PEBS": "1", "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -515,7 +498,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -525,7 +507,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4" @@ -536,7 +517,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -547,7 +527,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -558,7 +537,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8" @@ -569,7 +547,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2" @@ -580,7 +557,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10" @@ -591,7 +567,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4" @@ -602,7 +577,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -665,6 +639,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -675,6 +659,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1030000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x830000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -705,6 +709,76 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C4477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1830004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1030004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x830004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.RFO_TO_CORE.L3_HIT_M", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F80040022", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3", "EventCode": "0x21", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json index 250781a8ca64..137da7efa8b1 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json @@ -20,6 +20,16 @@ "CountersNumGeneric": "4" }, { + "Unit": "CXLCM", + "CountersNumFixed": "0", + "CountersNumGeneric": 8 + }, + { + "Unit": "CXLDP", + "CountersNumFixed": "0", + "CountersNumGeneric": 4 + }, + { "Unit": "B2HOT", "CountersNumFixed": "0", "CountersNumGeneric": 4 @@ -52,26 +62,16 @@ { "Unit": "PCU", "CountersNumFixed": "0", - "CountersNumGeneric": 4 + "CountersNumGeneric": "4" }, { "Unit": "CHACMS", "CountersNumFixed": "0", - "CountersNumGeneric": 4 + "CountersNumGeneric": "4" }, { "Unit": "MDF", "CountersNumFixed": "0", "CountersNumGeneric": "4" - }, - { - "Unit": "CXLCM", - "CountersNumFixed": "0", - "CountersNumGeneric": 8 - }, - { - "Unit": "CXLDP", - "CountersNumFixed": "0", - "CountersNumGeneric": 4 } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json index 663c1a0e55a2..dc81055941b1 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json @@ -41,7 +41,6 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PEBS": "1", "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", "SampleAfterValue": "100007", "UMask": "0x3" @@ -53,7 +52,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -65,7 +63,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -77,7 +74,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -89,7 +85,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -101,7 +96,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -113,7 +107,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -125,7 +118,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -137,7 +129,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -149,7 +140,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -161,7 +151,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -173,7 +162,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -185,7 +173,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -197,7 +184,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -209,7 +195,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -221,7 +206,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -233,7 +217,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -244,8 +227,7 @@ "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATE_SWPF", "MSRIndex": "0x3F7", - "MSRValue": "0x9", - "PEBS": "1", + "MSRValue": "0xA", "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions", "SampleAfterValue": "100007", "UMask": "0x3" @@ -257,7 +239,6 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PEBS": "1", "PublicDescription": "ANT retired branches that got just mispredicted", "SampleAfterValue": "100007", "UMask": "0x2" @@ -269,7 +250,6 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x3" }, @@ -280,7 +260,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x3" @@ -292,7 +271,6 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x3" }, diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json new file mode 100644 index 000000000000..a345b6874606 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json @@ -0,0 +1,2325 @@ +[ + { + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" + }, + { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "The average number of cores that are in cstate C0 as observed by the power control unit (PCU)", + "MetricExpr": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0 / pcu_0@UNC_P_CLOCKTICKS@ * #num_packages", + "MetricGroup": "cpu_cstate", + "MetricName": "cpu_cstate_c0" + }, + { + "BriefDescription": "The average number of cores are in cstate C6 as observed by the power control unit (PCU)", + "MetricExpr": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6 / pcu_0@UNC_P_CLOCKTICKS@ * #num_packages", + "MetricGroup": "cpu_cstate", + "MetricName": "cpu_cstate_c6" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpus_utilized", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS * 4 / 1e6 / duration_time", + "MetricName": "iio_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS * 4 / 1e6 / duration_time", + "MetricName": "iio_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read_local", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read_remote", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write_local", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write_remote", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_2nd_level_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA + UNC_CHA_TOR_INSERTS.IA_MISS_DRD + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF) / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to DRAM in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_to_dram_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory", + "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory", + "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT_SCH0.RD + UNC_M_CAS_COUNT_SCH1.RD) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT_SCH0.RD + UNC_M_CAS_COUNT_SCH1.RD + UNC_M_CAS_COUNT_SCH0.WR + UNC_M_CAS_COUNT_SCH1.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT_SCH0.WR + UNC_M_CAS_COUNT_SCH1.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" + }, + { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the Advanced Matrix eXtensions (AMX) execution engine was busy with tile (arithmetic) operations", + "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks", + "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_amx_busy", + "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots", + "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_avx_assists", + "MetricThreshold": "tma_avx_assists > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", + "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks", + "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_c01_wait", + "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks", + "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_c02_wait", + "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, FRONTEND_RETIRED.L1I_MISS * FRONTEND_RETIRED.L1I_MISS:R / tma_info_thread_clks - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "FRONTEND_RETIRED.L2_MISS * FRONTEND_RETIRED.L2_MISS:R / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, FRONTEND_RETIRED.ITLB_MISS * FRONTEND_RETIRED.ITLB_MISS:R / tma_info_thread_clks - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "FRONTEND_RETIRED.STLB_MISS * FRONTEND_RETIRED.STLB_MISS:R / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", + "MetricExpr": "BR_MISP_RETIRED.COND_NTAKEN_COST * BR_MISP_RETIRED.COND_NTAKEN_COST:R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_nt_mispredicts", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches", + "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_COST * BR_MISP_RETIRED.COND_TAKEN_COST:R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_tk_mispredicts", + "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", + "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_LOADS * MEM_INST_RETIRED.STLB_HIT_LOADS:R, MEM_INST_RETIRED.STLB_HIT_LOADS * 7) if 0 < MEM_INST_RETIRED.STLB_HIT_LOADS:R else MEM_INST_RETIRED.STLB_HIT_LOADS * 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_STORES * MEM_INST_RETIRED.STLB_HIT_STORES:R, MEM_INST_RETIRED.STLB_HIT_STORES * 7) if 0 < MEM_INST_RETIRED.STLB_HIT_STORES:R else MEM_INST_RETIRED.STLB_HIT_STORES * 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "Default;FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.2", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", + "MetricGroup": "Default;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", + "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", + "MetricExpr": "30 * ASSISTS.FP / tma_info_thread_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_fp_assists", + "MetricThreshold": "tma_fp_assists > 0.1", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", + "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", + "MetricExpr": "BR_MISP_RETIRED.INDIRECT_CALL_COST * BR_MISP_RETIRED.INDIRECT_CALL_COST:R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_call_mispredicts", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", + "MetricExpr": "max((BR_MISP_RETIRED.INDIRECT_COST * BR_MISP_RETIRED.INDIRECT_COST:R - BR_MISP_RETIRED.INDIRECT_CALL_COST * BR_MISP_RETIRED.INDIRECT_CALL_COST:R) / tma_info_thread_clks, 0)", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_jump_mispredicts", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 6 / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", + "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", + "MetricGroup": "BrMispredicts", + "MetricName": "tma_info_bad_spec_spec_clears_ratio" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", + "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" + }, + { + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_nt" + }, + { + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_tk" + }, + { + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches" + }, + { + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else tma_info_thread_clks)", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_core_clks" + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_core_coreipc" + }, + { + "BriefDescription": "uops Executed per Cycle", + "MetricExpr": "UOPS_EXECUTED.THREAD / tma_info_thread_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_core_epc" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" + }, + { + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_frontend_dsb_switch_cost" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses", + "MetricExpr": "FRONTEND_RETIRED.ANY_DSB_MISS * FRONTEND_RETIRED.ANY_DSB_MISS:R / tma_info_thread_clks", + "MetricGroup": "DSBmiss;Fed;FetchLat", + "MetricName": "tma_info_frontend_dsb_switches_ret", + "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05" + }, + { + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_frontend_fetch_upc" + }, + { + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / ICACHE_DATA.STALL_PERIODS", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" + }, + { + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" + }, + { + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" + }, + { + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" + }, + { + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer", + "MetricExpr": "FRONTEND_RETIRED.MS_FLOWS * FRONTEND_RETIRED.MS_FLOWS:R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_frontend_ms_latency_ret", + "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05" + }, + { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_unknown_branch_cost", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", + "MetricExpr": "FRONTEND_RETIRED.UNKNOWN_BRANCH * FRONTEND_RETIRED.UNKNOWN_BRANCH:R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat", + "MetricName": "tma_info_frontend_unknown_branches_ret" + }, + { + "BriefDescription": "Branch instructions per taken branch", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_inst_mix_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR + (FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR))", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED2.SCALAR", + "MetricGroup": "Flops;FpScalar;InsType;Server", + "MetricName": "tma_info_inst_mix_iparith_scalar_hp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" + }, + { + "BriefDescription": "Instructions per PAUSE (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / CPU_CLK_UNHALTED.PAUSE_INST", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_ippause" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" + }, + { + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" + }, + { + "BriefDescription": "Instructions per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", + "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw_2t" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw_2t" + }, + { + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_nonsilent_pki" + }, + { + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_silent_pki" + }, + { + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw_2t" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l3_cache_fill_bw_2t" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_fb_hpki" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1d_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1mpki" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1mpki_load" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l2_cache_fill_bw" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2hpki_all" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2hpki_load" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheHits;Mem", + "MetricName": "tma_info_memory_l2mpki" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheHits;Mem;Offcore", + "MetricName": "tma_info_memory_l2mpki_all" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2mpki_load" + }, + { + "BriefDescription": "Offcore requests (L2 cache miss) per kilo instruction for demand RFOs", + "MetricExpr": "1e3 * L2_RQSTS.RFO_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Offcore", + "MetricName": "tma_info_memory_l2mpki_rfo" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_l3_cache_access_bw" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l3_cache_fill_bw" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_l3mpki" + }, + { + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_latency_data_l2_mlp" + }, + { + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "LockCont;Memory_Lat;Offcore", + "MetricName": "tma_info_memory_latency_load_l2_miss_latency" + }, + { + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_latency_load_l2_mlp" + }, + { + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_latency_load_l3_miss_latency" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" + }, + { + "BriefDescription": "\"Bus lock\" per kilo instruction", + "MetricExpr": "1e3 * SQ_MISC.BUS_LOCK / INST_RETIRED.ANY", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_mix_bus_lock_pki" + }, + { + "BriefDescription": "Off-core accesses per kilo instruction for modified write requests", + "MetricExpr": "1e3 * OCR.MODIFIED_WRITE.ANY_RESPONSE / tma_info_inst_mix_instructions", + "MetricGroup": "Offcore", + "MetricName": "tma_info_memory_mix_offcore_mwrite_any_pki" + }, + { + "BriefDescription": "Off-core accesses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", + "MetricExpr": "1e3 * OCR.READS_TO_CORE.ANY_RESPONSE / tma_info_inst_mix_instructions", + "MetricGroup": "CacheHits;Offcore", + "MetricName": "tma_info_memory_mix_offcore_read_any_pki" + }, + { + "BriefDescription": "L3 cache misses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)", + "MetricExpr": "1e3 * OCR.READS_TO_CORE.L3_MISS / tma_info_inst_mix_instructions", + "MetricGroup": "Offcore", + "MetricName": "tma_info_memory_mix_offcore_read_l3m_pki" + }, + { + "BriefDescription": "Un-cacheable retired load per kilo instruction", + "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_mix_uc_load_pki" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + }, + { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15" + }, + { + "BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket", + "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricName": "tma_info_memory_soc_r2c_dram_bw", + "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW" + }, + { + "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", + "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricName": "tma_info_memory_soc_r2c_l3m_bw", + "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW" + }, + { + "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", + "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricName": "tma_info_memory_soc_r2c_offcore_bw", + "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads", + "MetricExpr": "MEM_INST_RETIRED.STLB_MISS_LOADS * MEM_INST_RETIRED.STLB_MISS_LOADS:R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05" + }, + { + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores", + "MetricExpr": "MEM_INST_RETIRED.STLB_MISS_STORES * MEM_INST_RETIRED.STLB_MISS_STORES:R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" + }, + { + "BriefDescription": "Average number of uops fetched from DSB per cycle", + "MetricExpr": "IDQ.DSB_UOPS / IDQ.DSB_CYCLES_ANY", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_dsb" + }, + { + "BriefDescription": "Average number of uops fetched from MITE per cycle", + "MetricExpr": "IDQ.MITE_UOPS / IDQ.MITE_CYCLES_ANY", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_mite" + }, + { + "BriefDescription": "Instructions per a microcode Assist invocation", + "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", + "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", + "MetricName": "tma_info_pipeline_ipassist", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" + }, + { + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricGroup": "MicroSeq;Pipeline;Ret", + "MetricName": "tma_info_pipeline_strings_cycles", + "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1" + }, + { + "BriefDescription": "Fraction of cycles the processor is waiting yet unhalted; covering legacy PAUSE instruction, as well as C0.1 / C0.2 power-performance optimized states", + "MetricExpr": "CPU_CLK_UNHALTED.C0_WAIT / tma_info_thread_clks", + "MetricGroup": "C0Wait", + "MetricName": "tma_info_system_c0_wait", + "MetricThreshold": "tma_info_system_c0_wait > 0.05" + }, + { + "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_core_frequency" + }, + { + "BriefDescription": "Average CPU Utilization (percentage)", + "MetricExpr": "tma_info_system_cpus_utilized / #num_cpus_online", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average number of utilized CPUs", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_cpus_utilized" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT_SCH0.RD + UNC_M_CAS_COUNT_SCH1.RD + UNC_M_CAS_COUNT_SCH0.WR + UNC_M_CAS_COUNT_SCH1.WR) / 1e9 / tma_info_system_time", + "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / tma_info_system_time", + "MetricGroup": "IoBW;MemOffcore;Server;SoC", + "MetricName": "tma_info_system_io_read_bw", + "PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e9 / tma_info_system_time", + "MetricGroup": "IoBW;MemOffcore;Server;SoC", + "MetricName": "tma_info_system_io_write_bw", + "PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", + "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", + "MetricName": "tma_info_system_mem_dram_read_latency", + "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_system_smt_2t_utilization" + }, + { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cha_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_socket_clks" + }, + { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_uncore_frequency" + }, + { + "BriefDescription": "Cross-socket Ultra Path Interconnect (UPI) data transmit bandwidth for data only [MB / sec]", + "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 64 / 9 / 1e6", + "MetricGroup": "Server;SoC", + "MetricName": "tma_info_system_upi_data_transmit_bw" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "slots", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots_utilization" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" + }, + { + "BriefDescription": "Uops per taken branch", + "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_int_operations", + "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_128b", + "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_256b", + "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", + "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", + "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", + "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "(min(MEM_LOAD_RETIRED.L2_HIT * MEM_LOAD_RETIRED.L2_HIT:R, MEM_LOAD_RETIRED.L2_HIT * (4.4 * tma_info_system_core_frequency)) if 0 < MEM_LOAD_RETIRED.L2_HIT:R else MEM_LOAD_RETIRED.L2_HIT * (4.4 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", + "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "(min(MEM_LOAD_RETIRED.L3_HIT * MEM_LOAD_RETIRED.L3_HIT:R, MEM_LOAD_RETIRED.L3_HIT * (37 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_RETIRED.L3_HIT:R else MEM_LOAD_RETIRED.L3_HIT * (37 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "DECODE.LCP / tma_info_thread_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM:R * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_local_mem", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "MEM_INST_RETIRED.LOCK_LOADS * MEM_INST_RETIRED.LOCK_LOADS:R / tma_info_thread_clks", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;BvMS;Default;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)", + "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", + "MetricName": "tma_mba_stalls", + "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", + "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "DefaultMetricgroupName": "TopdownL2", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2;Default", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_memory_fence", + "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", + "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", + "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_other_mispredicts", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", + "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_other_nukes", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", + "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_thread_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_page_faults", + "MetricThreshold": "tma_page_faults > 0.05", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "max(EXE_ACTIVITY.EXE_BOUND_0_PORTS - RESOURCE_STALLS.SCOREBOARD, 0) / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", + "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricExpr": "(MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM:R + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD:R) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricExpr": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM:R * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_mem", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", + "MetricExpr": "BR_MISP_RETIRED.RET_COST * BR_MISP_RETIRED.RET_COST:R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ret_mispredicts", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait", + "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer)", + "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", + "MetricName": "tma_shuffles_256b", + "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_LOADS * MEM_INST_RETIRED.SPLIT_LOADS:R, MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) if 0 < MEM_INST_RETIRED.SPLIT_LOADS:R else MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_STORES * MEM_INST_RETIRED.SPLIT_STORES:R, MEM_INST_RETIRED.SPLIT_STORES) if 0 < MEM_INST_RETIRED.SPLIT_STORES:R else MEM_INST_RETIRED.SPLIT_STORES) / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages) / 1e9 / duration_time", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_receive_bw", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_transmit_bw", + "ScaleUnit": "1MB/s" + } +] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json index 38b74c6752c2..5da5a10275ba 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json @@ -72,7 +72,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1" @@ -85,7 +84,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1" @@ -98,7 +96,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -111,7 +108,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "23", "UMask": "0x1" @@ -124,7 +120,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1" @@ -137,7 +132,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -150,7 +144,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1" @@ -163,7 +156,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1" @@ -176,7 +168,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1" @@ -189,7 +180,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -200,7 +190,6 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PEBS": "2", "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", "SampleAfterValue": "1000003", "UMask": "0x2" @@ -246,6 +235,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F04C04477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster. It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70CC04477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data read requests that miss the L3 cache.", "Counter": "0,1,2,3", "EventCode": "0x21", @@ -271,5 +280,95 @@ "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", "SampleAfterValue": "2000003", "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an RTM execution aborted.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED", + "PublicDescription": "Counts the number of times RTM abort was triggered.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times an RTM execution successfully committed", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Counts the number of times RTM commit succeeded.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_READ", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "SampleAfterValue": "100003", + "UMask": "0x1" } ] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/metricgroups.json b/tools/perf/pmu-events/arch/x86/graniterapids/metricgroups.json new file mode 100644 index 000000000000..9129fb7b7ce4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/metricgroups.json @@ -0,0 +1,145 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "C0Wait": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemOffcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_assists_group": "Metrics contributing to tma_assists category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", + "tma_int_operations_group": "Metrics contributing to tma_int_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueComp": "Metrics related by the issue $issueComp", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", + "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", + "tma_mem_bandwidth_group": "Metrics contributing to tma_mem_bandwidth category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_other_light_ops_group": "Metrics contributing to tma_other_light_ops category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" +} diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/other.json b/tools/perf/pmu-events/arch/x86/graniterapids/other.json index 8b9b3c920934..8df37f303273 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/other.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/other.json @@ -1,5 +1,14 @@ [ { + "BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. the event also counts for Machine Ordering count.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc1", + "EventName": "ASSISTS.HARDWARE", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { "BriefDescription": "ASSISTS.PAGE_FAULT", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", @@ -66,6 +75,36 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -116,6 +155,66 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70C004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F33004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x733004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", @@ -126,6 +225,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.WRITE_ESTIMATE.MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFBFF80822", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json index 0ef9daf64e2e..da6478607984 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json @@ -32,7 +32,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009" }, @@ -41,7 +40,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -51,7 +49,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -61,7 +58,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -71,7 +67,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -81,7 +76,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -91,7 +85,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" @@ -101,7 +94,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -111,7 +103,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -121,7 +112,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "400009" }, @@ -130,7 +120,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x44" }, @@ -139,7 +128,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -149,7 +137,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x51" }, @@ -158,7 +145,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -168,7 +154,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x50" }, @@ -177,7 +162,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -187,7 +171,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x41" }, @@ -196,7 +179,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -206,7 +188,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "400009", "UMask": "0x2" @@ -216,7 +197,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x42" }, @@ -225,7 +205,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", - "PEBS": "1", "SampleAfterValue": "100003", "UMask": "0xc0" }, @@ -234,7 +213,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -244,7 +222,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x60" }, @@ -253,7 +230,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -263,7 +239,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x48" }, @@ -511,7 +486,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -521,7 +495,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003" }, @@ -530,7 +503,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -539,7 +511,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", "SampleAfterValue": "2000003", "UMask": "0x2" @@ -548,7 +519,6 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -558,7 +528,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PEBS": "1", "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8" @@ -789,6 +758,15 @@ "UMask": "0x20" }, { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json index e0a45d4ea848..53055986534d 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json @@ -10,6 +10,16 @@ "Unit": "CHACMS" }, { + "BriefDescription": "Counts the number of cycles FAST trigger is received from the global FAST distress wire.", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_CHACMS_RING_SRC_THRTL", + "Experimental": "1", + "PerPkg": "1", + "PortMask": "0x000", + "Unit": "CHACMS" + }, + { "BriefDescription": "Number of CHA clock cycles while the event is enabled", "Counter": "0,1,2,3", "EventCode": "0x01", @@ -844,6 +854,16 @@ "Unit": "CHA" }, { + "BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "Counter": "0", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { "BriefDescription": "All TOR Inserts", "Counter": "0,1,2,3", "EventCode": "0x35", @@ -1056,7 +1076,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Code read from local IA that miss the cache", + "BriefDescription": "Code read from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", @@ -1076,7 +1096,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read from local IA that miss the cache", + "BriefDescription": "Data read from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD", @@ -1096,7 +1116,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read prefetch from local IA that miss the cache", + "BriefDescription": "Data read prefetch from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF", @@ -1276,7 +1296,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Last level cache prefetch read for ownership from local IA that miss the cache", + "BriefDescription": "Last level cache prefetch read for ownership from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", @@ -1405,7 +1425,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read from local IA that miss the cache", + "BriefDescription": "Data read from local IA that miss the cache and targets local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL", @@ -1476,7 +1496,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read prefetch from local IA that miss the cache", + "BriefDescription": "Data read prefetch from local IA that miss the cache and targets local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL", @@ -1518,7 +1538,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read prefetch from local IA that miss the cache", + "BriefDescription": "Data read prefetch from local IA that miss the cache and targets remote memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE", @@ -1549,7 +1569,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read from local IA that miss the cache", + "BriefDescription": "Data read from local IA that miss the cache and targets remote memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE", @@ -1741,7 +1761,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA that miss the LLC targeting local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", @@ -1770,7 +1790,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", @@ -1780,7 +1800,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting remote memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", @@ -1790,7 +1810,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA that miss the LLC targeting remote memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", @@ -1882,7 +1902,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", @@ -1892,7 +1912,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cxl.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cxl.json index 383a5ba5a697..43e094c233cc 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cxl.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-cxl.json @@ -13,7 +13,6 @@ "Counter": "4,5,6,7", "EventCode": "0x41", "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_DATA", - "Experimental": "1", "PerPkg": "1", "UMask": "0x10", "Unit": "CXLCM" @@ -23,7 +22,6 @@ "Counter": "0,1,2,3", "EventCode": "0x02", "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_DATA", - "Experimental": "1", "PerPkg": "1", "UMask": "0x20", "Unit": "CXLDP" diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json index 856ee985ecd4..5c50275c79b0 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json @@ -809,6 +809,26 @@ "Unit": "IRP" }, { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "Counter": "0,1,2,3", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REJ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "Counter": "0,1,2,3", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { "BriefDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", "Counter": "0,1,2,3", "EventCode": "0x1F", @@ -819,6 +839,46 @@ "Unit": "IRP" }, { + "BriefDescription": "Snoop Hit E/S responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Hit I responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Hit M responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop miss responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x71", + "Unit": "IRP" + }, + { "BriefDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", "Counter": "0,1,2,3", "EventCode": "0x11", @@ -1551,6 +1611,33 @@ "Unit": "UPI" }, { + "BriefDescription": "Cycles in L0p", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "Experimental": "1", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "Experimental": "1", + "PerPkg": "1", + "Unit": "UPI" + }, + { "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", "Counter": "0,1,2,3", "EventCode": "0x04", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json index cffb9d94b53d..886b99a971be 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json @@ -17,7 +17,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -29,7 +29,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -41,7 +41,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -53,7 +53,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -65,7 +65,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -77,7 +77,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -89,7 +89,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -101,7 +101,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -113,7 +113,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -125,7 +125,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff0ff", + "UMask": "0xff", "Unit": "IIO" }, { @@ -137,7 +137,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -149,7 +149,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -161,7 +161,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -173,7 +173,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -185,7 +185,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -197,7 +197,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -209,7 +209,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -221,7 +221,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -233,7 +233,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -245,7 +245,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -257,7 +257,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -269,7 +269,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -281,7 +281,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -293,7 +293,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -305,7 +305,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -317,7 +317,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -329,7 +329,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -341,7 +341,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -352,7 +352,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -363,7 +363,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -374,7 +374,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -385,7 +385,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -396,7 +396,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -407,7 +407,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -418,7 +418,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -429,7 +429,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -440,7 +440,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -451,7 +451,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -462,7 +462,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -473,7 +473,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -484,7 +484,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -495,7 +495,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -506,7 +506,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -517,7 +517,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x10", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -528,7 +528,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x20", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -539,7 +539,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x40", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -550,7 +550,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x80", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -561,7 +561,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -572,7 +572,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -583,7 +583,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -594,7 +594,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -605,7 +605,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -616,7 +616,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x10", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -627,7 +627,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x20", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -638,7 +638,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x40", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -649,7 +649,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x80", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -661,7 +661,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -673,7 +673,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -685,7 +685,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -697,7 +697,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -709,7 +709,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -721,7 +721,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -733,7 +733,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -745,7 +745,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -757,7 +757,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -769,7 +769,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -781,7 +781,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -793,7 +793,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -805,7 +805,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -817,7 +817,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -829,7 +829,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -841,7 +841,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -853,7 +853,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1129,7 +1129,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1141,7 +1141,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1153,7 +1153,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1165,7 +1165,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1177,7 +1177,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1189,7 +1189,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1201,7 +1201,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1213,7 +1213,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -1225,7 +1225,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -1237,7 +1237,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1249,7 +1249,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1261,7 +1261,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1273,7 +1273,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1285,7 +1285,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1297,7 +1297,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1318,7 +1318,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1329,7 +1329,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1340,7 +1340,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1351,7 +1351,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1362,7 +1362,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1373,7 +1373,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1384,7 +1384,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1395,7 +1395,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1406,7 +1406,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1417,7 +1417,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1428,7 +1428,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1439,7 +1439,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1450,7 +1450,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1461,7 +1461,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1472,7 +1472,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1483,7 +1483,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1494,7 +1494,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1505,7 +1505,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1516,7 +1516,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1527,7 +1527,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1538,7 +1538,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1549,7 +1549,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1560,7 +1560,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1571,7 +1571,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1582,7 +1582,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1593,7 +1593,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1604,7 +1604,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1615,7 +1615,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1626,7 +1626,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1637,7 +1637,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1648,7 +1648,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1659,7 +1659,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1670,7 +1670,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1681,7 +1681,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1692,7 +1692,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1703,7 +1703,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1715,7 +1715,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1727,7 +1727,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1739,7 +1739,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1751,7 +1751,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1763,7 +1763,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1775,7 +1775,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1787,7 +1787,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1799,7 +1799,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1811,7 +1811,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1823,7 +1823,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1835,7 +1835,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1847,7 +1847,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1859,7 +1859,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1871,7 +1871,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1883,7 +1883,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1895,7 +1895,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" } ] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json index 08e410b9b0a2..5f4783ff6ce5 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json @@ -169,7 +169,7 @@ "Unit": "IMC" }, { - "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled", + "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled. DCLK is 1/4 of DRAM data rate.", "Counter": "0,1,2,3", "EventCode": "0x01", "EventName": "UNC_M_CLOCKTICKS", @@ -189,6 +189,104 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x10", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x20", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x40", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x80", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode and all pages are closed", + "Counter": "0,1,2,3", + "EventCode": "0x88", + "EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "Unit": "IMC" + }, + { "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", "Counter": "0,1,2,3", "EventCode": "0x03", @@ -359,6 +457,28 @@ "Unit": "IMC" }, { + "BriefDescription": "subevent0 - # of cycles all ranks were in SR subevent1 - # of times all ranks went into SR subevent2 -# of times ps_sr_active asserted (SRE) subevent3 - # of times ps_sr_active deasserted (SRX) subevent4 - # of times PS-&>Refresh ps_sr_req asserted (SRE) subevent5 - # of times PS-&>Refresh ps_sr_req deasserted (SRX) subevent6 - # of cycles PSCtrlr FSM was in FATAL", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles all ranks were in SR", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { "BriefDescription": "Write Pending Queue Allocations", "Counter": "0,1,2,3", "EventCode": "0x22", diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-power.json b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-power.json index 02e59f64a544..9ea852ef190e 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/uncore-power.json @@ -7,5 +7,103 @@ "PerPkg": "1", "PublicDescription": "PCU Clockticks: The PCU runs off a fixed 1 GHz clock. This event counts the number of pclk cycles measured while the counter was enabled. The pclk, like the Memory Controller's dclk, counts at a constant rate making it a good measure of actual wall time.", "Unit": "PCU" + }, + { + "BriefDescription": "Thermal Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x04", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Thermal Strongest Upper Limit Cycles : Number of cycles any frequency is reduced due to a thermal limit. Count only if throttling is occurring.", + "Unit": "PCU" + }, + { + "BriefDescription": "Power Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Power Strongest Upper Limit Cycles : Counts the number of cycles when power is the upper limit on frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Cycles spent changing Frequency : Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C2E", + "Counter": "0,1,2,3", + "EventCode": "0x2b", + "EventName": "UNC_P_PKG_RESIDENCY_C2E_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C2E : Counts the number of cycles when the package was in C2E. This event can be used in conjunction with edge detect to count C2E entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C6", + "Counter": "0,1,2,3", + "EventCode": "0x2d", + "EventName": "UNC_P_PKG_RESIDENCY_C6_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C6 : Counts the number of cycles when the package was in C6. This event can be used in conjunction with edge detect to count C6 entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C0", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0", + "PerPkg": "1", + "PublicDescription": "Number of cores in C0 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C3", + "Counter": "0,1,2,3", + "EventCode": "0x36", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Number of cores in C3 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C6", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6", + "PerPkg": "1", + "PublicDescription": "Number of cores in C6 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "External Prochot", + "Counter": "0,1,2,3", + "EventCode": "0x0a", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "External Prochot : Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" + }, + { + "BriefDescription": "Internal Prochot", + "Counter": "0,1,2,3", + "EventCode": "0x09", + "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Internal Prochot : Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index b693c0b0cafe..0c1040b7e38c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -74,12 +74,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -92,8 +92,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", "ScaleUnit": "100%" }, { @@ -104,7 +104,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", "ScaleUnit": "100%" }, { @@ -114,7 +114,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { @@ -125,7 +125,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -133,8 +133,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -143,18 +143,18 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -165,7 +165,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { @@ -174,8 +174,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -183,7 +183,7 @@ "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, @@ -193,8 +193,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -203,7 +203,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -211,7 +211,7 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -220,8 +220,8 @@ "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { @@ -229,27 +229,27 @@ "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", "ScaleUnit": "100%" }, { @@ -279,33 +279,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -316,7 +316,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -328,7 +328,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -347,7 +347,13 @@ "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -392,7 +398,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -415,7 +421,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -427,7 +433,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -445,7 +451,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -464,7 +470,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -496,14 +502,14 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -521,7 +527,7 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" @@ -531,13 +537,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -547,6 +554,19 @@ "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -559,13 +579,20 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -574,7 +601,8 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -600,24 +628,24 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -625,8 +653,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -635,8 +663,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { @@ -645,8 +673,8 @@ "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -654,18 +682,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -682,10 +710,10 @@ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -696,15 +724,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -713,19 +741,19 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { @@ -734,7 +762,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -743,7 +771,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", "ScaleUnit": "100%" }, { @@ -751,8 +779,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", "ScaleUnit": "100%" }, { @@ -761,7 +789,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -770,7 +798,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -806,7 +834,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -815,7 +843,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -830,46 +858,46 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -888,8 +916,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -897,16 +925,16 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -915,8 +943,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -924,18 +952,18 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json index edb1b5b9f553..a76f1862e5ea 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json @@ -412,7 +412,7 @@ "Counter": "0,1,2,3", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "2", + "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x4" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json b/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json index 4193c90c3459..0863375bdead 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -34,6 +35,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -51,6 +53,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -78,6 +81,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -103,6 +107,7 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 8f2ba3391e35..1a05b74be575 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -55,7 +55,7 @@ "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -76,24 +76,24 @@ "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" @@ -102,14 +102,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -209,13 +209,13 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -276,12 +276,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", @@ -294,8 +294,8 @@ "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST", "ScaleUnit": "100%" }, { @@ -306,7 +306,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", "ScaleUnit": "100%" }, { @@ -316,7 +316,7 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { @@ -327,7 +327,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { @@ -335,8 +335,8 @@ "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -345,18 +345,18 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -367,7 +367,7 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { @@ -376,8 +376,8 @@ "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -385,7 +385,7 @@ "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, @@ -395,8 +395,8 @@ "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -405,7 +405,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -413,7 +413,7 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -422,8 +422,8 @@ "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { @@ -431,27 +431,27 @@ "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", "ScaleUnit": "100%" }, { @@ -481,33 +481,33 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -518,7 +518,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -530,7 +530,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@))", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -549,7 +549,13 @@ "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -594,7 +600,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -617,7 +623,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -629,7 +635,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -647,7 +653,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -666,7 +672,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -698,14 +704,14 @@ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -723,7 +729,7 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" @@ -733,13 +739,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -750,19 +757,32 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -775,6 +795,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -782,12 +809,12 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -796,7 +823,8 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -822,24 +850,24 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { @@ -847,8 +875,8 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -857,8 +885,8 @@ "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { @@ -867,8 +895,8 @@ "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -876,18 +904,18 @@ "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -905,18 +933,18 @@ "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { @@ -927,15 +955,15 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, @@ -944,19 +972,19 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { @@ -965,7 +993,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -974,7 +1002,7 @@ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck", "ScaleUnit": "100%" }, { @@ -982,8 +1010,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer", "ScaleUnit": "100%" }, { @@ -992,7 +1020,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1001,7 +1029,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1037,7 +1065,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1046,7 +1074,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1061,46 +1089,46 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1109,8 +1137,8 @@ "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -1118,8 +1146,8 @@ "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM", "ScaleUnit": "100%" }, { @@ -1138,8 +1166,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1147,16 +1175,16 @@ "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, @@ -1165,8 +1193,8 @@ "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1174,18 +1202,18 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json b/tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json index 4193c90c3459..0863375bdead 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json @@ -9,6 +9,7 @@ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -34,6 +35,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -51,6 +53,7 @@ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -78,6 +81,7 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -103,6 +107,7 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json index 3c23bafcba28..d664af16c1db 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json @@ -812,7 +812,7 @@ "EventCode": "0x12", "EventName": "UNC_C_RxR_EXT_STARVED.IPQ", "PerPkg": "1", - "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", + "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally starved and therefore we are blocking the IRQ.", "UMask": "0x2", "Unit": "CBOX" }, @@ -1869,7 +1869,7 @@ "EventCode": "0x14", "EventName": "UNC_H_BYPASS_IMC.NOT_TAKEN", "PerPkg": "1", - "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.", "UMask": "0x2", "Unit": "HA" }, @@ -1879,7 +1879,7 @@ "EventCode": "0x14", "EventName": "UNC_H_BYPASS_IMC.TAKEN", "PerPkg": "1", - "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.", "UMask": "0x1", "Unit": "HA" }, @@ -2874,7 +2874,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN0", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", "UMask": "0x1", "Unit": "HA" }, @@ -2884,7 +2884,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN1", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", "UMask": "0x2", "Unit": "HA" }, @@ -2894,7 +2894,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN2", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", "UMask": "0x4", "Unit": "HA" }, @@ -2904,7 +2904,7 @@ "EventCode": "0x15", "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN3", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", "UMask": "0x8", "Unit": "HA" }, @@ -3438,7 +3438,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; Requests coming from both local and remote sockets.", "UMask": "0x3", "Unit": "HA" }, @@ -3448,7 +3448,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from the local socket.", "UMask": "0x1", "Unit": "HA" }, @@ -3458,7 +3458,7 @@ "EventCode": "0x3", "EventName": "UNC_H_TRACKER_CYCLES_NE.REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occupancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.; This filter includes only requests coming from remote sockets.", "UMask": "0x2", "Unit": "HA" }, @@ -3878,7 +3878,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN0", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", "UMask": "0x1", "Unit": "HA" }, @@ -3888,7 +3888,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN1", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", "UMask": "0x2", "Unit": "HA" }, @@ -3898,7 +3898,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN2", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", "UMask": "0x4", "Unit": "HA" }, @@ -3908,7 +3908,7 @@ "EventCode": "0x18", "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN3", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high bandwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", "UMask": "0x8", "Unit": "HA" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json index 121de411d312..8f73a8649b39 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json @@ -1,25 +1,5 @@ [ { - "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", - "Counter": "0,1,2,3", - "EventName": "QPI_CTL_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", - "ScaleUnit": "8Bytes", - "UMask": "0x4", - "Unit": "QPI" - }, - { - "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", - "Counter": "0,1,2,3", - "EventName": "QPI_DATA_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", - "ScaleUnit": "8Bytes", - "UMask": "0x2", - "Unit": "QPI" - }, - { "BriefDescription": "Total Write Cache Occupancy; Any Source", "Counter": "0,1", "EventCode": "0x12", @@ -53,7 +33,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x80", "Unit": "IRP" }, @@ -63,7 +43,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x2", "Unit": "IRP" }, @@ -73,7 +53,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.DRD", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x4", "Unit": "IRP" }, @@ -83,7 +63,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x20", "Unit": "IRP" }, @@ -93,7 +73,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x1", "Unit": "IRP" }, @@ -103,7 +83,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.PCITOM", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x10", "Unit": "IRP" }, @@ -113,7 +93,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.RFO", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x8", "Unit": "IRP" }, @@ -123,7 +103,7 @@ "EventCode": "0x13", "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "PublicDescription": "Counts the number of coherency related operations serviced by the IRP", "UMask": "0x40", "Unit": "IRP" }, @@ -493,7 +473,7 @@ "EventCode": "0x16", "EventName": "UNC_I_TRANSACTIONS.WRITES", "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", "UMask": "0x2", "Unit": "IRP" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/cache.json b/tools/perf/pmu-events/arch/x86/icelake/cache.json index 3508340acd0e..015f70f157d1 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/cache.json +++ b/tools/perf/pmu-events/arch/x86/icelake/cache.json @@ -75,11 +75,11 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -251,7 +251,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81" @@ -262,7 +261,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82" @@ -273,7 +271,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83" @@ -284,7 +281,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21" @@ -295,7 +291,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41" @@ -306,7 +301,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42" @@ -317,7 +311,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11" @@ -328,7 +321,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12" @@ -339,7 +331,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2" @@ -350,7 +341,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4" @@ -361,7 +351,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -372,7 +361,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" @@ -383,7 +371,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4" @@ -394,7 +381,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -405,7 +391,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -416,7 +401,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8" @@ -427,7 +411,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2" @@ -438,7 +421,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10" @@ -449,7 +431,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4" @@ -460,7 +441,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -911,6 +891,16 @@ "UMask": "0x8" }, { + "BriefDescription": "Cycles with outstanding code read requests pending.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Cycles with outstanding code read requests pending. Code Read requests include both cacheable and non-cacheable Code Reads. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { "BriefDescription": "Cycles where at least 1 outstanding Demand RFO request is pending.", "Counter": "0,1,2,3", "CounterMask": "1", diff --git a/tools/perf/pmu-events/arch/x86/icelake/frontend.json b/tools/perf/pmu-events/arch/x86/icelake/frontend.json index e7c7d4d4152d..7afa2436d584 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/icelake/frontend.json @@ -44,7 +44,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -56,7 +55,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -68,7 +66,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -80,7 +77,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -92,7 +88,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -104,7 +99,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x500106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -116,7 +110,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x508006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -128,7 +121,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x501006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -140,7 +132,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x500206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -152,7 +143,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x510006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -164,7 +154,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -176,7 +165,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x502006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -188,7 +176,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x500406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -200,7 +187,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x520006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -212,7 +198,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x504006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -224,7 +209,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x500806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -236,7 +220,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index 9085ea60f516..63e28a03dc60 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -89,12 +89,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -106,7 +106,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -129,11 +129,104 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -147,7 +240,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -155,8 +248,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -164,8 +257,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -173,18 +266,66 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(29 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((32.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -194,25 +335,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -221,7 +362,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -231,8 +372,8 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -241,7 +382,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -249,44 +390,44 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "32.5 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -296,7 +437,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -306,16 +447,16 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -324,7 +465,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -333,7 +474,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -341,7 +490,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -350,7 +499,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -359,8 +508,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -368,8 +517,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -377,7 +526,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -389,17 +538,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -407,41 +556,41 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 5 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -455,34 +604,13 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" }, { "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "tma_info_botlnk_l0_core_bound_likely", - "MetricGroup": "Cor;Metric;SMT", - "MetricName": "tma_info_botlnk_core_bound_likely", - "MetricThreshold": "tma_info_botlnk_core_bound_likely > 0.5" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd))", - "MetricGroup": "DSBmiss;Fed;Scaled_Slots;tma_issueFB", - "MetricName": "tma_info_botlnk_dsb_misses", - "MetricThreshold": "tma_info_botlnk_dsb_misses > 10" - }, - { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;Scaled_Slots;tma_issueFL", - "MetricName": "tma_info_botlnk_ic_misses", - "MetricThreshold": "tma_info_botlnk_ic_misses > 5" - }, - { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", "MetricGroup": "Cor;SMT", @@ -491,8 +619,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" @@ -500,7 +628,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -509,108 +637,10 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -671,11 +701,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -688,20 +718,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -737,7 +767,13 @@ "MetricName": "tma_info_frontend_lsd_coverage" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -755,7 +791,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -763,7 +799,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -771,7 +807,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -779,7 +815,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -787,7 +823,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -795,7 +831,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -840,7 +876,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -850,22 +886,10 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "\"Bus lock\" per kilo instruction", - "MetricExpr": "tma_info_memory_mix_bus_lock_pki", - "MetricGroup": "Mem;Metric", - "MetricName": "tma_info_memory_bus_lock_pki" - }, - { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "tma_info_memory_tlb_code_stlb_mpki", - "MetricGroup": "Fed;MemoryTLB;Metric", - "MetricName": "tma_info_memory_code_stlb_mpki" - }, - { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "tma_info_memory_l1d_cache_fill_bw", "MetricGroup": "Mem;MemoryBW", @@ -890,12 +914,6 @@ "MetricName": "tma_info_memory_core_l3_cache_fill_bw_2t" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "tma_info_memory_latency_data_l2_mlp", - "MetricGroup": "Memory_BW;Metric;Offcore", - "MetricName": "tma_info_memory_data_l2_mlp" - }, - { "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheHits;Mem", @@ -903,17 +921,11 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_memory_l1d_cache_fill_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW", - "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t" - }, - { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheHits;Mem", @@ -927,17 +939,11 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_memory_l2_cache_fill_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW", - "MetricName": "tma_info_memory_l2_cache_fill_bw_2t" - }, - { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheHits;Mem", @@ -969,29 +975,17 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_memory_l3_cache_access_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW;Offcore", - "MetricName": "tma_info_memory_l3_cache_access_bw_2t" - }, - { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_memory_l3_cache_fill_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW", - "MetricName": "tma_info_memory_l3_cache_fill_bw_2t" - }, - { "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", "MetricGroup": "Mem", @@ -1005,53 +999,23 @@ }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", - "MetricExpr": "tma_info_memory_load_l2_miss_latency", - "MetricGroup": "Memory_Lat;Offcore", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, { - "BriefDescription": "Average Latency for L3 cache miss demand Loads", - "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_memory_latency_load_l3_miss_latency" - }, - { - "BriefDescription": "Average Latency for L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Clocks_Latency;Memory_Lat;Offcore", - "MetricName": "tma_info_memory_load_l2_miss_latency" - }, - { - "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", - "MetricGroup": "Memory_BW;Metric;Offcore", - "MetricName": "tma_info_memory_load_l2_mlp" - }, - { - "BriefDescription": "Average Latency for L3 cache miss demand Loads", - "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x0@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "MetricGroup": "Clocks_Latency;Memory_Lat;Offcore", - "MetricName": "tma_info_memory_load_l3_miss_latency" - }, - { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", "MetricGroup": "Mem;MemoryBound;MemoryLat", "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "tma_info_memory_tlb_load_stlb_mpki", - "MetricGroup": "Mem;MemoryTLB;Metric", - "MetricName": "tma_info_memory_load_stlb_mpki" - }, - { "BriefDescription": "\"Bus lock\" per kilo instruction", "MetricExpr": "1e3 * SQ_MISC.BUS_LOCK / INST_RETIRED.ANY", "MetricGroup": "Mem", @@ -1059,7 +1023,7 @@ }, { "BriefDescription": "Un-cacheable retired load per kilo instruction", - "MetricExpr": "tma_info_memory_uc_load_pki", + "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY", "MetricGroup": "Mem", "MetricName": "tma_info_memory_mix_uc_load_pki" }, @@ -1071,17 +1035,11 @@ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "tma_info_memory_tlb_page_walks_utilization", - "MetricGroup": "Core_Metric;Mem;MemoryTLB", - "MetricName": "tma_info_memory_page_walks_utilization", - "MetricThreshold": "tma_info_memory_page_walks_utilization > 0.5" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "tma_info_memory_tlb_store_stlb_mpki", - "MetricGroup": "Mem;MemoryTLB;Metric", - "MetricName": "tma_info_memory_store_stlb_mpki" + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15" }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1109,14 +1067,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Un-cacheable retired load per kilo instruction", - "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY", - "MetricGroup": "Mem;Metric", - "MetricName": "tma_info_memory_uc_load_pki" - }, - { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1143,18 +1095,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1172,14 +1124,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -1189,13 +1141,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1205,11 +1158,24 @@ "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1217,7 +1183,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1225,7 +1191,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1240,13 +1206,20 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1255,14 +1228,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1272,13 +1246,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1294,33 +1268,41 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 7.5" + "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1329,8 +1311,17 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1339,17 +1330,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "9 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(12.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1357,18 +1348,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1385,7 +1376,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1393,16 +1384,40 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1412,7 +1427,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", "ScaleUnit": "100%" }, { @@ -1422,16 +1437,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1439,8 +1454,8 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1450,11 +1465,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1468,7 +1483,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1476,8 +1491,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1491,19 +1506,27 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { @@ -1511,8 +1534,8 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1520,7 +1543,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1535,19 +1558,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1583,7 +1606,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1591,8 +1614,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { @@ -1600,8 +1623,8 @@ "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1609,7 +1632,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1618,7 +1641,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1627,14 +1650,14 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1647,7 +1670,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1656,7 +1679,7 @@ "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -1665,8 +1688,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1675,17 +1698,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1693,8 +1716,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1703,17 +1726,17 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1730,7 +1753,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1738,7 +1761,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1746,7 +1793,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -1755,7 +1802,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1764,8 +1811,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/icelake/memory.json b/tools/perf/pmu-events/arch/x86/icelake/memory.json index f73035f44330..abaf3f4f9d63 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/memory.json +++ b/tools/perf/pmu-events/arch/x86/icelake/memory.json @@ -88,7 +88,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1" @@ -101,7 +100,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -114,7 +112,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1" @@ -127,7 +124,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -140,7 +136,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1" @@ -153,7 +148,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1" @@ -166,7 +160,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1" @@ -179,7 +172,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -287,17 +279,16 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4" }, { - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/metricgroups.json b/tools/perf/pmu-events/arch/x86/icelake/metricgroups.json index 3a88260194d1..80ca8021f2de 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/icelake/metricgroups.json @@ -37,6 +37,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -83,7 +84,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -93,6 +96,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_issue2P": "Metrics related by the issue $issue2P", "tma_issueBM": "Metrics related by the issue $issueBM", "tma_issueBW": "Metrics related by the issue $issueBW", @@ -112,10 +116,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -128,5 +135,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/icelake/pipeline.json b/tools/perf/pmu-events/arch/x86/icelake/pipeline.json index 4fdf07c7beb7..44659f26cbab 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/icelake/pipeline.json @@ -10,6 +10,15 @@ "UMask": "0x9" }, { + "BriefDescription": "ARITH.FP_DIVIDER_ACTIVE", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", @@ -23,7 +32,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009" }, @@ -32,7 +40,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -42,7 +49,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -52,7 +58,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -62,7 +67,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -72,7 +76,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -82,7 +85,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" @@ -92,7 +94,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -102,7 +103,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -112,7 +112,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "50021" }, @@ -121,7 +120,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x11" @@ -131,7 +129,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "50021", "UMask": "0x10" @@ -141,7 +138,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -151,7 +147,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", "SampleAfterValue": "50021", "UMask": "0x80" @@ -161,7 +156,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "50021", "UMask": "0x2" @@ -171,7 +165,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -181,7 +174,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "50021", "UMask": "0x8" @@ -377,7 +369,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -387,7 +378,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003" }, @@ -396,7 +386,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -404,7 +393,6 @@ "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json index 909a73d7f2d3..bee503eda18c 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json @@ -9,71 +9,6 @@ "Unit": "ARB" }, { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_IFA_OCCUPANCY.ALL", - "Counter": "0", - "Deprecated": "1", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated.", - "Counter": "0", - "Deprecated": "1", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_TRK_OCCUPANCY.RD", - "Counter": "0", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", - "Counter": "1", - "EventCode": "0x81", - "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated.", - "Counter": "0", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_OCCUPANCY.DRD", - "Counter": "0", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", "Counter": "1", "EventCode": "0x81", @@ -81,16 +16,5 @@ "PerPkg": "1", "UMask": "0x1", "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", - "Counter": "0,1", - "Deprecated": "1", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.RD", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" } ] diff --git a/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json index cc8110ac020c..1ac5b5ef8094 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", "Counter": "FIXED", "EventCode": "0xff", "EventName": "UNC_CLOCK.SOCKET", diff --git a/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json index 3ff51040f84f..9df790d4361f 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json @@ -28,6 +28,15 @@ "UMask": "0xe" }, { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "Counter": "0,1,2,3", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", "Counter": "0,1,2,3", "EventCode": "0x08", @@ -83,6 +92,15 @@ "UMask": "0xe" }, { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "Counter": "0,1,2,3", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", "Counter": "0,1,2,3", "EventCode": "0x49", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/cache.json b/tools/perf/pmu-events/arch/x86/icelakex/cache.json index 0cbb9d6a3ec1..e8ab6ef2cd50 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/cache.json @@ -75,15 +75,24 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3", + "EventCode": "0xf2", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { "BriefDescription": "L2 code requests", "Counter": "0,1,2,3", "EventCode": "0x24", @@ -224,7 +233,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81" @@ -235,7 +243,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82" @@ -246,7 +253,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83" @@ -257,7 +263,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21" @@ -268,7 +273,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41" @@ -279,7 +283,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42" @@ -290,7 +293,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11" @@ -301,7 +303,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12" @@ -312,7 +313,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4" @@ -324,7 +324,6 @@ "Deprecated": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "PEBS": "1", "SampleAfterValue": "20011", "UMask": "0x2" }, @@ -335,7 +334,6 @@ "Deprecated": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PEBS": "1", "SampleAfterValue": "20011", "UMask": "0x4" }, @@ -345,7 +343,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -356,7 +353,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" @@ -367,7 +363,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2" @@ -378,7 +373,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PEBS": "1", "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -389,7 +383,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x2" }, @@ -399,7 +392,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "PEBS": "1", "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -410,7 +402,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", - "PEBS": "1", "PublicDescription": "Retired load instructions whose data sources was remote HITM.", "SampleAfterValue": "100007", "UMask": "0x4" @@ -421,7 +412,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3 (AppDirect or Memory Mode) and DRAM cache(Memory Mode).", "SampleAfterValue": "100007", "UMask": "0x10" @@ -432,7 +422,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4" @@ -443,7 +432,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -454,7 +442,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -465,7 +452,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8" @@ -476,7 +462,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2" @@ -487,7 +472,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10" @@ -498,7 +482,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4" @@ -509,7 +492,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -520,7 +502,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.LOCAL_PMM", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3 (AppDirect or Memory Mode) and DRAM cache(Memory Mode).", "SampleAfterValue": "100003", "UMask": "0x80" diff --git a/tools/perf/pmu-events/arch/x86/icelakex/frontend.json b/tools/perf/pmu-events/arch/x86/icelakex/frontend.json index d79ddc15b220..3b1bdcfaa276 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/frontend.json @@ -44,7 +44,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -56,7 +55,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -68,7 +66,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -80,7 +77,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -92,7 +88,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -104,7 +99,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x500106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -116,7 +110,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x508006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -128,7 +121,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x501006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -140,7 +132,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x500206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -152,7 +143,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x510006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -164,7 +154,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -176,7 +165,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x502006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -188,7 +176,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x500406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -200,7 +187,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x520006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -212,7 +198,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x504006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -224,7 +209,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x500806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -236,7 +220,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index db5510ba9099..7bee03e532e4 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -34,7 +34,7 @@ "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -55,49 +55,55 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR + UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_remote", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_remote", "ScaleUnit": "1MB/s" @@ -106,14 +112,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -165,6 +171,12 @@ "ScaleUnit": "1per_instr" }, { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA + UNC_CHA_TOR_INSERTS.IA_MISS_DRD + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF) / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages)) * duration_time", "MetricName": "llc_demand_data_read_miss_latency", @@ -183,31 +195,37 @@ "ScaleUnit": "1ns" }, { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to DRAM in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_to_dram_latency", + "ScaleUnit": "1ns" + }, + { "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages)) * duration_time", "MetricName": "llc_demand_data_read_miss_to_pmem_latency", "ScaleUnit": "1ns" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_write", "ScaleUnit": "1MB/s" @@ -237,19 +255,19 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM).", + "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM)", "MetricExpr": "(UNC_CHA_DIR_UPDATE.HA + UNC_CHA_DIR_UPDATE.TOR + UNC_M2M_DIRECTORY_UPDATE.ANY) * 64 / 1e6 / duration_time", "MetricName": "memory_extra_write_bw_due_to_directory_updates", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -317,12 +335,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -334,7 +352,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -357,11 +375,104 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -375,7 +486,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -383,8 +494,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -392,8 +503,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -401,18 +512,66 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 43.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((48 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -422,25 +581,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43.5 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(47.5 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -449,18 +608,18 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound)", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -469,7 +628,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -477,44 +636,44 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "48 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricExpr": "(120 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 48 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -524,7 +683,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -534,16 +693,16 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -552,7 +711,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -561,7 +720,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -569,7 +736,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -578,7 +745,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -587,8 +754,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -596,8 +763,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -605,7 +772,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -617,17 +784,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -635,41 +802,41 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 5 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -683,7 +850,7 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" @@ -698,8 +865,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" @@ -707,7 +874,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -716,108 +883,10 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -878,11 +947,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -895,20 +964,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -938,7 +1007,13 @@ "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -956,7 +1031,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -964,7 +1039,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -972,7 +1047,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -980,7 +1055,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -988,7 +1063,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -996,7 +1071,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1041,7 +1116,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -1051,7 +1126,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1098,7 +1173,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -1116,7 +1191,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -1152,13 +1227,13 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -1177,22 +1252,16 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, { - "BriefDescription": "Average Latency for L3 cache miss demand Loads", - "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_memory_latency_load_l3_miss_latency" - }, - { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", "MetricGroup": "Mem;MemoryBound;MemoryLat", @@ -1218,6 +1287,13 @@ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15" + }, + { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Fed;MemoryTLB", @@ -1244,7 +1320,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1265,18 +1341,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1294,28 +1370,28 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_read_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e9 / duration_time", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_write_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU" @@ -1325,13 +1401,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1348,44 +1425,45 @@ "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { + "BriefDescription": "Fraction of Uncore cycles where requests got rejected due to duplicate address already in IRQ ingress queue in the cache homing agent", + "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS", + "MetricGroup": "LockCont;MemOffcore;Server;SoC", + "MetricName": "tma_info_system_mem_irq_duplicate_address", + "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)" + }, + { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", - "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@event\\=0x0@ if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", - "MetricName": "tma_info_system_mem_pmm_read_latency", - "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" - }, - { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_read_bw" + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_write_bw" + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1393,7 +1471,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1401,7 +1479,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1416,6 +1494,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -1423,12 +1508,12 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1437,14 +1522,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1454,13 +1540,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1476,33 +1562,41 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 7.5" + "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1511,8 +1605,17 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1521,17 +1624,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "19 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(23 * tma_info_system_core_frequency - 4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1539,18 +1642,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1567,7 +1670,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1575,15 +1678,39 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "43.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(66.5 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, @@ -1591,9 +1718,9 @@ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1604,16 +1731,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1621,8 +1748,8 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1632,11 +1759,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1650,7 +1777,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1658,8 +1785,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1673,19 +1800,27 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { @@ -1693,8 +1828,8 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1702,7 +1837,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1717,28 +1852,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", - "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_pmm_bound", - "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1774,7 +1900,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1782,8 +1908,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { @@ -1791,8 +1917,8 @@ "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1800,7 +1926,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1809,7 +1935,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1818,32 +1944,32 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "(97 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 97 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "((120 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (120 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "108 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(131 * tma_info_system_core_frequency - 23 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1856,7 +1982,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1865,7 +1991,7 @@ "MetricExpr": "37 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -1874,8 +2000,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1884,17 +2010,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1902,8 +2028,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1912,17 +2038,17 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1939,7 +2065,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1947,7 +2073,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1955,7 +2105,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -1964,7 +2114,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1973,8 +2123,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/icelakex/memory.json b/tools/perf/pmu-events/arch/x86/icelakex/memory.json index 32a3dedb82fb..ec9577cce3ac 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/memory.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/memory.json @@ -25,7 +25,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1" @@ -38,7 +37,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -51,7 +49,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1" @@ -64,7 +61,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -77,7 +73,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1" @@ -90,7 +85,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1" @@ -103,7 +97,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1" @@ -116,7 +109,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -353,17 +345,16 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4" }, { - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json b/tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json index cccfcab3425e..4a28187c2896 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json @@ -38,6 +38,7 @@ "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -84,7 +85,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -94,6 +97,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_issue2P": "Metrics related by the issue $issue2P", "tma_issueBM": "Metrics related by the issue $issueBM", "tma_issueBW": "Metrics related by the issue $issueBW", @@ -113,10 +117,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -129,5 +136,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json index 74285b6c81e7..f1446f1b67c6 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json @@ -10,6 +10,15 @@ "UMask": "0x9" }, { + "BriefDescription": "ARITH.FP_DIVIDER_ACTIVE", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", @@ -23,7 +32,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009" }, @@ -32,7 +40,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -42,7 +49,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -52,7 +58,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -62,7 +67,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -72,7 +76,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -82,7 +85,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" @@ -92,7 +94,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -102,7 +103,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -112,7 +112,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "50021" }, @@ -121,7 +120,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x11" @@ -131,7 +129,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "50021", "UMask": "0x10" @@ -141,7 +138,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -151,7 +147,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", "SampleAfterValue": "50021", "UMask": "0x80" @@ -161,7 +156,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) calls, including both register and memory indirect.", "SampleAfterValue": "50021", "UMask": "0x2" @@ -171,7 +165,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -181,7 +174,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "50021", "UMask": "0x8" @@ -377,7 +369,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -387,7 +378,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003" }, @@ -396,7 +386,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -404,7 +393,6 @@ "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json index 759714618e08..15fb9921f4fc 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json @@ -1,5 +1,256 @@ [ { + "BriefDescription": "Counts the number of request that were not accepted into the L2Q because the L2Q is FULL.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x31", + "EventName": "CORE_REJECT_L2Q.ANY", + "PublicDescription": "Counts the number of (demand and L1 prefetchers) core requests rejected by the L2Q due to a full or nearly full w condition which likely indicates back pressure from L2Q. It also counts requests that would have gone directly to the XQ, but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link. The L2Q may also reject transactions from a core to insure fairness between cores, or to delay a cores dirty eviction when the address conflicts incoming external snoops. (Note that L2 prefetcher requests that are dropped are not counted by this event.)", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "DL1.DIRTY_EVICTION", + "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches. Does not count evictions or dirty writebacks caused by snoops. Does not count a replacement unless a (dirty) line was written back.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines replaced in L0 data cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.L0_REPLACEMENT", + "PublicDescription": "Counts L0 data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts cachelines replaced into the L0 and L1 d-cache.", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.FB_FULL", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.L2_STALLS", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of demand requests that missed L1D cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x49", + "EventName": "L1D_MISS.LOAD", + "PublicDescription": "Count occurrences (rising-edge) of DCACHE_PENDING sub-event0. Impl. sends per-port binary inc-bit the occupancy increases* (at FB alloc or promotion).", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of L1D misses that are outstanding", + "Counter": "2", + "EventCode": "0x48", + "EventName": "L1D_PENDING.LOAD", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PENDING.LOAD_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.E", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.F", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Invalid state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.I", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Invalid state, does not count lines that go Invalid due to an eviction", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.M", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.S", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of L2 cache lines that have been L2 hardware prefetched but not used by demand accesses. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of L2 prefetches initiated by either the L2 Stream or AMP that were throttled due to Dynamic Prefetch Throttling. The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_PREFETCHES_THROTTLED.DPT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of L2 prefetches initiated by the L2 Stream that were throttled due to Demand Throttle Prefetcher. DTP Global Triggered with no Local Override. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_PREFETCHES_THROTTLED.DTP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of L2 prefetches initiated by the L2 Stream and not throttled by DTP due to local override. These prefetches may still be throttled due to another throttler mechanism besides DTP. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_PREFETCHES_THROTTLED.DTP_OVERRIDE", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of L2 prefetches initiated by either the L2 Stream or AMP that were throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or XQ_THRESHOLD. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_PREFETCHES_THROTTLED.XQ_THRESH", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x30", + "EventName": "L2_REJECT_XQ.ANY", + "PublicDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition which likely indicates back pressure from the IDI link. The XQ may reject transactions from the L2Q (non-cacheable requests), BBL (L2 misses) and WOB (L2 write-back victims).", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of L2 Cache Accesses Counts the total number of L2 Cache Accesses - sum of hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only, per core event", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x24", @@ -10,11 +261,178 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject short and long rejects (includes those counted in L2_reject_XQ.any), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.REJECTS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read access L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0xe1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ANY", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0x44", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read miss L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_REQUEST.MISS]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]", + "SampleAfterValue": "200003", + "UMask": "0xff", + "Unit": "cpu_core" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when L1D is locked", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x42", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "PublicDescription": "This event counts the number of cycles when the L1D is locked.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x41", "Unit": "cpu_atom" @@ -34,7 +452,7 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x4f", "Unit": "cpu_atom" @@ -50,13 +468,86 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Retired load instructions.", + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.L2_HIT", + "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or Translation Lookaside Buffer (TLB) miss which hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x35", + "EventName": "MEM_BOUND_STALLS_IFETCH.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT", + "PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which missed in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts all retired load instructions.", "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", - "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -67,58 +558,423 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of load uops retired.", - "Counter": "0,1,2,3,4,5,6,7", + "BriefDescription": "Retired software prefetch instructions.", + "Counter": "0,1,2,3", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_SWPF", + "PublicDescription": "Counts all retired software prefetch instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x84", + "Unit": "cpu_core" + }, + { + "BriefDescription": "All retired memory instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xd0", - "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PEBS": "1", + "EventName": "MEM_INST_RETIRED.ANY", + "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "SampleAfterValue": "1000003", + "UMask": "0x87", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with locked access.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PublicDescription": "Counts retired load instructions with locked access.", + "SampleAfterValue": "100007", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", + "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that hit the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", + "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0xa", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x11", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions that miss the STLB.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x12", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", + "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)", + "SampleAfterValue": "20011", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.", + "SampleAfterValue": "20011", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions which data source is memory side cache.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.MEMSIDE_CACHE", + "SampleAfterValue": "100007", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "SampleAfterValue": "100007", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache.", + "Counter": "0,1,2,3", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1", + "SampleAfterValue": "1000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", - "UMask": "0x81", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "100021", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "100021", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", + "SampleAfterValue": "1000003", + "UMask": "0x1", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of store uops retired.", + "BriefDescription": "This event is deprecated. Refer to new event MEM_LOAD_UOPS_LLC_MISS_RETIRED.MEMSIDE_CACHE", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.MEMSIDE_CACHE", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss the L2 cache, missed the Memory Side Cache and hit in DRAM", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss the LLC cache and hit in the Memory Side Cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.MEMSIDE_CACHE", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that hit in the L2 cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "PublicDescription": "Counts the number of load ops retired that hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that miss in the L2 cache", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to load buffer full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.LD_BUF", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to RSV full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.RSV", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that uops are blocked due to store buffer full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x04", + "EventName": "MEM_SCHEDULER_BLOCK.ST_BUF", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.L2_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of cache-lines required by retired stores whose Data Source is: Memory Side Cache", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.MEMSIDE_CACHE", + "SampleAfterValue": "100021", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of memory uops retired. A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST)", "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", - "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PEBS": "1", + "EventName": "MEM_UOPS_RETIRED.ALL", "SampleAfterValue": "200003", - "UMask": "0x82", + "UMask": "0x83", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "BriefDescription": "Counts the number of load uops retired.", "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", - "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", - "MSRIndex": "0x3F6", - "MSRValue": "0x400", - "PEBS": "2", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "SampleAfterValue": "200003", - "UMask": "0x5", + "UMask": "0x81", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "BriefDescription": "Counts the number of store uops retired.", "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", - "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", - "MSRIndex": "0x3F6", - "MSRValue": "0x80", - "PEBS": "2", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "SampleAfterValue": "200003", - "UMask": "0x5", + "UMask": "0x82", "Unit": "cpu_atom" }, { @@ -126,10 +982,9 @@ "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", - "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", - "MSRValue": "0x10", - "PEBS": "2", + "MSRValue": "0x80", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" @@ -139,10 +994,9 @@ "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", - "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", - "MSRValue": "0x800", - "PEBS": "2", + "MSRValue": "0x10", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" @@ -155,7 +1009,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" @@ -168,7 +1021,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" @@ -181,7 +1033,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" @@ -194,7 +1045,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" @@ -207,7 +1057,6 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" @@ -220,20 +1069,373 @@ "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "SampleAfterValue": "200003", "UMask": "0x5", "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of load uops retired that performed one or more locks", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x21", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory renamed load uops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.MRN_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x9", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory renamed store uops retired.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.MRN_STORES", + "SampleAfterValue": "200003", + "UMask": "0xa", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory uops retired that were splits.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x43", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired split load uops.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x41", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired split store uops.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "SampleAfterValue": "200003", + "UMask": "0x42", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load ops retired that filled the STLB - includes those in DTLB_LOAD_MISSES submasks", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of store ops retired (store STLB miss)", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", - "PEBS": "2", "SampleAfterValue": "200003", "UMask": "0x6", "Unit": "cpu_atom" + }, + { + "BriefDescription": "Retired memory uops for any access", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe5", + "EventName": "MEM_UOP_RETIRED.ANY", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "SampleAfterValue": "1000003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by mem side cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.MEMSIDE_CACHE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x11F80000004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x40001E00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001E00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by mem side cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.MEMSIDE_CACHE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x11F80000001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x40001E00002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Any memory transaction that reached the SQ.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cacheable and Non-Cacheable code read requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x2c", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.ANY", + "SampleAfterValue": "100003", + "UMask": "0xf", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ICACHE", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json b/tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json new file mode 100644 index 000000000000..d436e0c13e7e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json @@ -0,0 +1,484 @@ +[ + { + "BriefDescription": "Counts the number of cycles when any of the floating point dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles when floating-point divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.FPDIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for floating-point operations only.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of active floating point dividers per cycle in the loop stage.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_OCCUPANCY", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcd", + "EventName": "ARITH.FPDIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts all microcode FP assists.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.FP", + "PublicDescription": "Counts all microcode Floating Point assists.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ASSISTS.SSE_AVX_MIX", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.SSE_AVX_MIX", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 1st VEC port (port 0). FP-arith-uops are of type ADD* / SUB* / MUL / FMA* / DPP.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V0", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 2nd VEC port (port 1)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V1", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 3rd VEC port (port 5)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V2", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of FP-arith-uops dispatched on 4th VEC port", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.V3", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.4_FLOPS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "SampleAfterValue": "100003", + "UMask": "0x18", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_SINGLE", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.VECTOR", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "Deprecated": "1", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "1000003", + "UMask": "0x3c", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_128B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_128B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR_128B", + "SampleAfterValue": "100003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_256B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_256B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR_256B", + "SampleAfterValue": "100003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_SINGLE", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3c", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_128B [This event is alias to FP_ARITH_INST_RETIRED.VECTOR_128B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_128B", + "SampleAfterValue": "100003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_256B [This event is alias to FP_ARITH_INST_RETIRED.VECTOR_256B]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc7", + "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_256B", + "SampleAfterValue": "100003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP32", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc8", + "EventName": "FP_FLOPS_RETIRED.FP64", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit double precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit single precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.32B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.64B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of floating point retired instructions.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x3f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on all floating point ports.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x1f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 0.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.P0", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 1.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.P1", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 2.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.P2", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.P3", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 0, 1, 2, 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.PRIMARY", + "SampleAfterValue": "1000003", + "UMask": "0x1e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer store data port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.STD", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.FP_ASSIST", + "PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.", + "SampleAfterValue": "20003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt)", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.FPDIV", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_atom" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json index 0327bece0f94..07bd38a1904e 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json @@ -1,5 +1,447 @@ [ { + "BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Clears due to Unknown Branches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x60", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to a conditional jump.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.COND", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to an indirect branch.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.INDIRECT", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to a return branch.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.RETURN", + "SampleAfterValue": "200003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of BACLEARS due to a direct, unconditional jump.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe6", + "EventName": "BACLEARS.UNCOND", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x87", + "EventName": "DECODE.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles the Microcode Sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x87", + "EventName": "DECODE.MS_BUSY", + "SampleAfterValue": "500009", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of times a decode restriction reduces the decode throughput due to wrong instruction length prediction.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe9", + "EventName": "DECODE_RESTRICTION.PREDECODE_WRONG", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x61", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged with having preceded with frontend bound behavior", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ALL", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_ANT", + "MSRIndex": "0x3F7", + "MSRValue": "0x9", + "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles/empty issue slots due to a baclear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.BRANCH_DETECT", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles /empty issue slots due to a btclear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.BRANCH_RESTEER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged following an ms flow due to the bubble/wasted issue slot from exiting long ms flow", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.CISC", + "PublicDescription": "Counts the number of instructions retired that were tagged following an ms flow due to the bubble/wasted issue slot from exiting long ms flow", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged every cycle the decoder is unable to send 4 uops", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DECODE", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to icache miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ICACHE", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x608006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x601006", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x600206", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "MSRValue": "0x610006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x602006", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x600406", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x620006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x604006", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x600806", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MISP_ANT", + "MSRIndex": "0x3F7", + "MSRValue": "0x9", + "PublicDescription": "ANT retired branches that got just mispredicted", + "SampleAfterValue": "100007", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts flows delivered by the Microcode Sequencer", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MS_FLOWS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instruction retired tagged after a wasted issue slot if none of the previous events occurred", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.OTHER", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles/empty issue slots due to a predecode wrong", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.PREDECODE", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired instructions that caused clears due to being Unknown Branches.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "MSRIndex": "0x3F7", + "MSRValue": "0x17", + "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100007", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ICACHE_L2_HIT", + "PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that hit in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that also missed the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", @@ -9,6 +451,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are present.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.HIT", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", @@ -18,13 +469,212 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALLS", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "SampleAfterValue": "500009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ICACHE_DATA.STALL_PERIODS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALL_PERIODS", + "SampleAfterValue": "500009", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x83", + "EventName": "ICACHE_TAG.STALLS", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES_ANY", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of switches from DSB or MITE to the MS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" + }, + { + "BriefDescription": "This event is deprecated. [This event is alias to IDQ_BUBBLES.STARVATION_CYCLES]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "Deprecated": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when no uops are delivered by the IDQ for 2 or more cycles when backend of the machine is not stalled - normally indicating a Fetch Latency issue", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.FETCH_LATENCY", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls for 2 or more cycles - normally indicating a Fetch Latency issue.", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.STARVATION_CYCLES", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "MS_DECODED.MS_BUSY", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of times entered into a ucode flow in the FEC. Includes inserted flows due to front-end detected faults or assists.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "MS_DECODED.MS_ENTRY", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of times nanocode flow is executed.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "MS_DECODED.NANO_CODE", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json new file mode 100644 index 000000000000..e748f839c4bd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json @@ -0,0 +1,2730 @@ +[ + { + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C9 residency percent per package", + "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C9_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions", + "MetricExpr": "tma_core_bound", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_allocation_restriction", + "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_branch_detect", + "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_branch_resteer", + "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_cisc", + "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_decode", + "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_fast_nuke", + "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricgroupNoGroup": "TopdownL1;Default", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_ifetch_bandwidth", + "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_ifetch_latency", + "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_FLOPS_RETIRED.ALL@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipflop", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.ALL@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@FP_INST_RETIRED.128B_DP@ + cpu_atom@FP_INST_RETIRED.128B_SP@)", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_avx128", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX 256-bit instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@FP_INST_RETIRED.256B_DP@ + cpu_atom@FP_INST_RETIRED.256B_SP@)", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_avx256", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.64B_DP@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_scalar_dp", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.32B_SP@", + "MetricGroup": "Flops", + "MetricName": "tma_info_arith_inst_mix_ipfparith_scalar_sp", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", + "MetricExpr": "100 * (cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ + cpu_atom@LD_HEAD.PGWALK_AT_RET@) / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Ifetch", + "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles", + "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Load_Store_Miss", + "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall", + "MetricExpr": "100 * cpu_atom@LD_HEAD.ANY_AT_RET@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Mem_Exec", + "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles", + "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricName": "tma_info_br_inst_mix_ipbranch", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.NEAR_CALL@", + "MetricName": "tma_info_br_inst_mix_ipcall", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.FAR_BRANCH@u", + "MetricName": "tma_info_br_inst_mix_ipfarbranch", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)", + "MetricName": "tma_info_br_inst_mix_ipmisp_cond_ntaken", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.COND_TAKEN@", + "MetricName": "tma_info_br_inst_mix_ipmisp_cond_taken", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.INDIRECT@", + "MetricName": "tma_info_br_inst_mix_ipmisp_indirect", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired return Branch Misprediction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.RETURN@", + "MetricName": "tma_info_br_inst_mix_ipmisp_ret", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired Branch Misprediction", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@", + "MetricName": "tma_info_br_inst_mix_ipmispredict", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Ratio of all branches which mispredict", + "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / cpu_atom@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricName": "tma_info_br_mispredict_bound_branch_mispredict_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Ratio between Mispredicted branches and unknown branches", + "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / cpu_atom@BACLEARS.ANY@", + "MetricName": "tma_info_br_mispredict_bound_branch_mispredict_to_unknown_branch_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", + "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.LD_BUF@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full", + "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.RSV@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full", + "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles Per Instruction", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_core_cpi", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "cpu_atom@FP_FLOPS_RETIRED.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Flops", + "MetricName": "tma_info_core_flopc", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions Per Cycle", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_core_ipc", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_core_upi", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.L2_HIT@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.L2_MISS@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.L2_HIT@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.L2_MISS@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block", + "MetricExpr": "100 * cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_store_bound_l1_bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement", + "MetricExpr": "100 * (cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ + cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@) / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_store_bound_load_bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full", + "MetricExpr": "100 * (cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@MEM_SCHEDULER_BLOCK.ALL@) * tma_mem_scheduler", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_store_bound_store_bound", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory disambiguation", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.DISAMBIGUATION@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_disamb_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to floating point assists", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.FP_ASSIST@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_fp_assist_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory ordering", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_monuke_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory renaming", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.MRN_NUKE@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_mrn_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to page faults", + "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.PAGE_FAULT@ / cpu_atom@INST_RETIRED.ANY@", + "MetricName": "tma_info_machine_clear_bound_machine_clears_page_fault_pki", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", + "MetricExpr": "100 * cpu_atom@LD_BLOCKS.ADDRESS_ALIAS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", + "MetricExpr": "100 * cpu_atom@LD_BLOCKS.DATA_UNKNOWN@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", + "MetricExpr": "100 * cpu_atom@LD_HEAD.L1_MISS_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc", + "MetricExpr": "100 * cpu_atom@LD_HEAD.OTHER_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk", + "MetricExpr": "100 * cpu_atom@LD_HEAD.PGWALK_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss", + "MetricExpr": "100 * cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match", + "MetricExpr": "100 * cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@", + "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Load", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_mix_ipload", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per Store", + "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@MEM_UOPS_RETIRED.ALL_STORES@", + "MetricName": "tma_info_mem_mix_ipstore", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads that perform one or more locks", + "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.LOCK_LOADS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_mix_load_locks_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads that are splits", + "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.SPLIT_LOADS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@", + "MetricName": "tma_info_mem_mix_load_splits_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Ratio of mem load uops to all uops", + "MetricExpr": "1e3 * cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_mem_mix_memload_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", + "MetricExpr": "100 * cpu_atom@SERIALIZATION.C01_MS_SCB@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricName": "tma_info_serialization_%_tpause_cycles", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricName": "tma_info_system_cpu_utilization", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "cpu_atom@FP_FLOPS_RETIRED.ALL@ / (duration_time * 1e9)", + "MetricGroup": "Flops", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@k / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_kernel_utilization", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@ / cpu_atom@CPU_CLK_UNHALTED.REF_TSC@", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are FPDiv uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.FPDIV@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_fpdiv_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are IDiv uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.IDIV@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_idiv_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are microcode ops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.MS@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_microcode_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are x87 uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.X87@ / cpu_atom@TOPDOWN_RETIRING.ALL@", + "MetricName": "tma_info_uop_mix_x87_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_machine_clears", + "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_mem_scheduler", + "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_non_mem_scheduler", + "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)", + "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_nuke", + "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_other_fb", + "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", + "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricName": "tma_predecode", + "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_register", + "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_reorder_buffer", + "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation", + "MetricExpr": "tma_backend_bound - tma_core_bound", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_resource_bound", + "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", + "MetricgroupNoGroup": "TopdownL2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that result in retirement slots", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "Default;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "(tma_retiring >0.75)", + "MetricgroupNoGroup": "TopdownL1;Default", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)", + "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_serialization", + "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.4", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", + "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", + "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_avx_assists", + "MetricThreshold": "tma_avx_assists > 0.1", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", + "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_c01_wait", + "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", + "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_c02_wait", + "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_nt_mispredicts", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@br_misp_retired.cond_taken_bwd_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_tk_bwd_mispredicts", + "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@br_misp_retired.cond_taken_fwd_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_tk_fwd_mispredicts", + "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricExpr": "cpu_core@MEMORY_STALLS.MEM@ / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(cpu_core@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ + cpu_core@IDQ.DSB_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "cpu_core@L1D_MISS.FB_FULL@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", + "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", + "MetricExpr": "30 * cpu_core@ASSISTS.FP@ / tma_info_thread_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_fp_assists", + "MetricThreshold": "tma_fp_assists > 0.1", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_call_mispredicts", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", + "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_jump_mispredicts", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 8 / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / 100", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", + "MetricExpr": "cpu_core@INT_MISC.CLEARS_COUNT@ / (cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ + cpu_core@MACHINE_CLEARS.COUNT@)", + "MetricGroup": "BrMispredicts", + "MetricName": "tma_info_bad_spec_spec_clears_ratio", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", + "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@BR_INST_RETIRED.NEAR_RETURN@) / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_NTAKEN@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_nt", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are forward taken conditionals", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN_BWD@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_tk_bwd", + "MetricThreshold": "tma_info_branches_cond_tk_bwd > 0.3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are forward taken conditionals", + "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN_FWD@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_tk_fwd", + "MetricThreshold": "tma_info_branches_cond_tk_fwd > 0.2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ - cpu_core@BR_INST_RETIRED.COND_TAKEN_BWD@ - cpu_core@BR_INST_RETIRED.COND_TAKEN_FWD@ - 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@) / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk_bwd + tma_info_branches_cond_tk_fwd + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches", + "Unit": "cpu_core" + }, + { + "BriefDescription": "uops Executed per Cycle", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / tma_info_thread_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_core_epc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_thread_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.V0@ + cpu_core@FP_ARITH_DISPATCHED.V1@ + cpu_core@FP_ARITH_DISPATCHED.V2@ + cpu_core@FP_ARITH_DISPATCHED.V3@) / (4 * tma_info_thread_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 8 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_frontend_dsb_switch_cost", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks", + "MetricGroup": "DSBmiss;Fed;FetchLat", + "MetricName": "tma_info_frontend_dsb_switches_ret", + "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_frontend_fetch_upc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALL_PERIODS@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / cpu_core@BACLEARS.ANY@", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * cpu_core@FRONTEND_RETIRED.L2_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.CODE_RD_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_frontend_lsd_coverage", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_frontend_ms_latency_ret", + "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_unknown_branch_cost", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat", + "MetricName": "tma_info_frontend_unknown_branches_ret", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Branch instructions per taken branch", + "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_inst_mix_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.ALL_BRANCHES@", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_CALL@", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@MEM_INST_RETIRED.ALL_LOADS@", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per PAUSE (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / cpu_core@CPU_CLK_UNHALTED.PAUSE_INST@", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_ippause", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@MEM_INST_RETIRED.ALL_SWPF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per taken branch", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1", + "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_fb_hpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1d_cache_fill_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the Level 0 within L1D cache [GB / sec]", + "MetricExpr": "64 * cpu_core@L1D.L0_REPLACEMENT@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l1dl0_cache_fill_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.ALL_DEMAND_DATA_RD@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l1mpki_load", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l2_cache_fill_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (cpu_core@L2_RQSTS.REFERENCES@ - cpu_core@L2_RQSTS.MISS@) / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2hpki_all", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_HIT@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2hpki_load", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L2_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Backend;CacheHits;Mem", + "MetricName": "tma_info_memory_l2mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem;Offcore", + "MetricName": "tma_info_memory_l2mpki_all", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheHits;Mem", + "MetricName": "tma_info_memory_l2mpki_load", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Offcore requests (L2 cache miss) per kilo instruction for demand RFOs", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.RFO_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "CacheMisses;Offcore", + "MetricName": "tma_info_memory_l2mpki_rfo", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_l3_cache_access_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / tma_info_system_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_l3_cache_fill_bw", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L3_MISS@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_l3mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_latency_data_l2_mlp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS.DEMAND_DATA_RD@", + "MetricGroup": "LockCont;Memory_Lat;Offcore", + "MetricName": "tma_info_memory_latency_load_l2_miss_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_latency_load_l2_mlp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD@", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_latency_load_l3_miss_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "cpu_core@L1D_PENDING.LOAD@ / cpu_core@L1D_MISS.LOAD@", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "\"Bus lock\" per kilo instruction", + "MetricExpr": "1e3 * cpu_core@SQ_MISC.BUS_LOCK@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_mix_bus_lock_pki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Un-cacheable retired load per kilo instruction", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_MISC_RETIRED.UC@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem", + "MetricName": "tma_info_memory_mix_uc_load_pki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "cpu_core@L1D_PENDING.LOAD@ / cpu_core@L1D_PENDING.LOAD_CYCLES@", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "cpu_core@L2_LINES_OUT.USELESS_HWPF@ / (cpu_core@L2_LINES_OUT.SILENT@ + cpu_core@L2_LINES_OUT.NON_SILENT@)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15", + "Unit": "cpu_core" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(cpu_core@ITLB_MISSES.WALK_PENDING@ + cpu_core@DTLB_LOAD_MISSES.WALK_PENDING@ + cpu_core@DTLB_STORE_MISSES.WALK_PENDING@) / (4 * tma_info_thread_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of uops fetched from DSB per cycle", + "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@IDQ.DSB_CYCLES_ANY@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_dsb", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of uops fetched from LSD per cycle", + "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@LSD.CYCLES_ACTIVE@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_lsd", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of uops fetched from MITE per cycle", + "MetricExpr": "cpu_core@IDQ.MITE_UOPS@ / cpu_core@IDQ.MITE_CYCLES_ANY@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_pipeline_fetch_mite", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per a microcode Assist invocation", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", + "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", + "MetricName": "tma_info_pipeline_ipassist", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", + "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", + "MetricGroup": "MicroSeq;Pipeline;Ret", + "MetricName": "tma_info_pipeline_strings_cycles", + "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of cycles the processor is waiting yet unhalted; covering legacy PAUSE instruction, as well as C0.1 / C0.2 power-performance optimized states", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C0_WAIT@ / tma_info_thread_clks", + "MetricGroup": "C0Wait", + "MetricName": "tma_info_system_c0_wait", + "MetricThreshold": "tma_info_system_c0_wait > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_core_frequency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average CPU Utilization (percentage)", + "MetricExpr": "tma_info_system_cpus_utilized / #num_cpus_online", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of utilized CPUs", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_cpus_utilized", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@ / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / cpu_core@CPU_CLK_UNHALTED.REF_TSC@", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr", + "Unit": "cpu_core" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "slots", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@INST_RETIRED.ANY@", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops per taken branch", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_int_operations", + "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "cpu_core@INT_VEC_RETIRED.128BIT@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_128b", + "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "cpu_core@INT_VEC_RETIRED.256BIT@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_256b", + "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", + "MetricExpr": "cpu_core@MEMORY_STALLS.L1@ / tma_info_thread_clks", + "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * cpu_core@mem_load_retired.l1_hit_l1@R, cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) if 0 < cpu_core@mem_load_retired.l1_hit_l1@R else cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_l1_latency_capacity", + "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", + "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "cpu_core@MEMORY_STALLS.L2@ / tma_info_thread_clks", + "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "cpu_core@MEMORY_STALLS.L3@ / tma_info_thread_clks", + "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "cpu_core@UOPS_DISPATCHED.LOAD@ / (3 * tma_info_thread_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", + "MetricExpr": "cpu_core@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_lsd", + "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", + "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_memory_fence", + "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", + "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "cpu_core@UOPS_RETIRED.MS@ / tma_info_thread_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", + "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * cpu_core@IDQ.MS_SWITCHES@ / tma_info_thread_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ - cpu_core@INST_RETIRED.BR_FUSED@) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + cpu_core@FP_ARITH_INST_RETIRED.VECTOR@) / (tma_retiring * tma_info_thread_slots) + (cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@ + cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", + "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", + "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_other_mispredicts", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", + "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", + "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_other_nukes", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", + "MetricExpr": "99 * cpu_core@ASSISTS.PAGE_FAULT@ / tma_info_thread_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_page_faults", + "MetricThreshold": "tma_page_faults > 0.05", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", + "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ret_mispredicts", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "(cpu_core@BE_STALLS.SCOREBOARD@ + cpu_core@CPU_CLK_UNHALTED.C02@) / tma_info_thread_clks", + "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer)", + "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", + "MetricName": "tma_shuffles_256b", + "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(cpu_core@XQ.FULL@ + cpu_core@L1D_MISS.L2_STALLS@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(cpu_core@UOPS_DISPATCHED.STD@ + cpu_core@UOPS_DISPATCHED.STA@) / (7 * tma_info_thread_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", + "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", + "ScaleUnit": "100%", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json index 3d12e226d5ef..60daff922a89 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json @@ -1,13 +1,168 @@ [ { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ANY_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xff", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_BOUND_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xf4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DL1 miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x81", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to other block cases.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.OTHER", + "PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to other block cases such as pipeline conflicts, fences, etc.", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.OTHER_AT_RET", + "PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases such as pipeline conflicts, fences, etc.", + "SampleAfterValue": "1000003", + "UMask": "0xc0", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a pagewalk.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.PGWALK", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a pagewalk.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.PGWALK_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0xa0", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a store address match.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ST_ADDR", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a store address match.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ST_ADDR_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x84", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to store data forward block.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.ST_DATA", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to request buffers full or lock in progress.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.WCB_FULL", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to request buffers full or lock in progress.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.WCB_FULL_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x82", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of memory ordering machine clears triggered due to a snoop from an external agent. Does not count internally generated machine clears such as those due to disambiguations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "20003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of machine clears due to memory ordering conflicts.", "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING_FAST", + "SampleAfterValue": "20003", + "UMask": "0x82", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1", @@ -15,13 +170,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1", @@ -29,13 +183,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1", @@ -43,13 +196,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "23", "UMask": "0x1", @@ -57,13 +209,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1", @@ -71,13 +222,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -85,13 +235,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1", @@ -99,13 +248,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1", @@ -113,13 +261,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1", @@ -127,13 +274,12 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", - "Counter": "0,1,2,3,4,5,6,7,8,9", + "Counter": "2,3,4,5,6,7,8,9", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1", @@ -145,54 +291,112 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PEBS": "2", "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" }, { - "BriefDescription": "Counts cacheable demand data reads were not supplied by the L3 cache.", + "BriefDescription": "Counts misaligned loads that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts misaligned stores that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x13", + "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x13FBFC00004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBFC00001", + "MSRValue": "0x13FBFC00001", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0xFE7F8000001", + "MSRValue": "0x9E7FA000001", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO were not supplied by the L3 cache.", + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBFC00002", + "MSRValue": "0x13FBFC00002", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).", "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0xFE7F8000002", + "MSRValue": "0x9E7FA000002", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data read requests that miss the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json new file mode 100644 index 000000000000..855585fe6fae --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json @@ -0,0 +1,150 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "C0Wait": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ifetch": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Load_Store_Miss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemOffcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem_Exec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "load_store_bound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_assists_group": "Metrics contributing to tma_assists category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", + "tma_ifetch_bandwidth_group": "Metrics contributing to tma_ifetch_bandwidth category", + "tma_ifetch_latency_group": "Metrics contributing to tma_ifetch_latency category", + "tma_int_operations_group": "Metrics contributing to tma_int_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueComp": "Metrics related by the issue $issueComp", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", + "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_other_light_ops_group": "Metrics contributing to tma_other_light_ops category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_resource_bound_group": "Metrics contributing to tma_resource_bound category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" +} diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json index 0b49b4684c4b..667707d4fe37 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/other.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json @@ -1,6 +1,345 @@ [ { - "BriefDescription": "Counts cacheable demand data reads Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.HARDWARE", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "ASSISTS.PAGE_FAULT", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.PAGE_FAULT", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa2", + "EventName": "BE_STALLS.SCOREBOARD", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x63", + "EventName": "BUS_LOCK.BLOCKED_CYCLES", + "PublicDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to an Accepted lock it issued, includes both split and non-split lock cycles.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x63", + "EventName": "BUS_LOCK.LOCK_CYCLES", + "PublicDescription": "Counts the number of unhalted cycles a Core is blocked due to an Accepted lock it issued, includes both split and non-split lock cycles. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of non-split locks such as UC locks issued by a Core (does not include cache locks)", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x63", + "EventName": "BUS_LOCK.NON_SPLIT_LOCKS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of split locks issued by a Core", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x63", + "EventName": "BUS_LOCK.SPLIT_LOCKS", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x02", + "EventName": "DEPENDENT_LOADS.ANY", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cycles the L2 Prefetchers are at throttle level 0", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL0_SOC", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 1", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL1_SOC", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL2_SOC", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 3", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL3_SOC", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 4", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL4_SOC", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on all Integer ports.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.ALL", + "SampleAfterValue": "1000003", + "UMask": "0xff", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a load port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.LD", + "PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 0.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P0", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 1.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P1", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 2.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P2", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.P3", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.PRIMARY", + "SampleAfterValue": "1000003", + "UMask": "0x78", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on a Store address port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STA", + "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "INT_UOPS_EXECUTED.STD_JMP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches that were throttled due to Dynamic Prefetch Throttling. The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.DPT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches throttled due to Demand Throttle Prefetcher. DTP Global Triggered with no Local Override. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.DTP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches not throttled by DTP due to local override. These prefetches may still be throttled due to another throttler mechanism. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.DTP_OVERRIDE", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches throttled due to LLC hit rate in <insert knob name here>. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.HIT_RATE", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LLC prefetches throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or LLC_XQ_THRESHOLD. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x29", + "EventName": "LLC_PREFETCHES_THROTTLED.XQ_THRESH", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L2", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.L3", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x46", + "EventName": "MEMORY_STALLS.MEM", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts all requests that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.ALL_REQUESTS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFF0000001DFFF", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts writebacks of modified cachelines that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.COREWB_M.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10008", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.COREWB_NONM.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x11000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1FBC000004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", @@ -22,7 +361,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts cacheable demand data reads were supplied by DRAM.", + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.DRAM", @@ -44,7 +383,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", @@ -64,5 +403,156 @@ "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1FBC000002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts full streaming stores (64 bytes, WCiLF) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts partial streaming stores (less than 64 bytes, WCiL) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "UMask": "0x7", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_RESOURCE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.C01_MS_SCB", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number issue slots not consumed due to a color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.COLOR_STALLS", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles the uncore cannot take further requests", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x2d", + "EventName": "XQ.FULL", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand request.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xf4", + "EventName": "XQ_PROMOTION.ALL", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand code read.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xf4", + "EventName": "XQ_PROMOTION.CRDS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand read.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xf4", + "EventName": "XQ_PROMOTION.DRDS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand RFO.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xf4", + "EventName": "XQ_PROMOTION.RFOS", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json index 220c2115fec9..f4ec7a884937 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json @@ -1,10 +1,97 @@ [ { + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.DIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "SampleAfterValue": "1000003", + "UMask": "0x9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of active floating point and integer dividers per cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_OCCUPANCY", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of floating point and integer divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcd", + "EventName": "ARITH.DIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles when any of the integer dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles when integer divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.IDIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer operations only.", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of active integer dividers per cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_OCCUPANCY", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of integer divider uops executed per cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcd", + "EventName": "ARITH.IDIV_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc1", + "EventName": "ASSISTS.ANY", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "SampleAfterValue": "100003", + "UMask": "0x1f", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", "SampleAfterValue": "200003", "Unit": "cpu_atom" @@ -14,17 +101,214 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009", "Unit": "cpu_core" }, { + "BriefDescription": "Counts retired JCC (Jump on Conditional Code) branch instructions retired includes both taken and not taken branches", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "SampleAfterValue": "200003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "Counts conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x111", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of not taken JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "SampleAfterValue": "200003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of taken JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xfe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PublicDescription": "Counts taken conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x101", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken backward conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD", + "PublicDescription": "Counts taken backward conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken forward conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD", + "PublicDescription": "Counts taken forward conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x102", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and Interrupt call and return", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "SampleAfterValue": "200003", + "UMask": "0xbf", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Far branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PublicDescription": "Counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "SampleAfterValue": "200003", + "UMask": "0xeb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Indirect near branch instructions retired (excluding returns)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of near indirect JMP branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of near CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "SampleAfterValue": "200003", + "UMask": "0xf9", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near RET branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "SampleAfterValue": "200003", + "UMask": "0xf7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PublicDescription": "Counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of taken branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xc0", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of near relative CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfd", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", "SampleAfterValue": "200003", "Unit": "cpu_atom" @@ -34,13 +318,302 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "400009", "Unit": "cpu_core" }, { - "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "BriefDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", + "SampleAfterValue": "400009", + "UMask": "0x44", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "SampleAfterValue": "200003", + "UMask": "0x7e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x111", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_COST", + "SampleAfterValue": "400009", + "UMask": "0x151", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted not taken JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "SampleAfterValue": "200003", + "UMask": "0x7f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "SampleAfterValue": "400009", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", + "SampleAfterValue": "400009", + "UMask": "0x50", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted taken JCC branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xfe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x101", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD", + "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST", + "SampleAfterValue": "400009", + "UMask": "0x8001", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", + "SampleAfterValue": "400009", + "UMask": "0x141", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD", + "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST", + "SampleAfterValue": "400009", + "UMask": "0x8002", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "SampleAfterValue": "200003", + "UMask": "0xeb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfb", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", + "SampleAfterValue": "400009", + "UMask": "0x42", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_COST", + "SampleAfterValue": "100003", + "UMask": "0xc0", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", + "SampleAfterValue": "400009", + "UMask": "0x60", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RETURN", + "SampleAfterValue": "200003", + "UMask": "0xf7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET_COST", + "SampleAfterValue": "100007", + "UMask": "0x48", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the total number of BTCLEARS.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe8", + "EventName": "BTCLEAR.ANY", + "PublicDescription": "Counts the total number of BTCLEARS which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C01", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C02", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C0_WAIT", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x70", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.CORE", "SampleAfterValue": "2000003", @@ -74,7 +647,27 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles", + "BriefDescription": "Core clocks when a PAUSE is pending.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Pause instructions", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles.", "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", "SampleAfterValue": "2000003", @@ -111,7 +704,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.", "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", "SampleAfterValue": "2000003", @@ -145,10 +738,119 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Fixed Counter: Counts the number of instructions retired", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "16", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "4", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "SampleAfterValue": "2000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "5", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "SampleAfterValue": "2000003", + "UMask": "0x21", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "2", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instruction decoders utilized in a cycle", + "Counter": "2", + "EventCode": "0x75", + "EventName": "INST_DECODED.DECODERS", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of instructions retired.", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -157,7 +859,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1", @@ -168,7 +869,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, @@ -177,17 +877,247 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, { + "BriefDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.BR_FUSED", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INST_RETIRED.MACRO_FUSED", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.MACRO_FUSED", + "SampleAfterValue": "2000003", + "UMask": "0x30", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired NOP instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.NOP", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Precise instruction retired with PEBS precise-distribution", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.PREC_DIST", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Iterations of Repeat string retired instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.REP_ITERATION", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Bubble cycles of BPClear.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.BPCLEAR_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0xB", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Clears speculative count", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "SampleAfterValue": "500009", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0x7", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots where uops got dropped", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xad", + "EventName": "INT_MISC.UOP_DROPPING", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.128BIT", + "SampleAfterValue": "1000003", + "UMask": "0x13", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of vector integer instructions retired of 256-bit vector-width.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.256BIT", + "SampleAfterValue": "1000003", + "UMask": "0xac", + "Unit": "cpu_core" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 128-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_128", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 256-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_256", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.MUL_256", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.MUL_256", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.SHUFFLES", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.SHUFFLES", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_128", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_128", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_256", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_256", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of occurrences a retired load was blocked for any of the following reasons: utlb_miss, 4k_alias, unknown_sta/bad_fwd, unready_fwd (includes md blocks and esp consuming load blocks)", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address exactly matches an older store whose data is not ready (a.k.a. unknown). unready_fwd", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x88", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_atom" @@ -203,11 +1133,155 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of demand loads that match on a wcb (request buffer) allocated by an L1 hardware prefetch", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x4c", + "EventName": "LOAD_HIT_PREFETCH.HW_PF", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "8", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_OK", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xa8", + "EventName": "LSD.UOPS", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts all machine clears for any reason including, but not limited to memory ordering, SMC, and FP assist.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.ANY", + "SampleAfterValue": "20003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.ANY_FAST", + "SampleAfterValue": "20003", + "UMask": "0xff", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.COUNT", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of memory ordering machine clears triggered due to an internal load passing an older store within the same CPU.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.DISAMBIGUATION", + "SampleAfterValue": "20003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.DISAMBIGUATION_FAST", + "SampleAfterValue": "20003", + "UMask": "0x88", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of nukes due to memory renaming", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MRN_NUKE", + "SampleAfterValue": "20003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MRN_NUKE_FAST", + "SampleAfterValue": "20003", + "UMask": "0x90", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of times that the machine clears due to a page fault. Covers both I-Side and D-Side (Loads/Stores) page faults. A page fault occurs when either the page is not present, or an access violation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.PAGE_FAULT", + "SampleAfterValue": "20003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event is deprecated.", + "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SLOW", + "SampleAfterValue": "20003", + "UMask": "0x6e", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "LFENCE instructions retired", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xe0", + "EventName": "MISC2_RETIRED.LFENCE", + "PublicDescription": "number of LFENCE retired instructions", + "SampleAfterValue": "400009", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -217,12 +1291,119 @@ "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of CLFLUSH, CLWB, and CLDEMOTE instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe0", + "EventName": "MISC_RETIRED1.CL_INST", + "SampleAfterValue": "1000003", + "UMask": "0xff", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of LFENCE instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe0", + "EventName": "MISC_RETIRED1.LFENCE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of RDPMC, RDTSC, and RDTSCP instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe0", + "EventName": "MISC_RETIRED1.RDPMC_RDTSC_P", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Count the number of WRMSR instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe0", + "EventName": "MISC_RETIRED1.WRMSR", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of faults and software interrupts with vector < 32.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.FAULT_ALL", + "PublicDescription": "Counts the number of faults and software interrupts with vector < 32, including VOE cases.", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of PSB+ nuke events and ToPA trap events.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.INTEL_PT_CLEARS", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of accesses to KeyLocker cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.KEYLOCKER_ACCESS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of misses to KeyLocker cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.KEYLOCKER_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x11", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of user interrupts delivered.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.ULI_DELIVERY", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of SENDUIPI instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.ULI_SENDUIPI", + "SampleAfterValue": "1000003", + "UMask": "0x9", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of VM exits.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe1", + "EventName": "MISC_RETIRED2.VM_EXIT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x75", + "EventName": "SERIALIZATION.NON_C01_MS_SCB", + "PublicDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires. The most commonly executed instruction with an MS scoreboard is PAUSE.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xa4", @@ -233,6 +1414,35 @@ "Unit": "cpu_core" }, { + "BriefDescription": "TMA slots wasted due to incorrect speculations.", + "Counter": "0", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BAD_SPEC_SLOTS", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "SampleAfterValue": "10000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", + "Counter": "0", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "SampleAfterValue": "10000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TOPDOWN.MEMORY_BOUND_SLOTS", + "Counter": "3", + "EventCode": "0xa4", + "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "SampleAfterValue": "10000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", @@ -252,15 +1462,16 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", - "Counter": "0,1,2,3,4,5,6,7", - "EventCode": "0x73", + "BriefDescription": "Fixed Counter: Counts the number of issue slots not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "Counter": "36", "EventName": "TOPDOWN_BAD_SPECULATION.ALL", + "PublicDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the IQ. Also, includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "SampleAfterValue": "1000003", + "UMask": "0x5", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P", @@ -268,6 +1479,42 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Fast Nukes such as Memory Ordering Machine clears and MRN nukes", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.FASTNUKE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to a machine clear (nuke).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.NUKE", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", @@ -277,6 +1524,23 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to due to certain allocation restrictions", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALL_NON_ARCH", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", @@ -286,7 +1550,52 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls", + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC and FPC RAT stalls - which can be due to the FIQ and IEC reservation station stall (integer, FP and SIMD scheduler not being able to accept another uop. )", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to mrbl stall. A 'marble' refers to a physical register file entry, also known as the physical destination (PDST).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REGISTER", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.SERIALIZATION", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls.", "Counter": "37", "EventName": "TOPDOWN_FE_BOUND.ALL", "SampleAfterValue": "1000003", @@ -296,6 +1605,14 @@ { "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ALL_NON_ARCH", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "TOPDOWN_FE_BOUND.ALL_P", "SampleAfterValue": "1000003", @@ -303,10 +1620,90 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTClear", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.BRANCH_RESTEER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to ms", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.CISC", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to decode stall", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.DECODE", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH", + "SampleAfterValue": "1000003", + "UMask": "0x8d", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to latency related stalls including BACLEARs, BTCLEARs, ITLB misses, and ICache misses.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY", + "SampleAfterValue": "1000003", + "UMask": "0x72", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to itlb miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ITLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend that do not categorize into any other common frontend stall", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.OTHER", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to predecode wrong", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.PREDECODE", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.", "Counter": "38", "EventName": "TOPDOWN_RETIRING.ALL", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x7", "Unit": "cpu_atom" @@ -314,14 +1711,295 @@ { "BriefDescription": "Counts the number of consumed retirement slots.", "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x72", + "EventName": "TOPDOWN_RETIRING.ALL_NON_ARCH", + "SampleAfterValue": "1000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of consumed retirement slots.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "TOPDOWN_RETIRING.ALL_P", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_atom" }, { + "BriefDescription": "Number of non dec-by-all uops decoded by decoder", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x76", + "EventName": "UOPS_DECODED.DEC0_UOPS", + "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on INT EU ALU ports.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.ALU", + "PublicDescription": "Number of ALU integer uops dispatch to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on any INT EU ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.INT_EU_ALL", + "PublicDescription": "Number of integer uops dispatched to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched/executed by any of the 3 JEUs (all ups that hold the JEU including macro; micro jumps; fetch-from-eip)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.JMP", + "PublicDescription": "Number of jump uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x40", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on Load ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.LOAD", + "PublicDescription": "Number of Load uops dispatched to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of (shift) 1-cycle Uops dispatched/executed by any of the Shift Eus", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.SHIFT", + "PublicDescription": "Number of SHIFT integer uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched/executed by Slow EU (e.g. 3+ cycles LEA, >1 cycles shift, iDIVs, CR; *H operation)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.SLOW", + "PublicDescription": "Number of Slow integer uops dispatch to execution.", + "SampleAfterValue": "2000003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of Uops dispatched on STA ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.STA", + "PublicDescription": "Number of STA (Store Address) uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x80", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops executed on STD ports", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.STD", + "PublicDescription": "Number of STD (Store Data) uops dispatch to execution", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "3", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "Counter": "3", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "Counter": "3", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "3", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "3", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALLS", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of x87 uops dispatched.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "When 4-uops are requested and only 2-uops are delivered, the event counts 2. Uops_issued correlates to the number of ROB entries. If uop takes 2 ROB slots it counts as 2 uops_issued.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x0e", + "EventName": "UOPS_ISSUED.ANY", + "SampleAfterValue": "200003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Uops that RAT issues to RS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "UOPS_ISSUED.CYCLES", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of uops retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.ALL", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles with retired uop(s).", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.CYCLES", + "PublicDescription": "Counts cycles where at least one uop has retired.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired uops except the last uop of each instruction.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.HEAVY", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of integer divide uops retired", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.IDIV", + "SampleAfterValue": "2000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops retired that were delivered by the loop stream detector (LSD).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.LSD", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "UOPS_RETIRED.MS", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of non-speculative switches to the Microcode Sequencer (MS)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS_SWITCHES", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "PublicDescription": "Switches to the Microcode Sequencer", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", "Counter": "0,1,2,3,4,5,6,7,8,9", "EventCode": "0xc2", @@ -330,5 +2008,26 @@ "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALLS", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of x87 uops retired, includes those in ms flows", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.X87", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json new file mode 100644 index 000000000000..7d63580302de --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json @@ -0,0 +1,36 @@ +[ + { + "BriefDescription": "Read CAS command sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x22", + "EventName": "UNC_M_CAS_COUNT_RD", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Write CAS command sent to DRAM", + "Counter": "0,1,2,3,4", + "EventCode": "0x23", + "EventName": "UNC_M_CAS_COUNT_WR", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Any Rank at Hot state", + "Counter": "0,1,2,3,4", + "EventCode": "0x19", + "EventName": "UNC_M_DRAM_THERMAL_HOT", + "Experimental": "1", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Any Rank at Warm state", + "Counter": "0,1,2,3,4", + "EventCode": "0x1A", + "EventName": "UNC_M_DRAM_THERMAL_WARM", + "Experimental": "1", + "PerPkg": "1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json index 59af79e3466e..defa3a967754 100644 --- a/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json @@ -1,5 +1,71 @@ [ { + "BriefDescription": "Counts the number of page walks initiated by a demand load that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "200003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts walks that miss the PDE_CACHE", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.PDE_CACHE_MISS", + "SampleAfterValue": "200003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "200003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x320", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Account for 4k page size only. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K", + "SampleAfterValue": "200003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Account for large page sizes only. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT_LGPG", + "SampleAfterValue": "200003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", @@ -20,6 +86,125 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks initiated by a store that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts walks that miss the PDE_CACHE", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.PDE_CACHE_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x320", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", @@ -40,6 +225,134 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of times there was an ITLB miss and a new translation was filled into the ITLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x81", + "EventName": "ITLB.FILLS", + "PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) and a new translation was filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSED_WALK", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts walks that miss the PDE_CACHE", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.PDE_CACHE_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "2000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x120", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "CounterMask": "1", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", @@ -58,5 +371,120 @@ "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.", + "SampleAfterValue": "200003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.", + "Counter": "0,1,2,3,4,5,6,7,8,9", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of occurrences a load gets blocked because of a micro TLB miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.DTLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DTLB miss", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.DTLB_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x10", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DTLB miss.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "LD_HEAD.DTLB_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x90", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of PMH walks that hit in the L1 or WCBs", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xbc", + "EventName": "PAGE_WALKER_LOADS.DTLB_L1_HIT", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of PMH walks that hit in the L2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xbc", + "EventName": "PAGE_WALKER_LOADS.DTLB_L2_HIT", + "PublicDescription": "Counts the number of PMH walks that hit in the L2. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Count number of any STLB flush attempts (Entire, PCID, InvPage, CR3 write, etc)", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xbd", + "EventName": "TLB_FLUSHES.STLB_ANY", + "SampleAfterValue": "20003", + "UMask": "0x20", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index d503aa7e3594..56d5fc419acf 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,38 +1,40 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.27,alderlake,core -GenuineIntel-6-BE,v1.27,alderlaken,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.28,alderlake,core +GenuineIntel-6-BE,v1.28,alderlaken,core +GenuineIntel-6-C[56],v1.07,arrowlake,core GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core -GenuineIntel-6-(3D|47),v29,broadwell,core -GenuineIntel-6-56,v11,broadwellde,core -GenuineIntel-6-4F,v22,broadwellx,core -GenuineIntel-6-55-[56789ABCDEF],v1.22,cascadelakex,core +GenuineIntel-6-(3D|47),v30,broadwell,core +GenuineIntel-6-56,v12,broadwellde,core +GenuineIntel-6-4F,v23,broadwellx,core +GenuineIntel-6-55-[56789ABCDEF],v1.23,cascadelakex,core +GenuineIntel-6-DD,v1.00,clearwaterforest,core GenuineIntel-6-9[6C],v1.05,elkhartlake,core -GenuineIntel-6-CF,v1.09,emeraldrapids,core +GenuineIntel-6-CF,v1.11,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core -GenuineIntel-6-B6,v1.03,grandridge,core -GenuineIntel-6-A[DE],v1.02,graniterapids,core -GenuineIntel-6-(3C|45|46),v35,haswell,core -GenuineIntel-6-3F,v28,haswellx,core -GenuineIntel-6-7[DE],v1.22,icelake,core -GenuineIntel-6-6[AC],v1.26,icelakex,core +GenuineIntel-6-B6,v1.05,grandridge,core +GenuineIntel-6-A[DE],v1.06,graniterapids,core +GenuineIntel-6-(3C|45|46),v36,haswell,core +GenuineIntel-6-3F,v29,haswellx,core +GenuineIntel-6-7[DE],v1.24,icelake,core +GenuineIntel-6-6[AC],v1.27,icelakex,core GenuineIntel-6-3A,v24,ivybridge,core GenuineIntel-6-3E,v24,ivytown,core GenuineIntel-6-2D,v24,jaketown,core GenuineIntel-6-(57|85),v16,knightslanding,core -GenuineIntel-6-BD,v1.01,lunarlake,core -GenuineIntel-6-A[AC],v1.10,meteorlake,core +GenuineIntel-6-BD,v1.11,lunarlake,core +GenuineIntel-6-(AA|AC|B5),v1.12,meteorlake,core GenuineIntel-6-1[AEF],v4,nehalemep,core GenuineIntel-6-2E,v4,nehalemex,core -GenuineIntel-6-A7,v1.03,rocketlake,core +GenuineIntel-6-A7,v1.04,rocketlake,core GenuineIntel-6-2A,v19,sandybridge,core -GenuineIntel-6-8F,v1.23,sapphirerapids,core -GenuineIntel-6-AF,v1.04,sierraforest,core +GenuineIntel-6-8F,v1.25,sapphirerapids,core +GenuineIntel-6-AF,v1.08,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v59,skylake,core -GenuineIntel-6-55-[01234],v1.35,skylakex,core +GenuineIntel-6-55-[01234],v1.36,skylakex,core GenuineIntel-6-86,v1.23,snowridgex,core -GenuineIntel-6-8[CD],v1.16,tigerlake,core +GenuineIntel-6-8[CD],v1.17,tigerlake,core GenuineIntel-6-2C,v5,westmereep-dp,core GenuineIntel-6-25,v4,westmereep-sp,core GenuineIntel-6-2F,v4,westmereex,core diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json index 908e3c7f6d6e..ce351cd7caaf 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json @@ -92,11 +92,11 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_core" @@ -399,7 +399,7 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT", @@ -408,7 +408,7 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which missed all the caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS", @@ -436,7 +436,7 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT", @@ -445,7 +445,7 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", @@ -459,7 +459,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81", @@ -471,7 +470,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82", @@ -483,7 +481,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83", @@ -495,7 +492,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21", @@ -507,7 +503,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41", @@ -519,7 +514,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42", @@ -531,7 +525,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x9", @@ -543,7 +536,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0xa", @@ -555,7 +547,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11", @@ -567,7 +558,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12", @@ -589,7 +579,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4", @@ -601,7 +590,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1", @@ -613,7 +601,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8", @@ -625,7 +612,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2", @@ -637,7 +623,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PEBS": "1", "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -649,7 +634,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4", @@ -661,7 +645,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40", @@ -673,7 +656,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1", @@ -685,7 +667,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8", @@ -697,7 +678,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2", @@ -709,7 +689,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10", @@ -721,7 +700,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4", @@ -733,7 +711,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20", @@ -1028,6 +1005,36 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the second Level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of store uops retired that miss in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", @@ -1048,6 +1055,50 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json index b6c52f7385fc..a10614513c8d 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json @@ -55,7 +55,6 @@ "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PEBS": "1", "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)", "SampleAfterValue": "100007", "UMask": "0x3", @@ -68,7 +67,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -81,7 +79,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -103,7 +100,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -116,7 +112,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -129,7 +124,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -142,7 +136,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -155,7 +148,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -168,7 +160,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -181,7 +172,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -194,7 +184,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -207,7 +196,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -220,7 +208,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -233,7 +220,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -246,7 +232,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -259,7 +244,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -272,7 +256,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -285,7 +268,6 @@ "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", "MSRValue": "0x9", - "PEBS": "1", "PublicDescription": "ANT retired branches that got just mispredicted", "SampleAfterValue": "100007", "UMask": "0x2", @@ -298,7 +280,6 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -310,7 +291,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x3", @@ -323,7 +303,6 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x3", "Unit": "cpu_core" @@ -539,5 +518,14 @@ "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "MS_DECODED.MS_BUSY", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" } ] diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json index b464a8ab32ca..e4481fbc1e13 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json @@ -143,7 +143,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1", @@ -157,7 +156,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1", @@ -171,7 +169,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1", @@ -185,7 +182,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "23", "UMask": "0x1", @@ -199,7 +195,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1", @@ -213,7 +208,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1", @@ -227,7 +221,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1", @@ -241,7 +234,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1", @@ -255,7 +247,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1", @@ -269,7 +260,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1", @@ -281,7 +271,6 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PEBS": "2", "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", "SampleAfterValue": "1000003", "UMask": "0x2", @@ -306,6 +295,17 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json index b54a5fc0861f..855585fe6fae 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/metricgroups.json @@ -41,6 +41,7 @@ "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Load_Store_Miss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -89,7 +90,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -99,6 +102,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_ifetch_bandwidth_group": "Metrics contributing to tma_ifetch_bandwidth category", "tma_ifetch_latency_group": "Metrics contributing to tma_ifetch_latency category", "tma_int_operations_group": "Metrics contributing to tma_int_operations category", @@ -121,10 +125,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -138,5 +145,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json index 1a7392f0da86..20c52630127e 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/mtl-metrics.json @@ -49,13 +49,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "C8 residency percent per package", "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", "MetricGroup": "Power", @@ -63,13 +56,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", - "ScaleUnit": "100%" - }, - { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -89,28 +75,30 @@ "MetricExpr": "tma_core_bound", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "DefaultMetricgroupName": "TopdownL1", "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "tma_backend_bound > 0.1", - "MetricgroupNoGroup": "TopdownL1", + "MetricThreshold": "(tma_backend_bound >0.10)", + "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", + "DefaultMetricgroupName": "TopdownL1", "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "tma_bad_speculation > 0.15", - "MetricgroupNoGroup": "TopdownL1", + "MetricThreshold": "(tma_bad_speculation >0.15)", + "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -120,7 +108,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -130,7 +118,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -140,7 +128,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -149,7 +137,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -158,7 +146,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", + "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -168,7 +156,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -177,17 +165,18 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", + "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", + "DefaultMetricgroupName": "TopdownL1", "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "tma_frontend_bound > 0.2", - "MetricgroupNoGroup": "TopdownL1", + "MetricThreshold": "(tma_frontend_bound >0.20)", + "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -196,7 +185,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -205,7 +194,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -215,7 +204,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", + "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -388,6 +377,12 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2", + "MetricExpr": "100 * (cpu_atom@MEM_BOUND_STALLS_IFETCH.LLC_HIT@ + cpu_atom@MEM_BOUND_STALLS_IFETCH.LLC_MISS@) / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", + "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@", "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit", @@ -407,6 +402,13 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2", + "MetricExpr": "100 * (cpu_atom@MEM_BOUND_STALLS_LOAD.LLC_HIT@ + cpu_atom@MEM_BOUND_STALLS_LOAD.LLC_MISS@) / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", + "MetricGroup": "load_store_bound", + "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@", "MetricGroup": "load_store_bound", @@ -534,7 +536,7 @@ { "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", "MetricExpr": "100 * cpu_atom@SERIALIZATION.C01_MS_SCB@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", - "MetricName": "tma_info_serialization _%_tpause_cycles", + "MetricName": "tma_info_serialization_%_tpause_cycles", "Unit": "cpu_atom" }, { @@ -559,6 +561,13 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@ / cpu_atom@CPU_CLK_UNHALTED.REF_TSC@", "MetricGroup": "Power", @@ -594,7 +603,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -603,7 +612,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", + "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -613,7 +622,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -622,7 +631,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -631,7 +640,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", + "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -640,7 +649,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -649,7 +658,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", + "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -658,7 +667,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -667,7 +676,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -676,18 +685,19 @@ "MetricExpr": "tma_backend_bound - tma_core_bound", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", + "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of issue slots that result in retirement slots", + "DefaultMetricgroupName": "TopdownL1", "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL_P@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Default;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "tma_retiring > 0.75", - "MetricgroupNoGroup": "TopdownL1", + "MetricThreshold": "(tma_retiring >0.75)", + "MetricgroupNoGroup": "TopdownL1;Default", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -696,7 +706,7 @@ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (6 * cpu_atom@CPU_CLK_UNHALTED.CORE@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", + "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -708,7 +718,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -721,13 +731,13 @@ "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -737,34 +747,141 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", - "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", - "MetricgroupNoGroup": "TopdownL1", + "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "DefaultMetricgroupName": "TopdownL1", "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", - "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", - "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%", "Unit": "cpu_core" }, { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20", + "Unit": "cpu_core" + }, + { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -773,26 +890,26 @@ "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -801,7 +918,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -811,18 +928,90 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_nt_mispredicts", + "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_COST@ * cpu_core@br_misp_retired.cond_taken_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_cond_tk_mispredicts", + "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency) * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -833,26 +1022,26 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 24 * tma_info_system_core_frequency) * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -862,8 +1051,8 @@ "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -872,8 +1061,8 @@ "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -883,7 +1072,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -892,48 +1081,48 @@ "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "cpu_core@L1D_PEND_MISS.FB_FULL@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -944,28 +1133,28 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -975,7 +1164,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -985,7 +1174,16 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -994,8 +1192,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1004,8 +1202,8 @@ "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1014,8 +1212,8 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1024,40 +1222,41 @@ "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", - "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", + "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", - "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1066,21 +1265,39 @@ "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_call_mispredicts", + "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions", + "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ind_jump_mispredicts", + "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / 100", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 6 / cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", @@ -1088,7 +1305,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", @@ -1096,15 +1313,15 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -1120,7 +1337,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "cpu_core@INT_MISC.CLEARS_COUNT@ / (cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ + cpu_core@MACHINE_CLEARS.COUNT@)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio", @@ -1136,8 +1353,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", @@ -1145,7 +1362,7 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -1154,116 +1371,10 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY\\,umask\\=1@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20", "Unit": "cpu_core" }, { @@ -1334,12 +1445,12 @@ "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)", "Unit": "cpu_core" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" @@ -1354,22 +1465,30 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost", "Unit": "cpu_core" }, { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks", + "MetricGroup": "DSBmiss;Fed;FetchLat", + "MetricName": "tma_info_frontend_dsb_switches_ret", + "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05", + "Unit": "cpu_core" + }, + { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALL_PERIODS@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency", "Unit": "cpu_core" @@ -1411,15 +1530,37 @@ "Unit": "cpu_core" }, { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat;MicroSeq", + "MetricName": "tma_info_frontend_ms_latency_ret", + "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc", + "Unit": "cpu_core" + }, + { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", + "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.", + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears", + "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks", + "MetricGroup": "Fed;FetchLat", + "MetricName": "tma_info_frontend_unknown_branches_ret", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch", @@ -1439,7 +1580,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW", "Unit": "cpu_core" }, { @@ -1448,7 +1589,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1457,7 +1598,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1466,7 +1607,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1475,7 +1616,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting", "Unit": "cpu_core" }, { @@ -1527,7 +1668,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.ANY@", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100", @@ -1538,7 +1679,7 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 13", + "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", "Unit": "cpu_core" }, @@ -1579,7 +1720,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw", "Unit": "cpu_core" @@ -1600,7 +1741,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw", "Unit": "cpu_core" @@ -1649,14 +1790,14 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw", "Unit": "cpu_core" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / duration_time", + "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw", "Unit": "cpu_core" @@ -1678,13 +1819,13 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS.DEMAND_DATA_RD@", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency", "Unit": "cpu_core" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp", "Unit": "cpu_core" @@ -1726,6 +1867,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "cpu_core@L2_LINES_OUT.USELESS_HWPF@ / (cpu_core@L2_LINES_OUT.SILENT@ + cpu_core@L2_LINES_OUT.NON_SILENT@)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15", + "Unit": "cpu_core" + }, + { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", "MetricGroup": "Fed;MemoryTLB", @@ -1733,6 +1882,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05", + "Unit": "cpu_core" + }, + { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", "MetricGroup": "Mem;MemoryTLB", @@ -1748,6 +1905,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret", + "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05", + "Unit": "cpu_core" + }, + { "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED@ / cpu_core@INST_RETIRED.ANY@", "MetricGroup": "Mem;MemoryTLB", @@ -1755,8 +1920,8 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "BriefDescription": "", + "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute", "Unit": "cpu_core" @@ -1787,20 +1952,20 @@ "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire", "Unit": "cpu_core" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", @@ -1816,7 +1981,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency", "Unit": "cpu_core" @@ -1837,15 +2002,15 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_HAC_ARB_TRK_REQUESTS.ALL + UNC_HAC_ARB_COH_TRK_REQUESTS.ALL) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_HAC_ARB_TRK_REQUESTS.ALL + UNC_HAC_ARB_COH_TRK_REQUESTS.ALL) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / duration_time", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * cpu_core@FP_ARITH_INST_RETIRED.4_FLOPS@ + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width", @@ -1853,22 +2018,23 @@ }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000", "Unit": "cpu_core" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "OS", "MetricName": "tma_info_system_kernel_utilization", "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", @@ -1876,13 +2042,28 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", + "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@thresh\\=0x1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", "Unit": "cpu_core" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@ / cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power", + "Unit": "cpu_core" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - cpu_core@CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE@ / cpu_core@CPU_CLK_UNHALTED.REF_DISTRIBUTED@ if #SMT_on else 0)", "MetricGroup": "SMT", @@ -1897,6 +2078,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / cpu_core@CPU_CLK_UNHALTED.REF_TSC@", "MetricGroup": "Power", @@ -1904,7 +2093,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks", @@ -1915,6 +2104,7 @@ "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr", "Unit": "cpu_core" }, { @@ -1922,7 +2112,7 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage", "Unit": "cpu_core" }, { @@ -1934,14 +2124,14 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "cpu_core@TOPDOWN.SLOTS@", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization", "Unit": "cpu_core" @@ -1959,7 +2149,16 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 9", + "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { @@ -1968,7 +2167,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1977,8 +2176,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1987,8 +2186,8 @@ "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1997,28 +2196,28 @@ "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2027,8 +2226,18 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2037,18 +2246,18 @@ "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", + "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2057,19 +2266,19 @@ "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2088,7 +2297,7 @@ "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2097,16 +2306,43 @@ "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2117,7 +2353,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2128,17 +2364,17 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2147,34 +2383,34 @@ "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -2188,7 +2424,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2197,8 +2433,8 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2213,22 +2449,31 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", + "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2238,7 +2483,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2247,7 +2492,7 @@ "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2263,20 +2508,20 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2286,7 +2531,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2296,7 +2541,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2306,7 +2551,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2316,27 +2561,27 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_thread_clks)", + "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "max((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY_RESOURCE@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks, 1) * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks", + "MetricExpr": "max(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2345,7 +2590,7 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2356,8 +2601,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2367,18 +2612,28 @@ "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%", "Unit": "cpu_core" }, { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks", + "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", + "MetricName": "tma_ret_mispredicts", + "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", - "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", + "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", - "MetricgroupNoGroup": "TopdownL1", + "MetricgroupNoGroup": "TopdownL1;Default", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2388,7 +2643,7 @@ "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2398,8 +2653,8 @@ "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", + "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2409,38 +2664,38 @@ "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks", + "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2449,8 +2704,8 @@ "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2459,18 +2714,18 @@ "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2489,7 +2744,7 @@ "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2498,7 +2753,34 @@ "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2507,7 +2789,7 @@ "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2517,7 +2799,7 @@ "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2527,8 +2809,8 @@ "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%", "Unit": "cpu_core" } diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json index 53d23d8decc6..46a21776a4e9 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json @@ -1,5 +1,15 @@ [ { + "BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. the event also counts for Machine Ordering count.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc1", + "EventName": "ASSISTS.HARDWARE", + "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.", + "SampleAfterValue": "100003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { "BriefDescription": "ASSISTS.PAGE_FAULT", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", @@ -19,6 +29,28 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000004", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", @@ -96,6 +128,28 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x800000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x400000010000", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json index bc806c7330f4..265f6c5a0248 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "Counts the number of cycles when any of the dividers are active.", + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xcd", @@ -54,7 +54,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009", "Unit": "cpu_core" @@ -73,7 +72,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11", @@ -84,7 +82,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10", @@ -104,7 +101,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1", @@ -124,7 +120,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40", @@ -144,7 +139,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80", @@ -160,6 +154,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef", + "Unit": "cpu_atom" + }, + { "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL", "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", @@ -183,7 +186,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2", @@ -203,24 +205,49 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of near taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xc0", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Taken branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of near relative CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfd", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of near relative JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_JMP", + "SampleAfterValue": "200003", + "UMask": "0xdf", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", @@ -234,7 +261,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "400009", "Unit": "cpu_core" @@ -244,7 +270,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x44", "Unit": "cpu_core" @@ -263,7 +288,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11", @@ -274,7 +298,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x51", "Unit": "cpu_core" @@ -284,7 +307,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "400009", "UMask": "0x10", @@ -295,7 +317,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x50", "Unit": "cpu_core" @@ -314,7 +335,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1", @@ -325,7 +345,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x41", "Unit": "cpu_core" @@ -344,7 +363,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80", @@ -364,7 +382,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "400009", "UMask": "0x2", @@ -375,7 +392,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x42", "Unit": "cpu_core" @@ -385,12 +401,20 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", - "PEBS": "1", "SampleAfterValue": "100003", "UMask": "0xc0", "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", @@ -404,7 +428,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "UMask": "0x20", @@ -415,7 +438,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", - "PEBS": "1", "SampleAfterValue": "400009", "UMask": "0x60", "Unit": "cpu_core" @@ -425,7 +447,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8", @@ -445,7 +466,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x48", "Unit": "cpu_core" @@ -771,7 +791,6 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" @@ -780,7 +799,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1", @@ -799,7 +817,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "Unit": "cpu_core" @@ -809,7 +826,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" @@ -819,7 +835,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions", "SampleAfterValue": "2000003", "UMask": "0x2", @@ -829,7 +844,6 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1", @@ -840,7 +854,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PEBS": "1", "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8", @@ -1177,6 +1190,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "100003", + "UMask": "0x8", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json index 1ac5b5ef8094..b3f9c588b410 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json @@ -5,6 +5,6 @@ "EventCode": "0xff", "EventName": "UNC_CLOCK.SOCKET", "PerPkg": "1", - "Unit": "CLOCK" + "Unit": "CNCU" } ] diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/cache.json b/tools/perf/pmu-events/arch/x86/rocketlake/cache.json index 2e93b7835b41..791fa526d192 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/cache.json @@ -75,11 +75,11 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -251,7 +251,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81" @@ -262,7 +261,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82" @@ -273,7 +271,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83" @@ -284,7 +281,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21" @@ -295,7 +291,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41" @@ -306,7 +301,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42" @@ -317,7 +311,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11" @@ -328,7 +321,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12" @@ -339,7 +331,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2" @@ -350,7 +341,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4" @@ -361,7 +351,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -372,7 +361,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" @@ -383,7 +371,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4" @@ -394,7 +381,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -405,7 +391,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -416,7 +401,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8" @@ -427,7 +411,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2" @@ -438,7 +421,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10" @@ -449,7 +431,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4" @@ -460,7 +441,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -911,6 +891,16 @@ "UMask": "0x8" }, { + "BriefDescription": "Cycles with outstanding code read requests pending.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Cycles with outstanding code read requests pending. Code Read requests include both cacheable and non-cacheable Code Reads. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { "BriefDescription": "Cycles where at least 1 outstanding Demand RFO request is pending.", "Counter": "0,1,2,3", "CounterMask": "1", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/frontend.json b/tools/perf/pmu-events/arch/x86/rocketlake/frontend.json index e7c7d4d4152d..7afa2436d584 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/frontend.json @@ -44,7 +44,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -56,7 +55,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -68,7 +66,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -80,7 +77,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -92,7 +88,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -104,7 +99,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x500106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -116,7 +110,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x508006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -128,7 +121,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x501006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -140,7 +132,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x500206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -152,7 +143,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x510006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -164,7 +154,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -176,7 +165,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x502006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -188,7 +176,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x500406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -200,7 +187,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x520006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -212,7 +198,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x504006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -224,7 +209,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x500806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -236,7 +220,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/memory.json b/tools/perf/pmu-events/arch/x86/rocketlake/memory.json index f73035f44330..abaf3f4f9d63 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/memory.json @@ -88,7 +88,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1" @@ -101,7 +100,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -114,7 +112,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1" @@ -127,7 +124,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -140,7 +136,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1" @@ -153,7 +148,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1" @@ -166,7 +160,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1" @@ -179,7 +172,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -287,17 +279,16 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4" }, { - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/rocketlake/metricgroups.json index 3a88260194d1..80ca8021f2de 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/metricgroups.json @@ -37,6 +37,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -83,7 +84,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -93,6 +96,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_issue2P": "Metrics related by the issue $issue2P", "tma_issueBM": "Metrics related by the issue $issueBM", "tma_issueBW": "Metrics related by the issue $issueBW", @@ -112,10 +116,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -128,5 +135,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/pipeline.json b/tools/perf/pmu-events/arch/x86/rocketlake/pipeline.json index 4fdf07c7beb7..44659f26cbab 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/pipeline.json @@ -10,6 +10,15 @@ "UMask": "0x9" }, { + "BriefDescription": "ARITH.FP_DIVIDER_ACTIVE", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", @@ -23,7 +32,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009" }, @@ -32,7 +40,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -42,7 +49,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -52,7 +58,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -62,7 +67,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -72,7 +76,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -82,7 +85,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" @@ -92,7 +94,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -102,7 +103,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -112,7 +112,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "50021" }, @@ -121,7 +120,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x11" @@ -131,7 +129,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "50021", "UMask": "0x10" @@ -141,7 +138,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -151,7 +147,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", "SampleAfterValue": "50021", "UMask": "0x80" @@ -161,7 +156,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "50021", "UMask": "0x2" @@ -171,7 +165,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -181,7 +174,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "50021", "UMask": "0x8" @@ -377,7 +369,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -387,7 +378,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003" }, @@ -396,7 +386,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -404,7 +393,6 @@ "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json index 13474af97786..cfda8956353e 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json @@ -89,12 +89,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -106,7 +106,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -129,11 +129,104 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -147,7 +240,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -155,8 +248,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -164,8 +257,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -173,18 +266,66 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(29 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((32.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -194,25 +335,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "23.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(27 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -221,7 +362,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -231,8 +372,8 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -241,7 +382,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -249,44 +390,44 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "32.5 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -296,7 +437,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -306,16 +447,16 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -324,7 +465,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -333,7 +474,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -341,7 +490,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -350,7 +499,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -359,8 +508,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -368,8 +517,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -377,7 +526,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -389,17 +538,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -407,41 +556,41 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 5 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -455,34 +604,13 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" }, { "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "tma_info_botlnk_l0_core_bound_likely", - "MetricGroup": "Cor;Metric;SMT", - "MetricName": "tma_info_botlnk_core_bound_likely", - "MetricThreshold": "tma_info_botlnk_core_bound_likely > 0.5" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd))", - "MetricGroup": "DSBmiss;Fed;Scaled_Slots;tma_issueFB", - "MetricName": "tma_info_botlnk_dsb_misses", - "MetricThreshold": "tma_info_botlnk_dsb_misses > 10" - }, - { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;Scaled_Slots;tma_issueFL", - "MetricName": "tma_info_botlnk_ic_misses", - "MetricThreshold": "tma_info_botlnk_ic_misses > 5" - }, - { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", "MetricGroup": "Cor;SMT", @@ -491,8 +619,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" @@ -500,7 +628,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -509,108 +637,10 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -671,11 +701,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -688,20 +718,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -737,7 +767,13 @@ "MetricName": "tma_info_frontend_lsd_coverage" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -755,7 +791,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -763,7 +799,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -771,7 +807,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -779,7 +815,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -787,7 +823,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -795,7 +831,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -840,7 +876,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -850,22 +886,10 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "\"Bus lock\" per kilo instruction", - "MetricExpr": "tma_info_memory_mix_bus_lock_pki", - "MetricGroup": "Mem;Metric", - "MetricName": "tma_info_memory_bus_lock_pki" - }, - { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "tma_info_memory_tlb_code_stlb_mpki", - "MetricGroup": "Fed;MemoryTLB;Metric", - "MetricName": "tma_info_memory_code_stlb_mpki" - }, - { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "tma_info_memory_l1d_cache_fill_bw", "MetricGroup": "Mem;MemoryBW", @@ -890,12 +914,6 @@ "MetricName": "tma_info_memory_core_l3_cache_fill_bw_2t" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "tma_info_memory_latency_data_l2_mlp", - "MetricGroup": "Memory_BW;Metric;Offcore", - "MetricName": "tma_info_memory_data_l2_mlp" - }, - { "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheHits;Mem", @@ -903,17 +921,11 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_memory_l1d_cache_fill_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW", - "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t" - }, - { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheHits;Mem", @@ -927,17 +939,11 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_memory_l2_cache_fill_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW", - "MetricName": "tma_info_memory_l2_cache_fill_bw_2t" - }, - { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheHits;Mem", @@ -975,29 +981,17 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_memory_l3_cache_access_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW;Offcore", - "MetricName": "tma_info_memory_l3_cache_access_bw_2t" - }, - { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_memory_l3_cache_fill_bw", - "MetricGroup": "Core_Metric;Mem;MemoryBW", - "MetricName": "tma_info_memory_l3_cache_fill_bw_2t" - }, - { "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", "MetricGroup": "Mem", @@ -1011,53 +1005,23 @@ }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", - "MetricExpr": "tma_info_memory_load_l2_miss_latency", - "MetricGroup": "Memory_Lat;Offcore", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, { - "BriefDescription": "Average Latency for L3 cache miss demand Loads", - "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_memory_latency_load_l3_miss_latency" - }, - { - "BriefDescription": "Average Latency for L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Clocks_Latency;Memory_Lat;Offcore", - "MetricName": "tma_info_memory_load_l2_miss_latency" - }, - { - "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", - "MetricGroup": "Memory_BW;Metric;Offcore", - "MetricName": "tma_info_memory_load_l2_mlp" - }, - { - "BriefDescription": "Average Latency for L3 cache miss demand Loads", - "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x0@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "MetricGroup": "Clocks_Latency;Memory_Lat;Offcore", - "MetricName": "tma_info_memory_load_l3_miss_latency" - }, - { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", "MetricGroup": "Mem;MemoryBound;MemoryLat", "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "tma_info_memory_tlb_load_stlb_mpki", - "MetricGroup": "Mem;MemoryTLB;Metric", - "MetricName": "tma_info_memory_load_stlb_mpki" - }, - { "BriefDescription": "\"Bus lock\" per kilo instruction", "MetricExpr": "1e3 * SQ_MISC.BUS_LOCK / INST_RETIRED.ANY", "MetricGroup": "Mem", @@ -1065,7 +1029,7 @@ }, { "BriefDescription": "Un-cacheable retired load per kilo instruction", - "MetricExpr": "tma_info_memory_uc_load_pki", + "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY", "MetricGroup": "Mem", "MetricName": "tma_info_memory_mix_uc_load_pki" }, @@ -1077,17 +1041,11 @@ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "tma_info_memory_tlb_page_walks_utilization", - "MetricGroup": "Core_Metric;Mem;MemoryTLB", - "MetricName": "tma_info_memory_page_walks_utilization", - "MetricThreshold": "tma_info_memory_page_walks_utilization > 0.5" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "tma_info_memory_tlb_store_stlb_mpki", - "MetricGroup": "Mem;MemoryTLB;Metric", - "MetricName": "tma_info_memory_store_stlb_mpki" + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15" }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1115,14 +1073,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Un-cacheable retired load per kilo instruction", - "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY", - "MetricGroup": "Mem;Metric", - "MetricName": "tma_info_memory_uc_load_pki" - }, - { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1149,18 +1101,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1178,14 +1130,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -1195,13 +1147,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1225,11 +1178,24 @@ "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1237,7 +1203,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1245,7 +1211,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1260,13 +1226,20 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1275,14 +1248,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1292,13 +1266,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1314,33 +1288,41 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 7.5" + "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1349,8 +1331,17 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1359,17 +1350,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "9 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(12.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1377,18 +1368,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1405,7 +1396,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1413,16 +1404,40 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1432,7 +1447,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", "ScaleUnit": "100%" }, { @@ -1442,16 +1457,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1459,8 +1474,8 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1470,11 +1485,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1488,7 +1503,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1496,8 +1511,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1511,19 +1526,27 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { @@ -1531,8 +1554,8 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1540,7 +1563,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1555,19 +1578,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1603,7 +1626,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1611,8 +1634,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { @@ -1620,8 +1643,8 @@ "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1629,7 +1652,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1638,7 +1661,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1647,14 +1670,14 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1667,7 +1690,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1676,7 +1699,7 @@ "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -1685,8 +1708,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1695,17 +1718,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1713,8 +1736,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1723,17 +1746,17 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1750,7 +1773,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1758,7 +1781,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1766,7 +1813,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -1775,7 +1822,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1784,8 +1831,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/rocketlake/uncore-interconnect.json index 3946d4e01a8c..a0057f8d815e 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/uncore-interconnect.json @@ -39,16 +39,6 @@ "Unit": "ARB" }, { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", - "Counter": "1", - "EventCode": "0x81", - "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", - "Experimental": "1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk until deallocation. Accounts for Coherent and non-coherent traffic.", "Counter": "0", "EventCode": "0x80", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/rocketlake/uncore-other.json index cc8110ac020c..1ac5b5ef8094 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/uncore-other.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", "Counter": "FIXED", "EventCode": "0xff", "EventName": "UNC_CLOCK.SOCKET", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/rocketlake/virtual-memory.json index 3ff51040f84f..9df790d4361f 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/virtual-memory.json @@ -28,6 +28,15 @@ "UMask": "0xe" }, { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "Counter": "0,1,2,3", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", "Counter": "0,1,2,3", "EventCode": "0x08", @@ -83,6 +92,15 @@ "UMask": "0xe" }, { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "Counter": "0,1,2,3", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", "Counter": "0,1,2,3", "EventCode": "0x49", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json index eec7bf6ebd53..e35dbb7c2ccd 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json @@ -92,11 +92,11 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, @@ -311,7 +311,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81" @@ -322,7 +321,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82" @@ -333,7 +331,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83" @@ -344,7 +341,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21" @@ -355,7 +351,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41" @@ -366,7 +361,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42" @@ -377,7 +371,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11" @@ -388,7 +381,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12" @@ -408,7 +400,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", "SampleAfterValue": "20011", "UMask": "0x4" @@ -419,7 +410,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -430,7 +420,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" @@ -441,7 +430,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2" @@ -452,7 +440,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", - "PEBS": "1", "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -463,7 +450,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2" }, @@ -473,7 +459,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", - "PEBS": "1", "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -484,7 +469,6 @@ "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4" }, @@ -493,7 +477,6 @@ "Counter": "0,1,2,3", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.", "SampleAfterValue": "100007", "UMask": "0x10" @@ -504,7 +487,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", "SampleAfterValue": "100007", "UMask": "0x4" @@ -515,7 +497,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -526,7 +507,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -537,7 +517,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8" @@ -548,7 +527,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2" @@ -559,7 +537,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10" @@ -570,7 +547,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4" @@ -581,7 +557,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -592,7 +567,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.LOCAL_PMM", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.", "SampleAfterValue": "1000003", "UMask": "0x80" diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json index f6e3e40a3b20..bf68493d4509 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json @@ -41,7 +41,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -53,7 +52,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -65,7 +63,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -77,7 +74,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -89,7 +85,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -101,7 +96,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x600106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -113,7 +107,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x608006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -125,7 +118,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x601006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -137,7 +129,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x600206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -149,7 +140,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x610006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -161,7 +151,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -173,7 +162,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x602006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -185,7 +173,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x600406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -197,7 +184,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x620006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -209,7 +195,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x604006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -221,7 +206,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x600806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -233,7 +217,6 @@ "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", "MSRValue": "0x8", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x1" }, @@ -244,7 +227,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -256,7 +238,6 @@ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", "MSRValue": "0x17", - "PEBS": "1", "SampleAfterValue": "100007", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json index 2ea19539291b..41d4120d4dae 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json @@ -63,7 +63,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "53", "UMask": "0x1" @@ -76,7 +75,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1" @@ -89,7 +87,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -102,7 +99,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1" @@ -115,7 +111,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -128,7 +123,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1" @@ -141,7 +135,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1" @@ -154,7 +147,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1" @@ -167,7 +159,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -178,7 +169,6 @@ "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", - "PEBS": "2", "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", "SampleAfterValue": "1000003", "UMask": "0x2" @@ -305,17 +295,16 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4" }, { - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json index e1de6c2675c4..9129fb7b7ce4 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json @@ -40,6 +40,7 @@ "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -86,7 +87,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -96,6 +99,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_int_operations_group": "Metrics contributing to tma_int_operations category", "tma_issue2P": "Metrics related by the issue $issue2P", "tma_issueBM": "Metrics related by the issue $issueBM", @@ -116,10 +120,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_bandwidth_group": "Metrics contributing to tma_mem_bandwidth category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", @@ -133,5 +140,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json index 5d5811f26151..50cacfbbc7cf 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json @@ -62,7 +62,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009" }, @@ -71,7 +70,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -81,7 +79,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -91,7 +88,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -101,7 +97,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -111,7 +106,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -121,7 +115,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" @@ -131,7 +124,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -141,7 +133,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -151,7 +142,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "400009" }, @@ -160,7 +150,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -170,7 +159,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -180,7 +168,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -190,7 +177,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -200,7 +186,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "400009", "UMask": "0x2" @@ -210,7 +195,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -220,7 +204,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -469,7 +452,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -479,7 +461,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003" }, @@ -488,7 +469,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -497,7 +477,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2" @@ -506,7 +485,6 @@ "BriefDescription": "Precise instruction retired with PEBS precise-distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -516,7 +494,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", - "PEBS": "1", "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8" diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 2b3b013ccb06..b59fae4a887d 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -34,7 +34,7 @@ "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -55,85 +55,85 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS * 4 / 1e6 / duration_time", "MetricName": "iio_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS * 4 / 1e6 / duration_time", "MetricName": "iio_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_remote", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_remote", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache.", + "BriefDescription": "Percentage of inbound full cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM / UNC_CHA_TOR_INSERTS.IO_ITOM", "MetricName": "io_percent_of_inbound_full_writes_that_miss_l3", "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache.", + "BriefDescription": "Percentage of inbound partial cacheline writes initiated by end device controllers that miss the L3 cache", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_RFO) / (UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_RFO)", "MetricName": "io_percent_of_inbound_partial_writes_that_miss_l3", "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache.", + "BriefDescription": "Percentage of inbound reads initiated by end device controllers that miss the L3 cache", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR / UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", "MetricName": "io_percent_of_inbound_reads_that_miss_l3", "ScaleUnit": "100%" @@ -142,14 +142,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -237,25 +237,25 @@ "ScaleUnit": "1ns" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_write", "ScaleUnit": "1MB/s" @@ -285,19 +285,19 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM).", + "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM)", "MetricExpr": "(UNC_CHA_DIR_UPDATE.HA + UNC_CHA_DIR_UPDATE.TOR + UNC_M2M_DIRECTORY_UPDATE.ANY) * 64 / 1e6 / duration_time", "MetricName": "memory_extra_write_bw_due_to_directory_updates", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -360,7 +360,7 @@ "ScaleUnit": "1per_instr" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -372,7 +372,7 @@ "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks", "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_amx_busy", - "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -380,12 +380,12 @@ "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists", "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", @@ -395,7 +395,7 @@ { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -411,18 +411,111 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -430,24 +523,24 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)", "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c01_wait", - "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)", "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks", "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_c02_wait", - "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -455,7 +548,7 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", "ScaleUnit": "100%" }, @@ -464,17 +557,65 @@ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -485,24 +626,24 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -511,17 +652,17 @@ "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)", + "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -530,7 +671,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -538,44 +679,44 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -586,7 +727,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -597,16 +738,16 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -615,7 +756,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -624,7 +765,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -632,8 +781,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -641,8 +790,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -650,8 +799,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -659,8 +808,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -668,8 +817,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -680,27 +829,27 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .). Sample with: UOPS_RETIRED.HEAVY", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, { @@ -708,40 +857,40 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 6 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -755,7 +904,7 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" @@ -769,15 +918,15 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -785,104 +934,10 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu@RS.EMPTY\\,umask\\=1@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -943,11 +998,11 @@ "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -960,20 +1015,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -1003,14 +1058,20 @@ "MetricName": "tma_info_frontend_l2mpki_code_all" }, { + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed", "MetricName": "tma_info_frontend_unknown_branch_cost", - "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node." + "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -1028,7 +1089,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -1036,7 +1097,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -1044,7 +1105,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -1052,7 +1113,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -1060,7 +1121,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)", @@ -1068,7 +1129,7 @@ "MetricGroup": "Flops;FpScalar;InsType;Server", "MetricName": "tma_info_inst_mix_iparith_scalar_hp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -1076,7 +1137,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -1121,7 +1182,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -1131,7 +1192,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 13", + "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1178,7 +1239,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -1196,7 +1257,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -1238,13 +1299,13 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -1263,12 +1324,12 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, @@ -1322,25 +1383,32 @@ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15" + }, + { "BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket", - "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / duration_time", + "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_dram_bw", - "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW." + "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW" }, { "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)", - "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / duration_time", + "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_l3m_bw", - "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW." + "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW" }, { "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)", - "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / duration_time", + "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC", "MetricName": "tma_info_memory_soc_r2c_offcore_bw", - "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches." + "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches" }, { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", @@ -1369,7 +1437,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1390,18 +1458,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "MicroSeq;Pipeline;Ret", "MetricName": "tma_info_pipeline_strings_cycles", "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1" @@ -1415,7 +1483,7 @@ }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1433,28 +1501,28 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.8_FLOPS) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.8_FLOPS) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_read_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e9 / duration_time", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_write_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU" @@ -1464,13 +1532,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1481,44 +1550,45 @@ }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { + "BriefDescription": "Fraction of Uncore cycles where requests got rejected due to duplicate address already in IRQ ingress queue in the cache homing agent", + "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS", + "MetricGroup": "LockCont;MemOffcore;Server;SoC", + "MetricName": "tma_info_system_mem_irq_duplicate_address", + "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)" + }, + { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", - "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@ if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryLat;Server;SoC", - "MetricName": "tma_info_system_mem_pmm_read_latency", - "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" - }, - { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_read_bw" + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", - "MetricGroup": "MemOffcore;MemoryBW;Server;SoC", - "MetricName": "tma_info_system_pmm_write_bw" + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1528,11 +1598,18 @@ }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "uncore_cha_0@event\\=0x1@", + "MetricExpr": "cha_0@event\\=0x0@", "MetricGroup": "SoC", "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -1540,7 +1617,7 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, @@ -1551,7 +1628,7 @@ "MetricName": "tma_info_system_upi_data_transmit_bw" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1560,14 +1637,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1577,13 +1655,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1599,7 +1677,15 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 9" + "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", @@ -1607,7 +1693,7 @@ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_int_operations", "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain", "ScaleUnit": "100%" }, { @@ -1615,8 +1701,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", - "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1624,8 +1710,8 @@ "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", - "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1633,26 +1719,26 @@ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1660,8 +1746,17 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1669,17 +1764,17 @@ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1687,19 +1782,19 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "DefaultMetricgroupName": "TopdownL2", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1716,7 +1811,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1724,24 +1819,48 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1753,24 +1872,24 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)", "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", "MetricName": "tma_mba_stalls", - "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1778,32 +1897,32 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "DefaultMetricgroupName": "TopdownL2", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2;Default", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", - "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1816,7 +1935,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1824,8 +1943,8 @@ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1838,21 +1957,29 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1861,7 +1988,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", "ScaleUnit": "100%" }, { @@ -1869,7 +1996,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1883,19 +2010,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1904,16 +2031,7 @@ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", - "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_pmm_bound", - "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost", "ScaleUnit": "100%" }, { @@ -1922,7 +2040,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1931,7 +2049,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1940,25 +2058,25 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_thread_clks)", + "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(cpu@RS.EMPTY\\,umask\\=1@ - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", + "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1966,7 +2084,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1976,8 +2094,8 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6", "ScaleUnit": "100%" }, { @@ -1986,32 +2104,32 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2024,7 +2142,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -2033,8 +2151,8 @@ "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_shuffles_256b", - "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.", + "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers", "ScaleUnit": "100%" }, { @@ -2043,7 +2161,7 @@ "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -2052,8 +2170,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -2061,17 +2179,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -2079,8 +2197,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -2088,17 +2206,17 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -2115,7 +2233,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -2123,7 +2241,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -2131,7 +2273,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -2140,7 +2282,7 @@ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, @@ -2149,8 +2291,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json index 91013ced74aa..aab082ff9402 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json @@ -201,7 +201,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -214,7 +214,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -227,7 +227,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -240,7 +240,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -253,7 +253,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -266,7 +266,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -279,7 +279,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -292,7 +292,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -316,7 +316,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7000001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -329,7 +329,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 1", - "UMask": "0x7000002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -342,7 +342,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7000004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -355,7 +355,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 3", - "UMask": "0x7000008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -368,7 +368,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7000010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -381,7 +381,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 1", - "UMask": "0x7000020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -394,7 +394,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7000040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -407,7 +407,7 @@ "PerPkg": "1", "PortMask": "0x0000", "PublicDescription": "x4 card is plugged in to slot 3", - "UMask": "0x7000080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -431,7 +431,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -443,7 +443,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -455,7 +455,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -467,7 +467,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -479,7 +479,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -491,7 +491,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -503,7 +503,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -515,7 +515,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -662,7 +662,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -675,7 +675,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -688,7 +688,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7004008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -701,7 +701,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -714,7 +714,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7010008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -727,7 +727,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7020008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -740,7 +740,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7040008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -753,7 +753,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7080008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -766,7 +766,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -779,7 +779,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -792,7 +792,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -805,7 +805,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -818,7 +818,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -831,7 +831,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -844,7 +844,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -857,7 +857,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -974,7 +974,6 @@ "Counter": "0,1", "EventCode": "0x83", "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS", - "Experimental": "1", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x00ff", @@ -1082,7 +1081,6 @@ "Counter": "0,1", "EventCode": "0x83", "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS", - "Experimental": "1", "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x00ff", @@ -1299,7 +1297,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1351,7 +1349,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1364,7 +1362,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1377,7 +1375,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1390,7 +1388,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1403,7 +1401,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1416,7 +1414,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1429,7 +1427,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1442,7 +1440,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1962,7 +1960,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : PCIe Request complete : Only for posted requests : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1975,7 +1973,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : Writing line : Only for posted requests : Only for posted requests", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1988,7 +1986,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : Issuing final read or write of line : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -2001,7 +1999,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Request Ownership : Passing data to be written : Only for posted requests : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -2014,7 +2012,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Processing response from IOMMU : Passing data to be written : Only for posted requests", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -2026,7 +2024,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x00FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2039,7 +2037,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Processing response from IOMMU : Request Ownership : Only for posted requests", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -2052,7 +2050,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "Processing response from IOMMU : Writing line : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -2065,7 +2063,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -2091,7 +2089,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -2104,7 +2102,7 @@ "PerPkg": "1", "PortMask": "0x00FF", "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -2309,7 +2307,7 @@ "PerPkg": "1", "PortMask": "0x0001", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2322,7 +2320,7 @@ "PerPkg": "1", "PortMask": "0x0002", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2335,7 +2333,7 @@ "PerPkg": "1", "PortMask": "0x0004", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2348,7 +2346,7 @@ "PerPkg": "1", "PortMask": "0x0008", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2361,7 +2359,7 @@ "PerPkg": "1", "PortMask": "0x0010", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2374,7 +2372,7 @@ "PerPkg": "1", "PortMask": "0x0020", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2387,7 +2385,7 @@ "PerPkg": "1", "PortMask": "0x0040", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -2400,7 +2398,7 @@ "PerPkg": "1", "PortMask": "0x0080", "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" }, { diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json index 04802e254e51..072df00aff92 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json @@ -1,5 +1,92 @@ [ { + "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "DL1.DIRTY_EVICTION", + "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches. Does not count evictions or dirty writebacks caused by snoops. Does not count a replacement unless a (dirty) line was written back.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.E", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.F", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.M", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.S", + "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill. Increments on the core that brought the line in originally.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.HIT", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject short and long rejects, per core event", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_REQUEST.REJECTS", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", @@ -35,7 +122,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT", @@ -43,7 +130,7 @@ "UMask": "0x6" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which missed all the caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS", @@ -68,7 +155,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT", @@ -76,7 +163,7 @@ "UMask": "0x6" }, { - "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", @@ -84,6 +171,14 @@ "UMask": "0x78" }, { + "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x34", + "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd3", @@ -336,6 +431,33 @@ "UMask": "0x42" }, { + "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS", + "SampleAfterValue": "200003", + "UMask": "0x13" + }, + { + "BriefDescription": "Counts the number of load uops retired that miss in the second Level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "200003", + "UMask": "0x11" + }, + { + "BriefDescription": "Counts the number of store uops retired that miss in the second level TLB.", + "Counter": "0,1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "200003", + "UMask": "0x12" + }, + { "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/counter.json b/tools/perf/pmu-events/arch/x86/sierraforest/counter.json index e57e3bf98b2a..a92c75109e6a 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/counter.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/counter.json @@ -20,6 +20,16 @@ "CountersNumGeneric": "4" }, { + "Unit": "CXLCM", + "CountersNumFixed": "0", + "CountersNumGeneric": 8 + }, + { + "Unit": "CXLDP", + "CountersNumFixed": "0", + "CountersNumGeneric": 4 + }, + { "Unit": "B2HOT", "CountersNumFixed": "0", "CountersNumGeneric": 4 @@ -52,26 +62,16 @@ { "Unit": "PCU", "CountersNumFixed": "0", - "CountersNumGeneric": 4 + "CountersNumGeneric": "4" }, { "Unit": "CHACMS", "CountersNumFixed": "0", - "CountersNumGeneric": 4 + "CountersNumGeneric": "4" }, { "Unit": "MDF", "CountersNumFixed": "0", "CountersNumGeneric": 4 - }, - { - "Unit": "CXLCM", - "CountersNumFixed": "0", - "CountersNumGeneric": 8 - }, - { - "Unit": "CXLDP", - "CountersNumFixed": "0", - "CountersNumGeneric": 4 } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/frontend.json b/tools/perf/pmu-events/arch/x86/sierraforest/frontend.json index 7cdf611efb23..fef5cba533bb 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/frontend.json @@ -31,5 +31,13 @@ "EventName": "ICACHE.MISSES", "SampleAfterValue": "200003", "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "MS_DECODED.MS_BUSY", + "SampleAfterValue": "1000003", + "UMask": "0x4" } ] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/other.json b/tools/perf/pmu-events/arch/x86/sierraforest/other.json index 28f9a4c3ea84..4c77dac8ec78 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/other.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/other.json @@ -19,6 +19,26 @@ "UMask": "0x1" }, { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json index b67c0c89054d..df2c7bb474a0 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "Counts the number of cycles when any of the dividers are active.", + "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.", "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xcd", @@ -57,6 +57,14 @@ "UMask": "0xfb" }, { + "BriefDescription": "Counts the number of near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef" + }, + { "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL", "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", @@ -82,6 +90,30 @@ "UMask": "0xf7" }, { + "BriefDescription": "Counts the number of near taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "200003", + "UMask": "0xc0" + }, + { + "BriefDescription": "Counts the number of near relative CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_CALL", + "SampleAfterValue": "200003", + "UMask": "0xfd" + }, + { + "BriefDescription": "Counts the number of near relative JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.REL_JMP", + "SampleAfterValue": "200003", + "UMask": "0xdf" + }, + { "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", @@ -122,6 +154,14 @@ "UMask": "0xfb" }, { + "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xef" + }, + { "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", @@ -185,7 +225,6 @@ "BriefDescription": "Fixed Counter: Counts the number of instructions retired", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -237,8 +276,9 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "BriefDescription": "This event is deprecated.", "Counter": "0,1,2,3,4,5,6,7", + "Deprecated": "1", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SLOW", "SampleAfterValue": "20003", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json index b881b1958f11..83c86afd2960 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/srf-metrics.json @@ -1,5 +1,12 @@ [ { + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", + "ScaleUnit": "100%" + }, + { "BriefDescription": "C1 residency percent per core", "MetricExpr": "cstate_core@c1\\-residency@ / TSC", "MetricGroup": "Power", @@ -7,17 +14,24 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per module", - "MetricExpr": "cstate_module@c6\\-residency@ / TSC", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", "MetricGroup": "Power", - "MetricName": "C6_Module_Residency", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { @@ -28,7 +42,21 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -49,67 +77,67 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_2nd_level_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth observed by the integrated I/O traffic contoller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth observed by the integrated I/O traffic contoller (IIO) of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS * 4 / 1e6 / duration_time", "MetricName": "iio_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth observed by the integrated I/O traffic controller (IIO) of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS * 4 / 1e6 / duration_time", "MetricName": "iio_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the local CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from a remote CPU socket", "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_read_remote", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the local CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_local", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to a remote CPU socket", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE) * 64 / 1e6 / duration_time", "MetricName": "io_bandwidth_write_remote", "ScaleUnit": "1MB/s" @@ -118,14 +146,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_2nd_level_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -177,25 +205,25 @@ "ScaleUnit": "1ns" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_write", "ScaleUnit": "1MB/s" @@ -225,13 +253,13 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_REMOTE)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -260,17 +288,15 @@ { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions", "MetricExpr": "tma_core_bound", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_allocation_restriction", - "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", - "MetricThreshold": "tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count", "ScaleUnit": "100%" @@ -278,104 +304,92 @@ { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", - "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_detect", - "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", - "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", - "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_branch_resteer", - "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)", "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation", "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", - "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls", "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_decode", - "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming", "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", - "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls", "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", - "MetricThreshold": "tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses", "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_bandwidth", - "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations", "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_ifetch_latency", - "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, @@ -405,32 +419,6 @@ }, { "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", - "MetricExpr": "tma_info_bottleneck_dtlb_miss_bound_cycles", - "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss", - "MetricExpr": "tma_info_bottleneck_ifetch_miss_bound_cycles", - "MetricGroup": "Ifetch", - "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles", - "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound" - }, - { - "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss", - "MetricExpr": "tma_info_bottleneck_load_miss_bound_cycles", - "MetricGroup": "Load_Store_Miss", - "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound" - }, - { - "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall", - "MetricExpr": "tma_info_bottleneck_mem_exec_bound_cycles", - "MetricGroup": "Mem_Exec", - "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles", - "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound" - }, - { - "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss", "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE", "MetricGroup": "Cycles", "MetricName": "tma_info_bottleneck_dtlb_miss_bound_cycles", @@ -512,21 +500,6 @@ }, { "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", - "MetricExpr": "tma_info_buffer_stalls_load_buffer_stall_cycles", - "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full", - "MetricExpr": "tma_info_buffer_stalls_mem_rsv_stall_cycles", - "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full", - "MetricExpr": "tma_info_buffer_stalls_store_buffer_stall_cycles", - "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles" - }, - { - "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full", "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE", "MetricName": "tma_info_buffer_stalls_load_buffer_stall_cycles", "ScaleUnit": "100%" @@ -546,7 +519,8 @@ { "BriefDescription": "Cycles Per Instruction", "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY", - "MetricName": "tma_info_core_cpi" + "MetricName": "tma_info_core_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Floating Point Operations Per Cycle", @@ -566,21 +540,6 @@ }, { "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", - "MetricExpr": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit", - "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit" - }, - { - "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3", - "MetricExpr": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit", - "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit" - }, - { - "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3", - "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL", - "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss" - }, - { - "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL", "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit", "ScaleUnit": "100%" @@ -593,24 +552,6 @@ }, { "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", - "MetricExpr": "tma_info_load_miss_bound_loadmissbound_with_l2hit", - "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit" - }, - { - "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3", - "MetricExpr": "tma_info_load_miss_bound_loadmissbound_with_l3hit", - "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit" - }, - { - "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3", - "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL", - "MetricGroup": "load_store_bound", - "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss" - }, - { - "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2", "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL", "MetricGroup": "load_store_bound", "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l2hit", @@ -658,16 +599,6 @@ }, { "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", - "MetricExpr": "tma_info_mem_exec_blocks_loads_with_adressaliasing", - "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing" - }, - { - "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", - "MetricExpr": "tma_info_mem_exec_blocks_loads_with_storefwdblk", - "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk" - }, - { - "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block", "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", "MetricName": "tma_info_mem_exec_blocks_loads_with_adressaliasing", "ScaleUnit": "100%" @@ -680,31 +611,6 @@ }, { "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_l1miss", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_pagewalk", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_stlbhit", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match", - "MetricExpr": "tma_info_mem_exec_bound_loadhead_with_storefwding", - "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding" - }, - { - "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss", "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET", "MetricName": "tma_info_mem_exec_bound_loadhead_with_l1miss", "ScaleUnit": "100%" @@ -760,11 +666,6 @@ }, { "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", - "MetricExpr": "tma_info_serialization_tpause_cycles", - "MetricName": "tma_info_serialization _%_tpause_cycles" - }, - { - "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction", "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)", "MetricName": "tma_info_serialization_tpause_cycles", "ScaleUnit": "100%" @@ -783,14 +684,17 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE", - "MetricGroup": "Summary", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE", "MetricName": "tma_info_system_kernel_utilization" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE", + "MetricName": "tma_info_system_mux" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { @@ -814,102 +718,90 @@ "MetricName": "tma_info_uop_mix_x87_uop_ratio" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses", "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", - "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", - "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops", "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", - "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)", "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", - "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized", "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_other_fb", - "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes", "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group", "MetricName": "tma_predecode", - "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", - "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)", "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", - "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation", "MetricExpr": "tma_backend_bound - tma_core_bound", - "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_resource_bound", - "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1", "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that result in retirement slots", "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "Slots;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", - "MetricThreshold": "tma_retiring > 0.75", "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)", "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", - "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json index f37107373e3b..a779a1a73ea5 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cache.json @@ -10,6 +10,16 @@ "Unit": "CHACMS" }, { + "BriefDescription": "Counts the number of cycles FAST trigger is received from the global FAST distress wire.", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_CHACMS_RING_SRC_THRTL", + "Experimental": "1", + "PerPkg": "1", + "PortMask": "0x000", + "Unit": "CHACMS" + }, + { "BriefDescription": "Number of CHA clock cycles while the event is enabled", "Counter": "0,1,2,3", "EventCode": "0x01", @@ -844,6 +854,26 @@ "Unit": "CHA" }, { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "Counter": "0", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { "BriefDescription": "All TOR Inserts", "Counter": "0,1,2,3", "EventCode": "0x35", @@ -1066,7 +1096,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Code read from local IA that miss the cache", + "BriefDescription": "Code read from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", @@ -1086,7 +1116,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read opt from local IA that miss the cache", + "BriefDescription": "Data read opt from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", @@ -1096,7 +1126,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Data read opt prefetch from local IA that miss the cache", + "BriefDescription": "Data read opt prefetch from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", @@ -1266,7 +1296,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Last level cache prefetch read for ownership from local IA that miss the cache", + "BriefDescription": "Last level cache prefetch read for ownership from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", @@ -1400,7 +1430,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_LOCAL", "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC", + "PublicDescription": "TOR Inserts : Data read opt prefetch from local iA that missed the LLC targeting local memory", "UMask": "0xc8a6fe01", "Unit": "CHA" }, @@ -1410,7 +1440,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_REMOTE", "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC", + "PublicDescription": "TOR Inserts : Data read opt prefetch from local iA that missed the LLC targeting remote memory", "UMask": "0xc8a77e01", "Unit": "CHA" }, @@ -1420,7 +1450,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_REMOTE", "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC", + "PublicDescription": "TOR Inserts : Data read opt from local iA that missed the LLC targeting remote memory", "UMask": "0xc8277e01", "Unit": "CHA" }, @@ -1595,7 +1625,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA that miss the LLC targeting local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", @@ -1624,7 +1654,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting local memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", @@ -1634,7 +1664,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting remote memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", @@ -1644,7 +1674,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA that miss the LLC targeting remote memory", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", @@ -1736,7 +1766,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership from local IA that miss the cache", + "BriefDescription": "Read for ownership from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", @@ -1746,7 +1776,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Read for ownership prefetch from local IA that miss the cache", + "BriefDescription": "Read for ownership prefetch from local IA", "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", @@ -2380,7 +2410,6 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores", "UMask": "0xc827ff01", @@ -2442,7 +2471,6 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC", "UMask": "0xc827fd01", @@ -2453,7 +2481,6 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC", "UMask": "0xc8a7fd01", @@ -2663,7 +2690,6 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC", "UMask": "0xc827fe01", @@ -2674,7 +2700,6 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", - "Experimental": "1", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC", "UMask": "0xc8a7fe01", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cxl.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cxl.json index 383a5ba5a697..43e094c233cc 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cxl.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-cxl.json @@ -13,7 +13,6 @@ "Counter": "4,5,6,7", "EventCode": "0x41", "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_DATA", - "Experimental": "1", "PerPkg": "1", "UMask": "0x10", "Unit": "CXLCM" @@ -23,7 +22,6 @@ "Counter": "0,1,2,3", "EventCode": "0x02", "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_DATA", - "Experimental": "1", "PerPkg": "1", "UMask": "0x20", "Unit": "CXLDP" diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json index 80440edac431..2ccbc8bca24e 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-interconnect.json @@ -815,6 +815,26 @@ "Unit": "IRP" }, { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "Counter": "0,1,2,3", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REJ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "Counter": "0,1,2,3", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REQ", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { "BriefDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", "Counter": "0,1,2,3", "EventCode": "0x1F", @@ -825,6 +845,46 @@ "Unit": "IRP" }, { + "BriefDescription": "Snoop Hit E/S responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Hit I responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Hit M responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop miss responses", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "Experimental": "1", + "PerPkg": "1", + "UMask": "0x71", + "Unit": "IRP" + }, + { "BriefDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", "Counter": "0,1,2,3", "EventCode": "0x11", @@ -1197,6 +1257,33 @@ "Unit": "UPI" }, { + "BriefDescription": "Cycles in L0p", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "Experimental": "1", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "Experimental": "1", + "PerPkg": "1", + "Unit": "UPI" + }, + { "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", "Counter": "0,1,2,3", "EventCode": "0x04", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json index cffb9d94b53d..886b99a971be 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-io.json @@ -17,7 +17,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -29,7 +29,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -41,7 +41,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -53,7 +53,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -65,7 +65,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -77,7 +77,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -89,7 +89,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -101,7 +101,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -113,7 +113,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -125,7 +125,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff0ff", + "UMask": "0xff", "Unit": "IIO" }, { @@ -137,7 +137,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -149,7 +149,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -161,7 +161,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -173,7 +173,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -185,7 +185,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -197,7 +197,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -209,7 +209,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -221,7 +221,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -233,7 +233,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -245,7 +245,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -257,7 +257,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -269,7 +269,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -281,7 +281,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -293,7 +293,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -305,7 +305,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -317,7 +317,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -329,7 +329,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -341,7 +341,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -352,7 +352,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -363,7 +363,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -374,7 +374,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -385,7 +385,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -396,7 +396,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -407,7 +407,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -418,7 +418,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -429,7 +429,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -440,7 +440,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -451,7 +451,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -462,7 +462,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -473,7 +473,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -484,7 +484,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -495,7 +495,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -506,7 +506,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -517,7 +517,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x10", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -528,7 +528,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x20", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -539,7 +539,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x40", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -550,7 +550,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x80", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -561,7 +561,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -572,7 +572,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -583,7 +583,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x02", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -594,7 +594,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x04", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -605,7 +605,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x08", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -616,7 +616,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x10", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -627,7 +627,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x20", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -638,7 +638,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x40", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -649,7 +649,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x80", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -661,7 +661,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -673,7 +673,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -685,7 +685,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -697,7 +697,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -709,7 +709,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -721,7 +721,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -733,7 +733,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -745,7 +745,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -757,7 +757,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -769,7 +769,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -781,7 +781,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -793,7 +793,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -805,7 +805,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -817,7 +817,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -829,7 +829,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -841,7 +841,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -853,7 +853,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1129,7 +1129,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1141,7 +1141,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1153,7 +1153,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1165,7 +1165,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1177,7 +1177,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1189,7 +1189,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1201,7 +1201,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x700f010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1213,7 +1213,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff080", + "UMask": "0x80", "Unit": "IIO" }, { @@ -1225,7 +1225,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff040", + "UMask": "0x40", "Unit": "IIO" }, { @@ -1237,7 +1237,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff020", + "UMask": "0x20", "Unit": "IIO" }, { @@ -1249,7 +1249,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1261,7 +1261,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1273,7 +1273,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1285,7 +1285,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff010", + "UMask": "0x10", "Unit": "IIO" }, { @@ -1297,7 +1297,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1318,7 +1318,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1329,7 +1329,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1340,7 +1340,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1351,7 +1351,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1362,7 +1362,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1373,7 +1373,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1384,7 +1384,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1395,7 +1395,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1406,7 +1406,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1417,7 +1417,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1428,7 +1428,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1439,7 +1439,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1450,7 +1450,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1461,7 +1461,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1472,7 +1472,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1483,7 +1483,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1494,7 +1494,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1505,7 +1505,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1516,7 +1516,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1527,7 +1527,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x0FF", - "UMask": "0x70ff002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1538,7 +1538,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1549,7 +1549,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1560,7 +1560,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1571,7 +1571,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1582,7 +1582,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1593,7 +1593,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1604,7 +1604,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1615,7 +1615,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080004", + "UMask": "0x4", "Unit": "IIO" }, { @@ -1626,7 +1626,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1637,7 +1637,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1648,7 +1648,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1659,7 +1659,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1670,7 +1670,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1681,7 +1681,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1692,7 +1692,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1703,7 +1703,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080001", + "UMask": "0x1", "Unit": "IIO" }, { @@ -1715,7 +1715,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1727,7 +1727,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1739,7 +1739,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1751,7 +1751,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1763,7 +1763,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1775,7 +1775,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1787,7 +1787,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1799,7 +1799,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080008", + "UMask": "0x8", "Unit": "IIO" }, { @@ -1811,7 +1811,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x001", - "UMask": "0x7001002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1823,7 +1823,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x002", - "UMask": "0x7002002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1835,7 +1835,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x004", - "UMask": "0x7004002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1847,7 +1847,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x008", - "UMask": "0x7008002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1859,7 +1859,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x010", - "UMask": "0x7010002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1871,7 +1871,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x020", - "UMask": "0x7020002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1883,7 +1883,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x040", - "UMask": "0x7040002", + "UMask": "0x2", "Unit": "IIO" }, { @@ -1895,7 +1895,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x080", - "UMask": "0x7080002", + "UMask": "0x2", "Unit": "IIO" } ] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json index 7e6e6764f181..ae9c62b32e92 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-memory.json @@ -169,7 +169,7 @@ "Unit": "IMC" }, { - "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled", + "BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled. DCLK is 1/4 of DRAM data rate.", "Counter": "0,1,2,3", "EventCode": "0x01", "EventName": "UNC_M_CLOCKTICKS", @@ -189,6 +189,104 @@ "Unit": "IMC" }, { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x4", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x8", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x10", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x20", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x40", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode", + "Counter": "0,1,2,3", + "EventCode": "0x47", + "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x80", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles a given rank is in Power Down Mode and all pages are closed", + "Counter": "0,1,2,3", + "EventCode": "0x88", + "EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "Unit": "IMC" + }, + { "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", "Counter": "0,1,2,3", "EventCode": "0x03", @@ -361,6 +459,28 @@ "Unit": "IMC" }, { + "BriefDescription": "subevent0 - # of cycles all ranks were in SR subevent1 - # of times all ranks went into SR subevent2 -# of times ps_sr_active asserted (SRE) subevent3 - # of times ps_sr_active deasserted (SRX) subevent4 - # of times PS-&>Refresh ps_sr_req asserted (SRE) subevent5 - # of times PS-&>Refresh ps_sr_req deasserted (SRX) subevent6 - # of cycles PSCtrlr FSM was in FATAL", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "UNC_M_SELF_REFRESH.ENTER_SUCCESS", + "UMask": "0x2", + "Unit": "IMC" + }, + { + "BriefDescription": "# of cycles all ranks were in SR", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_SELF_REFRESH.ENTER_SUCCESS_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "-", + "UMask": "0x1", + "Unit": "IMC" + }, + { "BriefDescription": "Write Pending Queue Allocations", "Counter": "0,1,2,3", "EventCode": "0x22", diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-power.json b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-power.json index 02e59f64a544..9ea852ef190e 100644 --- a/tools/perf/pmu-events/arch/x86/sierraforest/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/sierraforest/uncore-power.json @@ -7,5 +7,103 @@ "PerPkg": "1", "PublicDescription": "PCU Clockticks: The PCU runs off a fixed 1 GHz clock. This event counts the number of pclk cycles measured while the counter was enabled. The pclk, like the Memory Controller's dclk, counts at a constant rate making it a good measure of actual wall time.", "Unit": "PCU" + }, + { + "BriefDescription": "Thermal Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x04", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Thermal Strongest Upper Limit Cycles : Number of cycles any frequency is reduced due to a thermal limit. Count only if throttling is occurring.", + "Unit": "PCU" + }, + { + "BriefDescription": "Power Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x05", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Power Strongest Upper Limit Cycles : Counts the number of cycles when power is the upper limit on frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Cycles spent changing Frequency : Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C2E", + "Counter": "0,1,2,3", + "EventCode": "0x2b", + "EventName": "UNC_P_PKG_RESIDENCY_C2E_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C2E : Counts the number of cycles when the package was in C2E. This event can be used in conjunction with edge detect to count C2E entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C6", + "Counter": "0,1,2,3", + "EventCode": "0x2d", + "EventName": "UNC_P_PKG_RESIDENCY_C6_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C6 : Counts the number of cycles when the package was in C6. This event can be used in conjunction with edge detect to count C6 entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C0", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0", + "PerPkg": "1", + "PublicDescription": "Number of cores in C0 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C3", + "Counter": "0,1,2,3", + "EventCode": "0x36", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C3", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Number of cores in C3 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C6", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6", + "PerPkg": "1", + "PublicDescription": "Number of cores in C6 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "External Prochot", + "Counter": "0,1,2,3", + "EventCode": "0x0a", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "External Prochot : Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" + }, + { + "BriefDescription": "Internal Prochot", + "Counter": "0,1,2,3", + "EventCode": "0x09", + "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", + "Experimental": "1", + "PerPkg": "1", + "PublicDescription": "Internal Prochot : Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" } ] diff --git a/tools/perf/pmu-events/arch/x86/skylake/metricgroups.json b/tools/perf/pmu-events/arch/x86/skylake/metricgroups.json index 3a88260194d1..00172bff5219 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/skylake/metricgroups.json @@ -37,6 +37,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -83,7 +84,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -112,10 +115,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -128,5 +134,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 4e954fe8547c..2a76dd01fb52 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -74,12 +74,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -91,7 +91,7 @@ "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -102,7 +102,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", "ScaleUnit": "100%" }, { @@ -112,10 +112,103 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", @@ -123,7 +216,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -131,8 +224,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -140,8 +233,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -149,18 +242,50 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(18.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 16.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((22 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + (20 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -171,25 +296,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "16.5 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(20 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -198,7 +323,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -208,8 +333,8 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -218,7 +343,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -226,47 +351,47 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "22 * tma_info_system_core_frequency * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", "ScaleUnit": "100%" }, { @@ -276,7 +401,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -286,17 +411,17 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -306,7 +431,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -315,7 +440,7 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", "ScaleUnit": "100%" }, { @@ -323,8 +448,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -333,8 +458,8 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -342,8 +467,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -351,8 +476,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -362,50 +487,50 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 4 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -415,7 +540,7 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" @@ -430,8 +555,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" @@ -439,7 +564,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -447,108 +572,10 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -577,7 +604,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -605,11 +632,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -622,20 +649,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -665,7 +692,13 @@ "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -684,7 +717,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -692,7 +725,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -700,7 +733,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -708,7 +741,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -716,7 +749,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -756,7 +789,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -766,7 +799,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -801,7 +834,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -819,7 +852,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -861,13 +894,13 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -886,7 +919,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -942,7 +975,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -963,18 +996,18 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -992,15 +1025,15 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -1010,13 +1043,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1027,19 +1061,32 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=1@", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@cmask\\=0x1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_REQUESTS.DATA_READ) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_REQUESTS.DATA_READ) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", @@ -1052,13 +1099,20 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1067,14 +1121,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1100,43 +1155,52 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1144,17 +1208,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "6.5 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(10 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1162,18 +1226,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1191,7 +1255,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1199,15 +1263,39 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1219,16 +1307,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1236,8 +1324,8 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1248,11 +1336,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1266,7 +1354,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1274,8 +1362,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1288,12 +1376,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1301,8 +1389,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1311,7 +1399,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", "ScaleUnit": "100%" }, { @@ -1319,7 +1407,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1333,19 +1421,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1354,7 +1442,7 @@ "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1363,7 +1451,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1399,7 +1487,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1408,7 +1496,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1425,8 +1513,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { @@ -1434,8 +1522,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1443,7 +1531,7 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1452,16 +1540,16 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1479,7 +1567,7 @@ "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1489,8 +1577,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1498,17 +1586,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1516,8 +1604,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1525,18 +1613,18 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1552,7 +1640,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1560,7 +1648,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1568,7 +1680,7 @@ "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1577,8 +1689,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json b/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json index cccfcab3425e..a579603f720b 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json @@ -38,6 +38,7 @@ "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -84,7 +85,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -113,10 +116,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -129,5 +135,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index e5e86892d7bb..2fe630cd4927 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -55,7 +55,7 @@ "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", "MetricName": "cpi", "ScaleUnit": "1per_instr" @@ -76,31 +76,31 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "dtlb_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB", "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU", "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e6 / duration_time", "MetricName": "io_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU", "MetricExpr": "(UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3) * 4 / 1e6 / duration_time", "MetricName": "io_bandwidth_write", "ScaleUnit": "1MB/s" @@ -109,14 +109,14 @@ "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB", "ScaleUnit": "1per_instr" }, { @@ -192,25 +192,25 @@ "ScaleUnit": "1per_instr" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", "MetricName": "llc_miss_local_memory_bandwidth_write", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_read", "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory", "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", "MetricName": "llc_miss_remote_memory_bandwidth_write", "ScaleUnit": "1MB/s" @@ -240,13 +240,13 @@ "ScaleUnit": "1MB/s" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", "MetricName": "numa_reads_addressed_to_local_dram", "ScaleUnit": "100%" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches", "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", "MetricName": "numa_reads_addressed_to_remote_dram", "ScaleUnit": "100%" @@ -295,12 +295,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -312,7 +312,7 @@ "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -323,7 +323,7 @@ "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound", "ScaleUnit": "100%" }, { @@ -333,10 +333,103 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", @@ -344,7 +437,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -352,8 +445,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -361,8 +454,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -370,18 +463,50 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { @@ -392,25 +517,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -419,7 +544,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -429,8 +554,8 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -439,7 +564,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -447,47 +572,47 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(110 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency", "ScaleUnit": "100%" }, { @@ -497,7 +622,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -507,17 +632,17 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -527,7 +652,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -536,7 +661,7 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", "ScaleUnit": "100%" }, { @@ -544,17 +669,17 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -563,8 +688,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -572,8 +697,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -581,7 +706,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -592,50 +717,50 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions", "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 4 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", @@ -645,7 +770,7 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" @@ -660,8 +785,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" @@ -669,7 +794,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -677,108 +802,10 @@ }, { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -807,7 +834,7 @@ }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)", "MetricGroup": "SMT", "MetricName": "tma_info_core_core_clks" }, @@ -832,14 +859,14 @@ }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -852,20 +879,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -895,7 +922,13 @@ "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -910,11 +943,11 @@ { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)", "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -922,7 +955,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -930,7 +963,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -938,7 +971,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -946,7 +979,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -954,7 +987,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -994,7 +1027,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -1004,7 +1037,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -1051,7 +1084,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -1069,7 +1102,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -1111,13 +1144,13 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -1136,7 +1169,7 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { @@ -1192,7 +1225,7 @@ }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1213,18 +1246,18 @@ "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1242,29 +1275,29 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / tma_info_system_time", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_read_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]. Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / tma_info_system_time", "MetricGroup": "IoBW;MemOffcore;Server;SoC", "MetricName": "tma_info_system_io_write_bw", "PublicDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]. Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU" @@ -1274,13 +1307,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1298,24 +1332,37 @@ }, { "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@", "MetricGroup": "Mem;MemoryBW;SoC", "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / tma_info_system_time)", "MetricGroup": "Mem;MemoryLat;SoC", "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "(power@energy\\-pkg@ * 61 + 15.6 * power@energy\\-ram@) / (duration_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1323,7 +1370,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1331,7 +1378,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1346,6 +1393,13 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -1353,12 +1407,12 @@ }, { "BriefDescription": "Measured Average Uncore Frequency for the SoC [GHz]", - "MetricExpr": "tma_info_system_socket_clks / 1e9 / duration_time", + "MetricExpr": "tma_info_system_socket_clks / 1e9 / tma_info_system_time", "MetricGroup": "SoC", "MetricName": "tma_info_system_uncore_frequency" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1367,14 +1421,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1400,43 +1455,52 @@ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 6" + "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1444,17 +1508,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1462,18 +1526,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "tma_retiring - tma_heavy_operations", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1491,7 +1555,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1499,24 +1563,48 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_mem", - "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1528,16 +1616,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1545,8 +1633,8 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1557,11 +1645,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1575,7 +1663,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1583,8 +1671,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1597,12 +1685,12 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1610,8 +1698,8 @@ "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1620,7 +1708,7 @@ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused", "ScaleUnit": "100%" }, { @@ -1628,7 +1716,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1642,19 +1730,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1708,7 +1796,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1717,7 +1805,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1734,8 +1822,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { @@ -1743,8 +1831,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1752,7 +1840,7 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1761,35 +1849,35 @@ "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", - "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", + "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_mem", - "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", "ScaleUnit": "100%" }, { @@ -1807,7 +1895,7 @@ "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1817,8 +1905,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1826,17 +1914,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1844,8 +1932,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1853,18 +1941,18 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1880,7 +1968,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1888,7 +1976,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1896,7 +2008,7 @@ "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1905,8 +2017,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json index 4fc818626491..da46a3aeb58c 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json @@ -4454,7 +4454,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4465,7 +4465,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4476,7 +4476,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -4486,7 +4486,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -4496,7 +4496,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4507,7 +4507,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4528,7 +4528,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4539,7 +4539,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4550,7 +4550,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -4560,7 +4560,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -4570,7 +4570,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4581,7 +4581,7 @@ "Counter": "0,1,2,3", "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4624,7 +4624,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", "Experimental": "1", - "Filter": "config1=0x4903300000000", + "Filter": "config1=0x49033", "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM request is used by IIO to request a data write without first reading the data for ownership.", "UMask": "0x24", @@ -4636,7 +4636,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RDCUR", "Experimental": "1", - "Filter": "config1=0x43c3300000000", + "Filter": "config1=0x43C33", "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RdCur requests and miss the LLC. A RdCur request is used by IIO to read data without changing state.", "UMask": "0x24", @@ -4648,7 +4648,7 @@ "EventCode": "0x35", "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", "Experimental": "1", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests a cache line to be cached in E state with the intent to modify.", "UMask": "0x24", @@ -4865,7 +4865,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4876,7 +4876,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4887,7 +4887,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -4897,7 +4897,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x11", "Unit": "CHA" @@ -4907,7 +4907,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4918,7 +4918,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", @@ -4939,7 +4939,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", - "Filter": "config1=0x4023300000000", + "Filter": "config1=0x40233", "PerPkg": "1", "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4950,7 +4950,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", - "Filter": "config1=0x4043300000000", + "Filter": "config1=0x40433", "PerPkg": "1", "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4961,7 +4961,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b23300000000", + "Filter": "config1=0x4b233", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -4971,7 +4971,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b43300000000", + "Filter": "config1=0x4b433", "PerPkg": "1", "UMask": "0x21", "Unit": "CHA" @@ -4981,7 +4981,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b03300000000", + "Filter": "config1=0x4b033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -4992,7 +4992,7 @@ "Counter": "0", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", @@ -5037,7 +5037,7 @@ "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", "Experimental": "1", - "Filter": "config1=0x4903300000000", + "Filter": "config1=0x49033", "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM is used by IIO to request a data write without first reading the data for ownership.", "UMask": "0x24", @@ -5049,7 +5049,7 @@ "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RDCUR", "Experimental": "1", - "Filter": "config1=0x43c3300000000", + "Filter": "config1=0x43C33", "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RdCur requests that miss the LLC. A RdCur request is used by IIO to read data without changing state.", "UMask": "0x24", @@ -5061,7 +5061,7 @@ "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", "Experimental": "1", - "Filter": "config1=0x4003300000000", + "Filter": "config1=0x40033", "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests data to be cached in E state with the intent to modify.", "UMask": "0x24", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json index 216a00237cd1..eef801c68bd2 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json @@ -13754,16 +13754,5 @@ "PerPkg": "1", "PublicDescription": "Number outstanding register requests within message channel tracker", "Unit": "UBOX" - }, - { - "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", - "Counter": "0,1,2,3", - "EventCode": "0x2", - "EventName": "UPI_DATA_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", - "ScaleUnit": "7.11E-06Bytes", - "UMask": "0xf", - "Unit": "UPI" } ] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json index f4144a1110be..d316eefee857 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json @@ -75,15 +75,24 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.", "Counter": "0,1,2,3", "EventCode": "0xf2", "EventName": "L2_LINES_OUT.SILENT", - "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.", "SampleAfterValue": "200003", "UMask": "0x1" }, { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3", + "EventCode": "0xf2", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { "BriefDescription": "L2 code requests", "Counter": "0,1,2,3", "EventCode": "0x24", @@ -233,7 +242,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81" @@ -244,7 +252,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", - "PEBS": "1", "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82" @@ -255,7 +262,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts all retired memory instructions - loads and stores.", "SampleAfterValue": "1000003", "UMask": "0x83" @@ -266,7 +272,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with locked access.", "SampleAfterValue": "100007", "UMask": "0x21" @@ -277,7 +282,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x41" @@ -288,7 +292,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "PEBS": "1", "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", "UMask": "0x42" @@ -299,7 +302,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x11" @@ -310,7 +312,6 @@ "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "PEBS": "1", "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", "SampleAfterValue": "100003", "UMask": "0x12" @@ -321,7 +322,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions where a cross-core snoop hit in another cores caches on this socket, the data was forwarded back to the requesting core as the data was modified (SNOOP_HITM) or the L3 did not have the data(SNOOP_HIT_WITH_FWD).", "SampleAfterValue": "20011", "UMask": "0x4" @@ -332,7 +332,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -343,7 +342,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" @@ -354,7 +352,6 @@ "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", - "PEBS": "1", "PublicDescription": "Counts retired load instructions in which the L3 supplied the data and a cross-core snoop hit in another cores caches on this socket but that other core did not forward the data back (SNOOP_HIT_NO_FWD).", "SampleAfterValue": "20011", "UMask": "0x2" @@ -365,7 +362,6 @@ "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access", "SampleAfterValue": "100007", "UMask": "0x4" @@ -376,7 +372,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -387,7 +382,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", "SampleAfterValue": "1000003", "UMask": "0x1" @@ -398,7 +392,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "200003", "UMask": "0x8" @@ -409,7 +402,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "200003", "UMask": "0x2" @@ -420,7 +412,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", "SampleAfterValue": "100021", "UMask": "0x10" @@ -431,7 +422,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", "SampleAfterValue": "100021", "UMask": "0x4" @@ -442,7 +432,6 @@ "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "PEBS": "1", "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -458,7 +447,7 @@ "UMask": "0x1" }, { - "BriefDescription": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another cores caches which forwarded the data to the requesting core.", "Counter": "0,1,2,3", "EventCode": "0xB7, 0xBB", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", @@ -533,6 +522,16 @@ "UMask": "0x8" }, { + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", "CounterMask": "1", diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json b/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json index 13c052d0f470..6ebdf6c5ce11 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json @@ -44,7 +44,6 @@ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x1", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -56,7 +55,6 @@ "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x11", - "PEBS": "1", "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -68,7 +66,6 @@ "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x14", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -80,7 +77,6 @@ "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x12", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -92,7 +88,6 @@ "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x13", - "PEBS": "1", "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -104,7 +99,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x500106", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -116,7 +110,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", "MSRValue": "0x508006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -128,7 +121,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", "MSRValue": "0x501006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -140,7 +132,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", "MSRValue": "0x500206", - "PEBS": "1", "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -152,7 +143,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", "MSRValue": "0x510006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -164,7 +154,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", "MSRValue": "0x100206", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -176,7 +165,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", "MSRValue": "0x502006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -188,7 +176,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", "MSRValue": "0x500406", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -200,7 +187,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", "MSRValue": "0x520006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -212,7 +198,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", "MSRValue": "0x504006", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -224,7 +209,6 @@ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", "MSRValue": "0x500806", - "PEBS": "1", "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -236,7 +220,6 @@ "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", "MSRValue": "0x15", - "PEBS": "1", "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/memory.json b/tools/perf/pmu-events/arch/x86/tigerlake/memory.json index a125cefa100f..f99018cab7e7 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/memory.json @@ -25,7 +25,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1" @@ -38,7 +37,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1" @@ -51,7 +49,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1" @@ -64,7 +61,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1" @@ -77,7 +73,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1" @@ -90,7 +85,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1" @@ -103,7 +97,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1" @@ -116,7 +109,6 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -135,17 +127,16 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", "PublicDescription": "Counts the number of times RTM abort was triggered.", "SampleAfterValue": "100003", "UMask": "0x4" }, { - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt)", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED_EVENTS", - "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).", "SampleAfterValue": "100003", "UMask": "0x80" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json index 3a88260194d1..80ca8021f2de 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json @@ -37,6 +37,7 @@ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", @@ -83,7 +84,9 @@ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category", "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category", "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_divider_group": "Metrics contributing to tma_divider category", "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", @@ -93,6 +96,7 @@ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category", "tma_issue2P": "Metrics related by the issue $issue2P", "tma_issueBM": "Metrics related by the issue $issueBM", "tma_issueBW": "Metrics related by the issue $issueBW", @@ -112,10 +116,13 @@ "tma_issueSpSt": "Metrics related by the issue $issueSpSt", "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category", "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category", "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", "tma_light_operations_group": "Metrics contributing to tma_light_operations category", "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category", "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", @@ -128,5 +135,6 @@ "tma_retiring_group": "Metrics contributing to tma_retiring category", "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", "tma_store_bound_group": "Metrics contributing to tma_store_bound category", - "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category", + "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category" } diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json index 09b53b0722a9..7ef1bac08463 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json @@ -10,6 +10,15 @@ "UMask": "0x9" }, { + "BriefDescription": "ARITH.FP_DIVIDER_ACTIVE", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", @@ -23,7 +32,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009" }, @@ -32,7 +40,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x11" @@ -42,7 +49,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts not taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x10" @@ -52,7 +58,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" @@ -62,7 +67,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "PublicDescription": "Counts far branch instructions retired.", "SampleAfterValue": "100007", "UMask": "0x40" @@ -72,7 +76,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", "SampleAfterValue": "100003", "UMask": "0x80" @@ -82,7 +85,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "PublicDescription": "Counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" @@ -92,7 +94,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "PublicDescription": "Counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" @@ -102,7 +103,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" @@ -112,7 +112,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "50021" }, @@ -121,7 +120,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "PublicDescription": "Counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x11" @@ -131,7 +129,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", - "PEBS": "1", "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", "SampleAfterValue": "50021", "UMask": "0x10" @@ -141,7 +138,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", "SampleAfterValue": "50021", "UMask": "0x1" @@ -151,7 +147,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", "SampleAfterValue": "50021", "UMask": "0x80" @@ -161,7 +156,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", "SampleAfterValue": "50021", "UMask": "0x2" @@ -171,7 +165,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "50021", "UMask": "0x20" @@ -181,7 +174,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", - "PEBS": "1", "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", "SampleAfterValue": "50021", "UMask": "0x8" @@ -396,7 +388,6 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1" @@ -406,7 +397,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003" }, @@ -415,7 +405,6 @@ "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", - "PEBS": "1", "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", "SampleAfterValue": "2000003", "UMask": "0x2" @@ -424,7 +413,6 @@ "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution", "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", - "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.", "SampleAfterValue": "2000003", "UMask": "0x1" diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index c45c6b4a380d..8c0cd6e63a2a 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -89,12 +89,12 @@ "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", - "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations", "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", @@ -106,7 +106,7 @@ "MetricExpr": "34 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", - "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, @@ -129,11 +129,104 @@ "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)", + "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "tma_bottleneck_big_code", + "MetricThreshold": "tma_bottleneck_big_code > 20" + }, + { + "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", + "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", + "MetricGroup": "BvBO;Ret", + "MetricName": "tma_bottleneck_branching_overhead", + "MetricThreshold": "tma_bottleneck_branching_overhead > 5", + "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))", + "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_bottleneck_cache_memory_bandwidth", + "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", + "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_bottleneck_cache_memory_latency", + "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20", + "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", + "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", + "MetricGroup": "BvCB;Cor;tma_issueComp", + "MetricName": "tma_bottleneck_compute_bound_est", + "MetricThreshold": "tma_bottleneck_compute_bound_est > 20", + "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", + "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code", + "MetricGroup": "BvFB;Fed;FetchBW;Frontend", + "MetricName": "tma_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of irregular execution (e.g", + "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_mispredicts_resteers) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", + "MetricName": "tma_bottleneck_irregular_overhead", + "MetricThreshold": "tma_bottleneck_irregular_overhead > 10", + "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))", + "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", + "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", + "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn", + "MetricName": "tma_bottleneck_memory_synchronization", + "MetricThreshold": "tma_bottleneck_memory_synchronization > 10", + "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", + "MetricName": "tma_bottleneck_mispredictions", + "MetricThreshold": "tma_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", + "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)", + "MetricGroup": "BvOB;Cor;Offcore", + "MetricName": "tma_bottleneck_other_bottlenecks", + "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20", + "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls" + }, + { + "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead", + "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", + "MetricGroup": "BvUW;Ret", + "MetricName": "tma_bottleneck_useful_work", + "MetricThreshold": "tma_bottleneck_useful_work > 20" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions", "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", @@ -147,7 +240,7 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { @@ -155,8 +248,8 @@ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", - "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -164,8 +257,8 @@ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_cisc", - "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources", "ScaleUnit": "100%" }, { @@ -173,18 +266,66 @@ "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", - "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache", + "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_hit", + "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks", + "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group", + "MetricName": "tma_code_l2_miss", + "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)", + "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_hit", + "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk", + "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group", + "MetricName": "tma_code_stlb_miss", + "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_2m", + "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses", + "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)", + "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group", + "MetricName": "tma_code_stlb_miss_4k", + "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "ScaleUnit": "100%" + }, + { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(49 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 48 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricExpr": "((54 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (53 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { @@ -194,25 +335,25 @@ "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "48 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricExpr": "(53 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", - "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, @@ -221,7 +362,7 @@ "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", - "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, @@ -231,8 +372,8 @@ "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", - "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS", "ScaleUnit": "100%" }, { @@ -241,7 +382,7 @@ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here", "ScaleUnit": "100%" }, { @@ -249,44 +390,44 @@ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", - "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", - "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", - "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs, tma_info_bottleneck_memory_synchronization", + "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricExpr": "54 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", - "MetricGroup": "BvMS;DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -296,7 +437,7 @@ "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { @@ -306,16 +447,16 @@ "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops", "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", "MetricName": "tma_few_uops_instructions", "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { @@ -324,7 +465,7 @@ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting", "ScaleUnit": "100%" }, { @@ -333,7 +474,15 @@ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active", + "MetricExpr": "ARITH.FP_DIVIDER_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_fp_divider", + "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -341,7 +490,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -350,7 +499,7 @@ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -359,8 +508,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", - "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -368,8 +517,8 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", - "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -377,7 +526,7 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", - "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, @@ -389,17 +538,17 @@ "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", "MetricgroupNoGroup": "TopdownL1;Default", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. ([ICL+] Note this may overcount due to approximation using indirect events; [ADL+] .)", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])", "ScaleUnit": "100%" }, { @@ -407,41 +556,41 @@ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", - "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_bottleneck_mispredictions * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES / 100", + "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 5 / BR_MISP_RETIRED.ALL_BRANCHES / 100", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", "MetricName": "tma_info_bad_spec_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_indirect", - "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000" }, { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", "MetricGroup": "Bad;BrMispredicts", "MetricName": "tma_info_bad_spec_ipmisp_ret", @@ -455,7 +604,7 @@ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { - "BriefDescription": "Speculative to Retired ratio of all clears (covering mispredicts and nukes)", + "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)", "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)", "MetricGroup": "BrMispredicts", "MetricName": "tma_info_bad_spec_spec_clears_ratio" @@ -470,8 +619,8 @@ }, { "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite)))", - "MetricGroup": "DSB;FetchBW;tma_issueFB", + "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_bandwidth", "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10", "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" @@ -479,7 +628,7 @@ { "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))", "MetricGroup": "DSBmiss;Fed;tma_issueFB", "MetricName": "tma_info_botlnk_l2_dsb_misses", "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", @@ -488,108 +637,10 @@ { "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))", "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", "MetricName": "tma_info_botlnk_l2_ic_misses", - "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "tma_info_bottleneck_big_code", - "MetricThreshold": "tma_info_bottleneck_big_code > 20" - }, - { - "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA", - "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)", - "MetricGroup": "BvBO;Ret", - "MetricName": "tma_info_bottleneck_branching_overhead", - "MetricThreshold": "tma_info_bottleneck_branching_overhead > 5", - "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_bottleneck_cache_memory_bandwidth", - "MetricThreshold": "tma_info_bottleneck_cache_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks", - "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_hit_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))", - "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_bottleneck_cache_memory_latency", - "MetricThreshold": "tma_info_bottleneck_cache_memory_latency > 20", - "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation", - "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))", - "MetricGroup": "BvCB;Cor;tma_issueComp", - "MetricName": "tma_info_bottleneck_compute_bound_est", - "MetricThreshold": "tma_info_bottleneck_compute_bound_est > 20", - "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: " - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", - "MetricGroup": "BvFB;Fed;FetchBW;Frontend", - "MetricName": "tma_info_bottleneck_instruction_fetch_bw", - "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" - }, - { - "BriefDescription": "Total pipeline cost of irregular execution (e.g", - "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS", - "MetricName": "tma_info_bottleneck_irregular_overhead", - "MetricThreshold": "tma_info_bottleneck_irregular_overhead > 10", - "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_hit_latency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_data_tlbs", - "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_synchronization" - }, - { - "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)", - "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))", - "MetricGroup": "BvMS;Mem;Offcore;tma_issueTLB", - "MetricName": "tma_info_bottleneck_memory_synchronization", - "MetricThreshold": "tma_info_bottleneck_memory_synchronization > 10", - "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_dtlb_load, tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM", - "MetricName": "tma_info_bottleneck_mispredictions", - "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end", - "MetricExpr": "100 - (tma_info_bottleneck_big_code + tma_info_bottleneck_instruction_fetch_bw + tma_info_bottleneck_mispredictions + tma_info_bottleneck_cache_memory_bandwidth + tma_info_bottleneck_cache_memory_latency + tma_info_bottleneck_memory_data_tlbs + tma_info_bottleneck_memory_synchronization + tma_info_bottleneck_compute_bound_est + tma_info_bottleneck_irregular_overhead + tma_info_bottleneck_branching_overhead + tma_info_bottleneck_useful_work)", - "MetricGroup": "BvOB;Cor;Offcore", - "MetricName": "tma_info_bottleneck_other_bottlenecks", - "MetricThreshold": "tma_info_bottleneck_other_bottlenecks > 20", - "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls." - }, - { - "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.", - "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)", - "MetricGroup": "BvUW;Ret", - "MetricName": "tma_info_bottleneck_useful_work", - "MetricThreshold": "tma_info_bottleneck_useful_work > 20" + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5" }, { "BriefDescription": "Fraction of branches that are CALL or RET", @@ -650,11 +701,11 @@ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_core_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", "MetricName": "tma_info_core_ilp" }, @@ -667,20 +718,20 @@ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "DSBmiss", "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@", "MetricGroup": "Fed;FetchBW", "MetricName": "tma_info_frontend_fetch_upc" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@", "MetricGroup": "Fed;FetchLat;IcMiss", "MetricName": "tma_info_frontend_icache_miss_latency" }, @@ -716,7 +767,13 @@ "MetricName": "tma_info_frontend_lsd_coverage" }, { - "BriefDescription": "Branch instructions per taken branch.", + "BriefDescription": "Taken Branches retired Per Cycle", + "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks", + "MetricGroup": "Branches;FetchBW", + "MetricName": "tma_info_frontend_tbpc" + }, + { + "BriefDescription": "Branch instructions per taken branch", "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;PGO", "MetricName": "tma_info_inst_mix_bptkbranch" @@ -734,7 +791,7 @@ "MetricGroup": "Flops;InsType", "MetricName": "tma_info_inst_mix_iparith", "MetricThreshold": "tma_info_inst_mix_iparith < 10", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW." + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", @@ -742,7 +799,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx128", "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", @@ -750,7 +807,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx256", "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", @@ -758,7 +815,7 @@ "MetricGroup": "Flops;FpVector;InsType", "MetricName": "tma_info_inst_mix_iparith_avx512", "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", @@ -766,7 +823,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_dp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", @@ -774,7 +831,7 @@ "MetricGroup": "Flops;FpScalar;InsType", "MetricName": "tma_info_inst_mix_iparith_scalar_sp", "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting." + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", @@ -819,7 +876,7 @@ }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricExpr": "INST_RETIRED.ANY / SW_PREFETCH_ACCESS.ANY", "MetricGroup": "Prefetches", "MetricName": "tma_info_inst_mix_ipswpf", "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" @@ -829,7 +886,7 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", "MetricName": "tma_info_inst_mix_iptb", - "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "MetricThreshold": "tma_info_inst_mix_iptb < 5 * 2 + 1", "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { @@ -864,7 +921,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l1d_cache_fill_bw" }, @@ -882,7 +939,7 @@ }, { "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l2_cache_fill_bw" }, @@ -924,13 +981,13 @@ }, { "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW;Offcore", "MetricName": "tma_info_memory_l3_cache_access_bw" }, { "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time", "MetricGroup": "Mem;MemoryBW", "MetricName": "tma_info_memory_l3_cache_fill_bw" }, @@ -949,22 +1006,16 @@ { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", + "MetricGroup": "LockCont;Memory_Lat;Offcore", "MetricName": "tma_info_memory_latency_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@", "MetricGroup": "Memory_BW;Offcore", "MetricName": "tma_info_memory_latency_load_l2_mlp" }, { - "BriefDescription": "Average Latency for L3 cache miss demand Loads", - "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_memory_latency_load_l3_miss_latency" - }, - { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", "MetricGroup": "Mem;MemoryBound;MemoryLat", @@ -990,6 +1041,13 @@ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { + "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses", + "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_memory_prefetches_useless_hwpf", + "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15" + }, + { "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Fed;MemoryTLB", @@ -1015,8 +1073,8 @@ "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)", + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)", "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", "MetricName": "tma_info_pipeline_execute" }, @@ -1043,18 +1101,18 @@ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY", "MetricGroup": "MicroSeq;Pipeline;Ret;Retire", "MetricName": "tma_info_pipeline_ipassist", - "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "MetricThreshold": "tma_info_pipeline_ipassist < 100000", "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@", "MetricGroup": "Pipeline;Ret", "MetricName": "tma_info_pipeline_retire" }, { "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time", "MetricGroup": "Power;Summary", "MetricName": "tma_info_system_core_frequency" }, @@ -1072,14 +1130,14 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / tma_info_system_time / 1e3", "MetricGroup": "HPC;MemOffcore;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.8_FLOPS + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / tma_info_system_time", "MetricGroup": "Cor;Flops;HPC", "MetricName": "tma_info_system_gflops", "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width" @@ -1089,13 +1147,14 @@ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", "MetricName": "tma_info_system_ipfarbranch", - "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + "MetricThreshold": "tma_info_system_ipfarbranch < 1000000" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_system_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", @@ -1119,11 +1178,24 @@ "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { + "BriefDescription": "PerfMon Event Multiplexing accuracy indicator", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_mux", + "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9" + }, + { + "BriefDescription": "Total package Power in Watts", + "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)", + "MetricGroup": "Power;SoC", + "MetricName": "tma_info_system_power" + }, + { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", "MetricName": "tma_info_system_power_license0_utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", @@ -1131,7 +1203,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license1_utilization", "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", @@ -1139,7 +1211,7 @@ "MetricGroup": "Power", "MetricName": "tma_info_system_power_license2_utilization", "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", @@ -1154,13 +1226,20 @@ "MetricName": "tma_info_system_socket_clks" }, { + "BriefDescription": "Run duration time in seconds", + "MetricExpr": "duration_time", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_time", + "MetricThreshold": "tma_info_system_time < 1" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Pipeline", "MetricName": "tma_info_thread_clks" @@ -1169,14 +1248,15 @@ "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / tma_info_thread_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_thread_cpi" + "MetricName": "tma_info_thread_cpi", + "ScaleUnit": "1per_instr" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", "MetricName": "tma_info_thread_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", @@ -1186,13 +1266,13 @@ }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", + "MetricExpr": "slots", "MetricGroup": "TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)", "MetricGroup": "SMT;TmaL1;tma_L1_group", "MetricName": "tma_info_thread_slots_utilization" }, @@ -1208,33 +1288,41 @@ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", "MetricName": "tma_info_thread_uptb", - "MetricThreshold": "tma_info_thread_uptb < 7.5" + "MetricThreshold": "tma_info_thread_uptb < 5 * 1.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active", + "MetricExpr": "tma_divider - tma_fp_divider", + "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group", + "MetricName": "tma_int_divider", + "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", - "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache", "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", - "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache", + "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache", "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_l1_hit_latency", - "MetricThreshold": "tma_l1_hit_latency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles with demand load accesses that hit the L1 cache. The short latency of the L1 data cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", + "MetricName": "tma_l1_latency_dependency", + "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT", "ScaleUnit": "100%" }, { @@ -1243,8 +1331,17 @@ "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)", + "MetricExpr": "5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group", + "MetricName": "tma_l2_hit_latency", + "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT", "ScaleUnit": "100%" }, { @@ -1253,17 +1350,17 @@ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "17.5 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", + "MetricExpr": "(22.5 * tma_info_system_core_frequency - 5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks", "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_cache_memory_latency, tma_mem_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency", "ScaleUnit": "100%" }, { @@ -1271,18 +1368,18 @@ "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", - "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)", "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { @@ -1299,7 +1396,7 @@ "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_hit", - "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1307,16 +1404,40 @@ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", - "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_1g", + "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_2m", + "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses", + "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group", + "MetricName": "tma_load_stlb_miss_4k", + "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", - "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, @@ -1326,7 +1447,7 @@ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure", "ScaleUnit": "100%" }, { @@ -1336,16 +1457,16 @@ "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { @@ -1353,8 +1474,8 @@ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_cache_memory_latency, tma_l3_hit_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1364,11 +1485,11 @@ "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", @@ -1382,7 +1503,7 @@ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { @@ -1390,8 +1511,8 @@ "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", - "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { @@ -1405,19 +1526,27 @@ }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)", + "MetricThreshold": "tma_mite_4wide > 0.05 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)", + "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)", "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", - "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details", + "MetricExpr": "cpu@IDQ.MS_UOPS\\,cmask\\=0x1@ / tma_info_core_core_clks / 2", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_ms", + "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2", "ScaleUnit": "100%" }, { @@ -1425,8 +1554,8 @@ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", - "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_info_bottleneck_irregular_overhead, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { @@ -1434,7 +1563,7 @@ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group", "MetricName": "tma_nop_instructions", - "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, @@ -1449,19 +1578,19 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).", + "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)", "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)", "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group", "MetricName": "tma_other_mispredicts", - "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering", "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)", "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_other_nukes", - "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)", + "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", "ScaleUnit": "100%" }, { @@ -1497,7 +1626,7 @@ "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", - "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { @@ -1505,8 +1634,8 @@ "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", - "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations", "ScaleUnit": "100%" }, { @@ -1514,8 +1643,8 @@ "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", - "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric", "ScaleUnit": "100%" }, { @@ -1523,7 +1652,7 @@ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, @@ -1532,7 +1661,7 @@ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, @@ -1541,14 +1670,14 @@ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", - "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "DefaultMetricgroupName": "TopdownL1", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1561,7 +1690,7 @@ "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO", "MetricName": "tma_serializing_operation", - "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, @@ -1570,7 +1699,7 @@ "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", - "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, @@ -1579,8 +1708,8 @@ "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", - "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "MetricThreshold": "tma_split_loads > 0.3", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS", "ScaleUnit": "100%" }, { @@ -1589,17 +1718,17 @@ "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", - "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", - "MetricGroup": "BvMS;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", - "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { @@ -1607,8 +1736,8 @@ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", - "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES", "ScaleUnit": "100%" }, { @@ -1617,17 +1746,17 @@ "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", - "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", - "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", - "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency", "ScaleUnit": "100%" }, { @@ -1644,7 +1773,7 @@ "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_hit", - "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1652,7 +1781,31 @@ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", - "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_1g", + "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_2m", + "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses", + "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)", + "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group", + "MetricName": "tma_store_stlb_miss_4k", + "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "ScaleUnit": "100%" }, { @@ -1660,7 +1813,7 @@ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", - "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2", "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, @@ -1669,7 +1822,7 @@ "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", - "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, @@ -1678,8 +1831,8 @@ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", - "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json index 1500bf109c99..3732b6a68fe8 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.", "Counter": "0,1", "EventCode": "0x84", "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", @@ -90,7 +90,7 @@ "Unit": "ARB" }, { - "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.ALL", diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json index cc8110ac020c..1ac5b5ef8094 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", "Counter": "FIXED", "EventCode": "0xff", "EventName": "UNC_CLOCK.SOCKET", diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/tigerlake/virtual-memory.json index 62dc0fc76748..76eeca979e0b 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/virtual-memory.json @@ -28,6 +28,15 @@ "UMask": "0xe" }, { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "Counter": "0,1,2,3", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", "Counter": "0,1,2,3", "EventCode": "0x08", @@ -83,6 +92,15 @@ "UMask": "0xe" }, { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "Counter": "0,1,2,3", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", "Counter": "0,1,2,3", "EventCode": "0x49", diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index 1c7a2cfa321f..0cb7ba7912e8 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -422,7 +422,7 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (pmu && !pmu__name_match(pmu, pmu_name)) + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data); @@ -443,7 +443,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (!pmu__name_match(pmu, pmu_name)) + if (!perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); @@ -462,7 +462,7 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table, const struct pmu_table_entry *table_pmu = &table->pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) count += table_pmu->num_entries; } return count; @@ -581,7 +581,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) const struct pmu_table_entry *table_pmu = &map->event_table.pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) return &map->event_table; } return NULL; diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 3e204700b59a..7499a35bfadd 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -945,7 +945,7 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (pmu && !pmu__name_match(pmu, pmu_name)) + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data); @@ -966,7 +966,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (!pmu__name_match(pmu, pmu_name)) + if (!perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); @@ -985,7 +985,7 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table, const struct pmu_table_entry *table_pmu = &table->pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) count += table_pmu->num_entries; } return count; @@ -1104,7 +1104,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) const struct pmu_table_entry *table_pmu = &map->event_table.pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) return &map->event_table; } return NULL; diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py index bba68a6d4515..15b0c8268996 100755 --- a/tools/perf/python/tracepoint.py +++ b/tools/perf/python/tracepoint.py @@ -5,24 +5,31 @@ import perf -class tracepoint(perf.evsel): - def __init__(self, sys, name): - config = perf.tracepoint(sys, name) - perf.evsel.__init__(self, - type = perf.TYPE_TRACEPOINT, - config = config, - freq = 0, sample_period = 1, wakeup_events = 1, - sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_RAW | perf.SAMPLE_TIME) +def change_proctitle(): + try: + import setproctitle + setproctitle.setproctitle("tracepoint.py") + except: + print("Install the setproctitle python package to help with top and friends") def main(): - tp = tracepoint("sched", "sched_switch") + change_proctitle() cpus = perf.cpu_map() threads = perf.thread_map(-1) + evlist = perf.parse_events("sched:sched_switch", cpus, threads) + # Disable tracking of mmaps and similar that are unnecessary. + for ev in evlist: + ev.tracking = False + # Configure evsels with default record options. + evlist.config() + # Simplify the sample_type and read_format of evsels + for ev in evlist: + ev.sample_type = ev.sample_type & ~perf.SAMPLE_IP + ev.read_format = 0 - evlist = perf.evlist(cpus, threads) - evlist.add(tp) evlist.open() evlist.mmap() + evlist.enable(); while True: evlist.poll(timeout = -1) diff --git a/tools/perf/scripts/Build b/tools/perf/scripts/Build index 46f0c6f76dbf..91229a1fe3ff 100644 --- a/tools/perf/scripts/Build +++ b/tools/perf/scripts/Build @@ -2,3 +2,29 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-util-$(CONFIG_LIBPERL) += perl/Perf-Trace-Util/ endif perf-util-$(CONFIG_LIBPYTHON) += python/Perf-Trace-Util/ + +ifdef MYPY + PY_TESTS := $(shell find python -type f -name '*.py') + MYPY_TEST_LOGS := $(PY_TESTS:python/%=python/%.mypy_log) +else + MYPY_TEST_LOGS := +endif + +$(OUTPUT)%.mypy_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false) + +perf-y += $(MYPY_TEST_LOGS) + +ifdef PYLINT + PY_TESTS := $(shell find python -type f -name '*.py') + PYLINT_TEST_LOGS := $(PY_TESTS:python/%=python/%.pylint_log) +else + PYLINT_TEST_LOGS := +endif + +$(OUTPUT)%.pylint_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false) + +perf-y += $(PYLINT_TEST_LOGS) diff --git a/tools/perf/scripts/Makefile.syscalls b/tools/perf/scripts/Makefile.syscalls deleted file mode 100644 index 8bf55333262e..000000000000 --- a/tools/perf/scripts/Makefile.syscalls +++ /dev/null @@ -1,61 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# This Makefile generates headers in -# tools/perf/arch/$(SRCARCH)/include/generated/asm from the architecture's -# syscall table. This will either be from the generic syscall table, or from a -# table that is specific to that architecture. - -PHONY := all -all: - -obj := $(OUTPUT)arch/$(SRCARCH)/include/generated/asm - -syscall_abis_32 := common,32 -syscall_abis_64 := common,64 -syscalltbl := $(srctree)/tools/scripts/syscall.tbl - -# let architectures override $(syscall_abis_%) and $(syscalltbl) --include $(srctree)/tools/perf/arch/$(SRCARCH)/entry/syscalls/Makefile.syscalls -include $(srctree)/tools/build/Build.include --include $(srctree)/tools/perf/arch/$(SRCARCH)/entry/syscalls/Kbuild - -systbl := $(srctree)/tools/perf/scripts/syscalltbl.sh - -syscall-y := $(addprefix $(obj)/, $(syscall-y)) - -# Remove stale wrappers when the corresponding files are removed from generic-y -old-headers := $(wildcard $(obj)/*.h) -unwanted := $(filter-out $(syscall-y),$(old-headers)) - -quiet_cmd_remove = REMOVE $(unwanted) - cmd_remove = rm -f $(unwanted) - -quiet_cmd_systbl = SYSTBL $@ - cmd_systbl = $(CONFIG_SHELL) $(systbl) \ - $(if $(systbl-args-$*),$(systbl-args-$*),$(systbl-args)) \ - --abis $(subst $(space),$(comma),$(strip $(syscall_abis_$*))) \ - $< $@ - -all: $(syscall-y) - $(if $(unwanted),$(call cmd,remove)) - @: - -$(obj)/syscalls_%.h: $(syscalltbl) $(systbl) FORCE - $(call if_changed,systbl) - -targets := $(syscall-y) - -# Create output directory. Skip it if at least one old header exists -# since we know the output directory already exists. -ifeq ($(old-headers),) -$(shell mkdir -p $(obj)) -endif - -PHONY += FORCE - -FORCE: - -existing-targets := $(wildcard $(sort $(targets))) - --include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) - -.PHONY: $(PHONY) diff --git a/tools/perf/scripts/python/bin/flamegraph-report b/tools/perf/scripts/python/bin/flamegraph-report index 53c5dc90c87e..453a6918afbe 100755 --- a/tools/perf/scripts/python/bin/flamegraph-report +++ b/tools/perf/scripts/python/bin/flamegraph-report @@ -1,3 +1,3 @@ #!/bin/bash # description: create flame graphs -perf script -s "$PERF_EXEC_PATH"/scripts/python/flamegraph.py -- "$@" +perf script -s "$PERF_EXEC_PATH"/scripts/python/flamegraph.py "$@" diff --git a/tools/perf/scripts/syscalltbl.sh b/tools/perf/scripts/syscalltbl.sh deleted file mode 100755 index 1ce0d5aa8b50..000000000000 --- a/tools/perf/scripts/syscalltbl.sh +++ /dev/null @@ -1,86 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate a syscall table header. -# -# Each line of the syscall table should have the following format: -# -# NR ABI NAME [NATIVE] [COMPAT] -# -# NR syscall number -# ABI ABI name -# NAME syscall name -# NATIVE native entry point (optional) -# COMPAT compat entry point (optional) - -set -e - -usage() { - echo >&2 "usage: $0 [--abis ABIS] INFILE OUTFILE" >&2 - echo >&2 - echo >&2 " INFILE input syscall table" - echo >&2 " OUTFILE output header file" - echo >&2 - echo >&2 "options:" - echo >&2 " --abis ABIS ABI(s) to handle (By default, all lines are handled)" - exit 1 -} - -# default unless specified by options -abis= - -while [ $# -gt 0 ] -do - case $1 in - --abis) - abis=$(echo "($2)" | tr ',' '|') - shift 2;; - -*) - echo "$1: unknown option" >&2 - usage;; - *) - break;; - esac -done - -if [ $# -ne 2 ]; then - usage -fi - -infile="$1" -outfile="$2" - -nxt=0 - -syscall_macro() { - nr="$1" - name="$2" - - echo " [$nr] = \"$name\"," -} - -emit() { - nr="$1" - entry="$2" - - syscall_macro "$nr" "$entry" -} - -echo "static const char *const syscalltbl[] = {" > $outfile - -sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) -grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | sort -n > $sorted_table - -max_nr=0 -# the params are: nr abi name entry compat -# use _ for intentionally unused variables according to SC2034 -while read nr _ name _ _; do - emit "$nr" "$name" >> $outfile - max_nr=$nr -done < $sorted_table - -rm -f $sorted_table - -echo "};" >> $outfile - -echo "#define SYSCALLTBL_MAX_ID ${max_nr}" >> $outfile diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 4bf8d3f5eae7..934f32090553 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -80,14 +80,40 @@ perf-test-y += workloads/ ifdef SHELLCHECK SHELL_TESTS := $(shell find tests/shell -executable -type f -name '*.sh') - TEST_LOGS := $(SHELL_TESTS:tests/shell/%=shell/%.shellcheck_log) + SHELL_TEST_LOGS := $(SHELL_TESTS:tests/shell/%=shell/%.shellcheck_log) else SHELL_TESTS := - TEST_LOGS := + SHELL_TEST_LOGS := endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) -perf-test-y += $(TEST_LOGS) +perf-test-y += $(SHELL_TEST_LOGS) + +ifdef MYPY + PY_TESTS := $(shell find tests/shell -type f -name '*.py') + MYPY_TEST_LOGS := $(PY_TESTS:tests/shell/%=shell/%.mypy_log) +else + MYPY_TEST_LOGS := +endif + +$(OUTPUT)%.mypy_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false) + +perf-test-y += $(MYPY_TEST_LOGS) + +ifdef PYLINT + PY_TESTS := $(shell find tests/shell -type f -name '*.py') + PYLINT_TEST_LOGS := $(PY_TESTS:tests/shell/%=shell/%.pylint_log) +else + PYLINT_TEST_LOGS := +endif + +$(OUTPUT)%.pylint_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false) + +perf-test-y += $(PYLINT_TEST_LOGS) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index b1abb34d7818..cf6edbe697b2 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -479,19 +479,25 @@ static int process_sample_event(struct machine *machine, struct thread *thread; int ret; - if (evlist__parse_sample(evlist, event, &sample)) { + perf_sample__init(&sample, /*all=*/false); + ret = evlist__parse_sample(evlist, event, &sample); + if (ret) { pr_debug("evlist__parse_sample failed\n"); - return -1; + ret = -1; + goto out; } thread = machine__findnew_thread(machine, sample.pid, sample.tid); if (!thread) { pr_debug("machine__findnew_thread failed\n"); - return -1; + ret = -1; + goto out; } ret = read_object_code(sample.ip, READLEN, sample.cpumode, thread, state); thread__put(thread); +out: + perf_sample__exit(&sample); return ret; } diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 5286ae8bd2d7..a1fff4203b75 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -106,14 +106,25 @@ struct test_data_offset offsets[] = { /* move it from util/dso.c for compatibility */ static int dso__data_fd(struct dso *dso, struct machine *machine) { - int fd = dso__data_get_fd(dso, machine); + int fd = -1; - if (fd >= 0) + if (dso__data_get_fd(dso, machine, &fd)) dso__data_put_fd(dso); return fd; } +static void dsos__delete(struct dsos *dsos) +{ + for (unsigned int i = 0; i < dsos->cnt; i++) { + struct dso *dso = dsos->dsos[i]; + + dso__data_close(dso); + unlink(dso__name(dso)); + } + dsos__exit(dsos); +} + static int test__dso_data(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; @@ -172,7 +183,7 @@ static int test__dso_data(struct test_suite *test __maybe_unused, int subtest __ } dso__put(dso); - dsos__exit(&machine.dsos); + dsos__delete(&machine.dsos); unlink(file); return 0; } @@ -222,17 +233,6 @@ static int dsos__create(int cnt, int size, struct dsos *dsos) return 0; } -static void dsos__delete(struct dsos *dsos) -{ - for (unsigned int i = 0; i < dsos->cnt; i++) { - struct dso *dso = dsos->dsos[i]; - - dso__data_close(dso); - unlink(dso__name(dso)); - } - dsos__exit(dsos); -} - static int set_fd_limit(int n) { struct rlimit rlim; diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index f85d391ced98..4803ab2d97ba 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -115,8 +115,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr unsigned long cnt = 0; int err = -1; - memset(&sample, 0, sizeof(sample)); - + perf_sample__init(&sample, /*all=*/true); if (test__arch_unwind_sample(&sample, thread)) { pr_debug("failed to get unwind sample\n"); goto out; @@ -134,7 +133,8 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr out: zfree(&sample.user_stack.data); - zfree(&sample.user_regs.regs); + zfree(&sample.user_regs->regs); + perf_sample__exit(&sample); return err; } diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index d6b4ce3ef4ee..9301fde11366 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -109,6 +109,7 @@ static int test__event_update(struct test_suite *test __maybe_unused, int subtes TEST_ASSERT_VAL("failed to synthesize attr update name", !perf_event__synthesize_event_update_name(&tmp.tool, evsel, process_event_name)); + perf_cpu_map__put(evsel->core.own_cpus); evsel->core.own_cpus = perf_cpu_map__new("1,2,3"); TEST_ASSERT_VAL("failed to synthesize attr update cpus", diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c index d2b066a2b557..0837aca1cdfa 100644 --- a/tools/perf/tests/hwmon_pmu.c +++ b/tools/perf/tests/hwmon_pmu.c @@ -13,17 +13,23 @@ static const struct test_event { const char *name; const char *alias; - long config; + union hwmon_pmu_event_key key; } test_events[] = { { "temp_test_hwmon_event1", "temp1", - 0xA0001, + .key = { + .num = 1, + .type = 10 + }, }, { "temp_test_hwmon_event2", "temp2", - 0xA0002, + .key = { + .num = 2, + .type = 10 + }, }, }; @@ -183,11 +189,11 @@ static int do_test(size_t i, bool with_pmu, bool with_alias) strcmp(evsel->pmu->name, "hwmon_a_test_hwmon_pmu")) continue; - if (evsel->core.attr.config != (u64)test_events[i].config) { + if (evsel->core.attr.config != (u64)test_events[i].key.type_and_num) { pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", __FILE__, __LINE__, str, evsel->core.attr.config, - test_events[i].config); + test_events[i].key.type_and_num); ret = TEST_FAIL; goto out; } diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 012c8ae439fd..bd2106628b34 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -130,14 +130,17 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest goto out_delete_evlist; } + perf_sample__init(&sample, /*all=*/false); err = evlist__parse_sample(evlist, event, &sample); if (err) { pr_err("Can't parse sample, err = %d\n", err); + perf_sample__exit(&sample); goto out_delete_evlist; } err = -1; evsel = evlist__id2evsel(evlist, sample.id); + perf_sample__exit(&sample); if (evsel == NULL) { pr_debug("event with id %" PRIu64 " doesn't map to an evsel\n", sample.id); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index ddd1da9a4ba9..446a3615d720 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -229,11 +229,11 @@ static int mmap_events(synth_cb synth) static int test__mmap_thread_lookup(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { /* perf_event__synthesize_threads synthesize */ - TEST_ASSERT_VAL("failed with sythesizing all", + TEST_ASSERT_VAL("failed with synthesizing all", !mmap_events(synth_all)); /* perf_event__synthesize_thread_map synthesize */ - TEST_ASSERT_VAL("failed with sythesizing process", + TEST_ASSERT_VAL("failed with synthesizing process", !mmap_events(synth_process)); return 0; diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 3943da441979..0ef4ba7c1571 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -111,14 +111,16 @@ static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused continue; } + perf_sample__init(&sample, /*all=*/false); err = evsel__parse_sample(evsel, event, &sample); if (err) { pr_debug("Can't parse sample, err = %d\n", err); + perf_sample__exit(&sample); goto out_delete_evlist; } tp_flags = evsel__intval(evsel, &sample, "flags"); - + perf_sample__exit(&sample); if (flags != tp_flags) { pr_debug("%s: Expected flags=%#x, got %#x\n", __func__, flags, tp_flags); diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 202f0a9a6796..50e68b7d43aa 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -13,6 +13,7 @@ static int process_event(struct evlist **pevlist, union perf_event *event) { struct perf_sample sample; + int ret; if (event->header.type == PERF_RECORD_HEADER_ATTR) { if (perf_event__process_attr(NULL, event, pevlist)) { @@ -28,7 +29,10 @@ static int process_event(struct evlist **pevlist, union perf_event *event) if (!*pevlist) return -1; - if (evlist__parse_sample(*pevlist, event, &sample)) { + perf_sample__init(&sample, /*all=*/false); + ret = evlist__parse_sample(*pevlist, event, &sample); + perf_sample__exit(&sample); + if (ret) { pr_debug("evlist__parse_sample failed\n"); return -1; } diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 1c4feec1adff..0958c7c8995f 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -70,6 +70,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, }; char sbuf[STRERR_BUFSIZE]; + perf_sample__init(&sample, /*all=*/false); if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ evlist = evlist__new_default(); @@ -330,6 +331,7 @@ found_exit: out_delete_evlist: evlist__delete(evlist); out: + perf_sample__exit(&sample); if (err == -EACCES) return TEST_SKIP; if (err < 0 || errs != 0) diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index bbe2ddeb9b74..d3e40fa5482c 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -153,6 +153,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su while ((event = perf_mmap__read_event(&md->core)) != NULL) { struct perf_sample sample; + perf_sample__init(&sample, /*all=*/false); if (event->header.type != PERF_RECORD_COMM || (pid_t)event->comm.pid != getpid() || (pid_t)event->comm.tid != getpid()) @@ -170,6 +171,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su } next_event: perf_mmap__consume(&md->core); + perf_sample__exit(&sample); } perf_mmap__read_done(&md->core); } diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 6a681e3fb552..4a9f8e090cf4 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -452,9 +452,9 @@ static int test__name_cmp(struct test_suite *test __maybe_unused, int subtest __ } /** - * Test perf_pmu__match() that's used to search for a PMU given a name passed + * Test perf_pmu__wildcard_match() that's used to search for a PMU given a name passed * on the command line. The name that's passed may also be a filename type glob - * match. If the name does not match, perf_pmu__match() attempts to match the + * match. If the name does not match, perf_pmu__wildcard_match() attempts to match the * alias of the PMU, if provided. */ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest __maybe_unused) @@ -463,41 +463,44 @@ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest _ .name = "pmuname", }; - TEST_ASSERT_EQUAL("Exact match", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Longer token", perf_pmu__match(&test_pmu, "longertoken"), false); - TEST_ASSERT_EQUAL("Shorter token", perf_pmu__match(&test_pmu, "pmu"), false); +#define TEST_PMU_MATCH(msg, to_match, expect) \ + TEST_ASSERT_EQUAL(msg, perf_pmu__wildcard_match(&test_pmu, to_match), expect) + + TEST_PMU_MATCH("Exact match", "pmuname", true); + TEST_PMU_MATCH("Longer token", "longertoken", false); + TEST_PMU_MATCH("Shorter token", "pmu", false); test_pmu.name = "pmuname_10"; - TEST_ASSERT_EQUAL("Diff suffix_", perf_pmu__match(&test_pmu, "pmuname_2"), false); - TEST_ASSERT_EQUAL("Sub suffix_", perf_pmu__match(&test_pmu, "pmuname_1"), true); - TEST_ASSERT_EQUAL("Same suffix_", perf_pmu__match(&test_pmu, "pmuname_10"), true); - TEST_ASSERT_EQUAL("No suffix_", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore_", perf_pmu__match(&test_pmu, "pmuname_"), true); - TEST_ASSERT_EQUAL("Substring_", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix_", "pmuname_2", false); + TEST_PMU_MATCH("Sub suffix_", "pmuname_1", true); + TEST_PMU_MATCH("Same suffix_", "pmuname_10", true); + TEST_PMU_MATCH("No suffix_", "pmuname", true); + TEST_PMU_MATCH("Underscore_", "pmuname_", true); + TEST_PMU_MATCH("Substring_", "pmuna", false); test_pmu.name = "pmuname_ab23"; - TEST_ASSERT_EQUAL("Diff suffix hex_", perf_pmu__match(&test_pmu, "pmuname_2"), false); - TEST_ASSERT_EQUAL("Sub suffix hex_", perf_pmu__match(&test_pmu, "pmuname_ab"), true); - TEST_ASSERT_EQUAL("Same suffix hex_", perf_pmu__match(&test_pmu, "pmuname_ab23"), true); - TEST_ASSERT_EQUAL("No suffix hex_", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore hex_", perf_pmu__match(&test_pmu, "pmuname_"), true); - TEST_ASSERT_EQUAL("Substring hex_", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix hex_", "pmuname_2", false); + TEST_PMU_MATCH("Sub suffix hex_", "pmuname_ab", true); + TEST_PMU_MATCH("Same suffix hex_", "pmuname_ab23", true); + TEST_PMU_MATCH("No suffix hex_", "pmuname", true); + TEST_PMU_MATCH("Underscore hex_", "pmuname_", true); + TEST_PMU_MATCH("Substring hex_", "pmuna", false); test_pmu.name = "pmuname10"; - TEST_ASSERT_EQUAL("Diff suffix", perf_pmu__match(&test_pmu, "pmuname2"), false); - TEST_ASSERT_EQUAL("Sub suffix", perf_pmu__match(&test_pmu, "pmuname1"), true); - TEST_ASSERT_EQUAL("Same suffix", perf_pmu__match(&test_pmu, "pmuname10"), true); - TEST_ASSERT_EQUAL("No suffix", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore", perf_pmu__match(&test_pmu, "pmuname_"), false); - TEST_ASSERT_EQUAL("Substring", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix", "pmuname2", false); + TEST_PMU_MATCH("Sub suffix", "pmuname1", true); + TEST_PMU_MATCH("Same suffix", "pmuname10", true); + TEST_PMU_MATCH("No suffix", "pmuname", true); + TEST_PMU_MATCH("Underscore", "pmuname_", false); + TEST_PMU_MATCH("Substring", "pmuna", false); test_pmu.name = "pmunameab23"; - TEST_ASSERT_EQUAL("Diff suffix hex", perf_pmu__match(&test_pmu, "pmuname2"), false); - TEST_ASSERT_EQUAL("Sub suffix hex", perf_pmu__match(&test_pmu, "pmunameab"), true); - TEST_ASSERT_EQUAL("Same suffix hex", perf_pmu__match(&test_pmu, "pmunameab23"), true); - TEST_ASSERT_EQUAL("No suffix hex", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore hex", perf_pmu__match(&test_pmu, "pmuname_"), false); - TEST_ASSERT_EQUAL("Substring hex", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix hex", "pmuname2", false); + TEST_PMU_MATCH("Sub suffix hex", "pmunameab", true); + TEST_PMU_MATCH("Same suffix hex", "pmunameab23", true); + TEST_PMU_MATCH("No suffix hex", "pmuname", true); + TEST_PMU_MATCH("Underscore hex", "pmuname_", false); + TEST_PMU_MATCH("Substring hex", "pmuna", false); /* * 2 hex chars or less are not considered suffixes so it shouldn't be @@ -505,7 +508,7 @@ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest _ * false results here than above. */ test_pmu.name = "pmuname_a3"; - TEST_ASSERT_EQUAL("Diff suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname_2"), false); + TEST_PMU_MATCH("Diff suffix 2 hex_", "pmuname_2", false); /* * This one should be false, but because pmuname_a3 ends in 3 which is * decimal, it's not possible to determine if it's a short hex suffix or @@ -513,19 +516,19 @@ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest _ * length of decimal suffix. Run the test anyway and expect the wrong * result. And slightly fuzzy matching shouldn't do too much harm. */ - TEST_ASSERT_EQUAL("Sub suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname_a"), true); - TEST_ASSERT_EQUAL("Same suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname_a3"), true); - TEST_ASSERT_EQUAL("No suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname"), false); - TEST_ASSERT_EQUAL("Underscore 2 hex_", perf_pmu__match(&test_pmu, "pmuname_"), false); - TEST_ASSERT_EQUAL("Substring 2 hex_", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Sub suffix 2 hex_", "pmuname_a", true); + TEST_PMU_MATCH("Same suffix 2 hex_", "pmuname_a3", true); + TEST_PMU_MATCH("No suffix 2 hex_", "pmuname", false); + TEST_PMU_MATCH("Underscore 2 hex_", "pmuname_", false); + TEST_PMU_MATCH("Substring 2 hex_", "pmuna", false); test_pmu.name = "pmuname_5"; - TEST_ASSERT_EQUAL("Glob 1", perf_pmu__match(&test_pmu, "pmu*"), true); - TEST_ASSERT_EQUAL("Glob 2", perf_pmu__match(&test_pmu, "nomatch*"), false); - TEST_ASSERT_EQUAL("Seq 1", perf_pmu__match(&test_pmu, "pmuname_[12345]"), true); - TEST_ASSERT_EQUAL("Seq 2", perf_pmu__match(&test_pmu, "pmuname_[67890]"), false); - TEST_ASSERT_EQUAL("? 1", perf_pmu__match(&test_pmu, "pmuname_?"), true); - TEST_ASSERT_EQUAL("? 2", perf_pmu__match(&test_pmu, "pmuname_1?"), false); + TEST_PMU_MATCH("Glob 1", "pmu*", true); + TEST_PMU_MATCH("Glob 2", "nomatch*", false); + TEST_PMU_MATCH("Seq 1", "pmuname_[12345]", true); + TEST_PMU_MATCH("Seq 2", "pmuname_[67890]", false); + TEST_PMU_MATCH("? 1", "pmuname_?", true); + TEST_PMU_MATCH("? 2", "pmuname_1?", false); return TEST_OK; } diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 25a3f6cece50..72411580f869 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -40,8 +40,8 @@ #define BS_EXPECTED_LE 0x1aa00000000 #define FLAG(s) s->branch_stack->entries[i].flags -static bool samples_same(const struct perf_sample *s1, - const struct perf_sample *s2, +static bool samples_same(struct perf_sample *s1, + struct perf_sample *s2, u64 type, u64 read_format, bool needs_swap) { size_t i; @@ -126,13 +126,15 @@ static bool samples_same(const struct perf_sample *s1, } if (type & PERF_SAMPLE_REGS_USER) { - size_t sz = hweight_long(s1->user_regs.mask) * sizeof(u64); - - COMP(user_regs.mask); - COMP(user_regs.abi); - if (s1->user_regs.abi && - (!s1->user_regs.regs || !s2->user_regs.regs || - memcmp(s1->user_regs.regs, s2->user_regs.regs, sz))) { + struct regs_dump *s1_regs = perf_sample__user_regs(s1); + struct regs_dump *s2_regs = perf_sample__user_regs(s2); + size_t sz = hweight_long(s1_regs->mask) * sizeof(u64); + + COMP(user_regs->mask); + COMP(user_regs->abi); + if (s1_regs->abi && + (!s1_regs->regs || !s2_regs->regs || + memcmp(s1_regs->regs, s2_regs->regs, sz))) { pr_debug("Samples differ at 'user_regs'\n"); return false; } @@ -157,13 +159,15 @@ static bool samples_same(const struct perf_sample *s1, COMP(transaction); if (type & PERF_SAMPLE_REGS_INTR) { - size_t sz = hweight_long(s1->intr_regs.mask) * sizeof(u64); - - COMP(intr_regs.mask); - COMP(intr_regs.abi); - if (s1->intr_regs.abi && - (!s1->intr_regs.regs || !s2->intr_regs.regs || - memcmp(s1->intr_regs.regs, s2->intr_regs.regs, sz))) { + struct regs_dump *s1_regs = perf_sample__intr_regs(s1); + struct regs_dump *s2_regs = perf_sample__intr_regs(s2); + size_t sz = hweight_long(s1_regs->mask) * sizeof(u64); + + COMP(intr_regs->mask); + COMP(intr_regs->abi); + if (s1_regs->abi && + (!s1_regs->regs || !s2_regs->regs || + memcmp(s1_regs->regs, s2_regs->regs, sz))) { pr_debug("Samples differ at 'intr_regs'\n"); return false; } @@ -223,6 +227,16 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) const u32 raw_data[] = {0x12345678, 0x0a0b0c0d, 0x11020304, 0x05060708, 0 }; const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL}; const u64 aux_data[] = {0xa55a, 0, 0xeeddee, 0x0282028202820282}; + struct regs_dump user_regs = { + .abi = PERF_SAMPLE_REGS_ABI_64, + .mask = sample_regs, + .regs = regs, + }; + struct regs_dump intr_regs = { + .abi = PERF_SAMPLE_REGS_ABI_64, + .mask = sample_regs, + .regs = regs, + }; struct perf_sample sample = { .ip = 101, .pid = 102, @@ -241,11 +255,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .callchain = &callchain.callchain, .no_hw_idx = false, .branch_stack = &branch_stack.branch_stack, - .user_regs = { - .abi = PERF_SAMPLE_REGS_ABI_64, - .mask = sample_regs, - .regs = regs, - }, + .user_regs = &user_regs, .user_stack = { .size = sizeof(data), .data = (void *)data, @@ -254,11 +264,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .time_enabled = 0x030a59d664fca7deULL, .time_running = 0x011b6ae553eb98edULL, }, - .intr_regs = { - .abi = PERF_SAMPLE_REGS_ABI_64, - .mask = sample_regs, - .regs = regs, - }, + .intr_regs = &intr_regs, .phys_addr = 113, .cgroup = 114, .data_page_size = 115, @@ -273,6 +279,8 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) size_t i, sz, bufsz; int err, ret = -1; + perf_sample__init(&sample_out, /*all=*/false); + perf_sample__init(&sample_out_endian, /*all=*/false); if (sample_type & PERF_SAMPLE_REGS_USER) evsel.core.attr.sample_regs_user = sample_regs; @@ -361,6 +369,8 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) ret = 0; out_free: free(event); + perf_sample__exit(&sample_out_endian); + perf_sample__exit(&sample_out); if (ret && read_format) pr_debug("read_format %#"PRIx64"\n", read_format); return ret; diff --git a/tools/perf/tests/shell/annotate.sh b/tools/perf/tests/shell/annotate.sh index 1590a37363de..16a1ccd06089 100755 --- a/tools/perf/tests/shell/annotate.sh +++ b/tools/perf/tests/shell/annotate.sh @@ -35,54 +35,78 @@ trap_cleanup() { trap trap_cleanup EXIT TERM INT test_basic() { - echo "Basic perf annotate test" - if ! perf record -o "${perfdata}" ${testprog} 2> /dev/null + mode=$1 + echo "${mode} perf annotate test" + if [ "x${mode}" == "xBasic" ] then - echo "Basic annotate [Failed: perf record]" + perf record -o "${perfdata}" ${testprog} 2> /dev/null + else + perf record -o - ${testprog} 2> /dev/null > "${perfdata}" + fi + if [ "x$?" != "x0" ] + then + echo "${mode} annotate [Failed: perf record]" err=1 return fi # Generate the annotated output file - perf annotate --no-demangle -i "${perfdata}" --stdio 2> /dev/null | head -250 > "${perfout}" + if [ "x${mode}" == "xBasic" ] + then + perf annotate --no-demangle -i "${perfdata}" --stdio 2> /dev/null > "${perfout}" + else + perf annotate --no-demangle -i - --stdio 2> /dev/null < "${perfdata}" > "${perfout}" + fi # check if it has the target symbol - if ! grep "${testsym}" "${perfout}" + if ! head -250 "${perfout}" | grep -q "${testsym}" then - echo "Basic annotate [Failed: missing target symbol]" + echo "${mode} annotate [Failed: missing target symbol]" err=1 return fi # check if it has the disassembly lines - if ! grep "${disasm_regex}" "${perfout}" + if ! head -250 "${perfout}" | grep -q "${disasm_regex}" then - echo "Basic annotate [Failed: missing disasm output from default disassembler]" + echo "${mode} annotate [Failed: missing disasm output from default disassembler]" err=1 return fi # check again with a target symbol name - if ! perf annotate --no-demangle -i "${perfdata}" "${testsym}" 2> /dev/null | \ - head -250 | grep -m 3 "${disasm_regex}" + if [ "x${mode}" == "xBasic" ] then - echo "Basic annotate [Failed: missing disasm output when specifying the target symbol]" + perf annotate --no-demangle -i "${perfdata}" "${testsym}" 2> /dev/null > "${perfout}" + else + perf annotate --no-demangle -i - "${testsym}" 2> /dev/null < "${perfdata}" > "${perfout}" + fi + + if ! head -250 "${perfout}"| grep -q -m 3 "${disasm_regex}" + then + echo "${mode} annotate [Failed: missing disasm output when specifying the target symbol]" err=1 return fi # check one more with external objdump tool (forced by --objdump option) - if ! perf annotate --no-demangle -i "${perfdata}" --objdump=objdump 2> /dev/null | \ - head -250 | grep -m 3 "${disasm_regex}" + if [ "x${mode}" == "xBasic" ] + then + perf annotate --no-demangle -i "${perfdata}" --objdump=objdump 2> /dev/null > "${perfout}" + else + perf annotate --no-demangle -i - "${testsym}" 2> /dev/null < "${perfdata}" > "${perfout}" + fi + if ! head -250 "${perfout}" | grep -q -m 3 "${disasm_regex}" then - echo "Basic annotate [Failed: missing disasm output from non default disassembler (using --objdump)]" + echo "${mode} annotate [Failed: missing disasm output from non default disassembler (using --objdump)]" err=1 return fi - echo "Basic annotate test [Success]" + echo "${mode} annotate test [Success]" } -test_basic +test_basic Basic +test_basic Pipe cleanup exit $err diff --git a/tools/perf/tests/shell/base_report/setup.sh b/tools/perf/tests/shell/base_report/setup.sh index b03501b2e8fc..8634e7e0dda6 100755 --- a/tools/perf/tests/shell/base_report/setup.sh +++ b/tools/perf/tests/shell/base_report/setup.sh @@ -15,6 +15,8 @@ # include working environment . ../common/init.sh +TEST_RESULT=0 + test -d "$HEADER_TAR_DIR" || mkdir -p "$HEADER_TAR_DIR" SW_EVENT="cpu-clock" @@ -26,7 +28,21 @@ PERF_EXIT_CODE=$? CHECK_EXIT_CODE=$? print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "prepare the perf.data file" -TEST_RESULT=$? +(( TEST_RESULT += $? )) + +# Some minimal parallel workload. +$CMD_PERF record --latency -o $CURRENT_TEST_DIR/perf.data.1 bash -c "for i in {1..100} ; do cat /proc/cpuinfo 1> /dev/null & done; sleep 1" 2> $LOGS_DIR/setup-latency.log +PERF_EXIT_CODE=$? + +echo ================== +cat $LOGS_DIR/setup-latency.log +echo ================== + +../common/check_all_patterns_found.pl "$RE_LINE_RECORD1" "$RE_LINE_RECORD2" < $LOGS_DIR/setup-latency.log +CHECK_EXIT_CODE=$? + +print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "prepare the perf.data.1 file" +(( TEST_RESULT += $? )) print_overall_results $TEST_RESULT exit $? diff --git a/tools/perf/tests/shell/base_report/test_basic.sh b/tools/perf/tests/shell/base_report/test_basic.sh index 2398eba4d3fd..adfd8713b8f8 100755 --- a/tools/perf/tests/shell/base_report/test_basic.sh +++ b/tools/perf/tests/shell/base_report/test_basic.sh @@ -183,6 +183,58 @@ print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "symbol filter" (( TEST_RESULT += $? )) +### latency and parallelism + +# Record with --latency should record with context switches. +$CMD_PERF report -i $CURRENT_TEST_DIR/perf.data.1 --stdio --header-only > $LOGS_DIR/latency_header.log +PERF_EXIT_CODE=$? + +../common/check_all_patterns_found.pl ", context_switch = 1, " < $LOGS_DIR/latency_header.log +CHECK_EXIT_CODE=$? + +print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "latency header" +(( TEST_RESULT += $? )) + + +# The default report for latency profile should show Overhead and Latency fields (in that order). +$CMD_PERF report --stdio -i $CURRENT_TEST_DIR/perf.data.1 > $LOGS_DIR/latency_default.log 2> $LOGS_DIR/latency_default.err +PERF_EXIT_CODE=$? + +../common/check_all_patterns_found.pl "# Overhead Latency Command" < $LOGS_DIR/latency_default.log +CHECK_EXIT_CODE=$? +../common/check_errors_whitelisted.pl "stderr-whitelist.txt" < $LOGS_DIR/latency_default.err +(( CHECK_EXIT_CODE += $? )) + +print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "default report for latency profile" +(( TEST_RESULT += $? )) + + +# The latency report for latency profile should show Latency and Overhead fields (in that order). +$CMD_PERF report --latency --stdio -i $CURRENT_TEST_DIR/perf.data.1 > $LOGS_DIR/latency_latency.log 2> $LOGS_DIR/latency_latency.err +PERF_EXIT_CODE=$? + +../common/check_all_patterns_found.pl "# Latency Overhead Command" < $LOGS_DIR/latency_latency.log +CHECK_EXIT_CODE=$? +../common/check_errors_whitelisted.pl "stderr-whitelist.txt" < $LOGS_DIR/latency_latency.err +(( CHECK_EXIT_CODE += $? )) + +print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "latency report for latency profile" +(( TEST_RESULT += $? )) + + +# Ensure parallelism histogram with parallelism filter does not fail/crash. +$CMD_PERF report --hierarchy --sort latency,parallelism,comm,symbol --parallelism=1,2 --stdio -i $CURRENT_TEST_DIR/perf.data.1 > $LOGS_DIR/parallelism_hierarchy.log 2> $LOGS_DIR/parallelism_hierarchy.err +PERF_EXIT_CODE=$? + +../common/check_all_patterns_found.pl "# Latency Parallelism / Command / Symbol" < $LOGS_DIR/parallelism_hierarchy.log +CHECK_EXIT_CODE=$? +../common/check_errors_whitelisted.pl "stderr-whitelist.txt" < $LOGS_DIR/parallelism_hierarchy.err +(( CHECK_EXIT_CODE += $? )) + +print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "parallelism histogram" +(( TEST_RESULT += $? )) + + # TODO: $CMD_PERF report -n --showcpuutilization -TUxDg 2> 01.log # print overall results diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S index 75cf084a927d..577760046772 100644 --- a/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S +++ b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S @@ -26,3 +26,5 @@ skip: mov x0, #0 mov x8, #93 // __NR_exit syscall svc #0 + +.section .note.GNU-stack, "", @progbits diff --git a/tools/perf/tests/shell/diff.sh b/tools/perf/tests/shell/diff.sh index 14b87af88703..e05a5dc49479 100755 --- a/tools/perf/tests/shell/diff.sh +++ b/tools/perf/tests/shell/diff.sh @@ -39,13 +39,13 @@ make_data() { file="$1" if ! perf record -o "${file}" ${testprog} 2> /dev/null then - echo "Workload record [Failed record]" + echo "Workload record [Failed record]" >&2 echo 1 return fi if ! perf report -i "${file}" -q | grep -q "${testsym}" then - echo "Workload record [Failed missing output]" + echo "Workload record [Failed missing output]" >&2 echo 1 return fi @@ -55,12 +55,12 @@ make_data() { test_two_files() { echo "Basic two file diff test" err=$(make_data "${perfdata1}") - if [ $err != 0 ] + if [ "$err" != 0 ] then return fi err=$(make_data "${perfdata2}") - if [ $err != 0 ] + if [ "$err" != 0 ] then return fi @@ -77,12 +77,12 @@ test_two_files() { test_three_files() { echo "Basic three file diff test" err=$(make_data "${perfdata1}") - if [ $err != 0 ] + if [ "$err" != 0 ] then return fi err=$(make_data "${perfdata2}") - if [ $err != 0 ] + if [ "$err" != 0 ] then return fi diff --git a/tools/perf/tests/shell/lib/attr.py b/tools/perf/tests/shell/lib/attr.py index 3db9a7d78715..bfccc727d9b2 100644 --- a/tools/perf/tests/shell/lib/attr.py +++ b/tools/perf/tests/shell/lib/attr.py @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -from __future__ import print_function - +import configparser import os import sys import glob @@ -13,11 +12,6 @@ import re import shutil import subprocess -try: - import configparser -except ImportError: - import ConfigParser as configparser - def data_equal(a, b): # Allow multiple values in assignment separated by '|' a_list = a.split('|') diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py index b066d721f897..9e772a89ce38 100644 --- a/tools/perf/tests/shell/lib/perf_json_output_lint.py +++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py @@ -19,6 +19,7 @@ ap.add_argument('--per-cluster', action='store_true') ap.add_argument('--per-die', action='store_true') ap.add_argument('--per-node', action='store_true') ap.add_argument('--per-socket', action='store_true') +ap.add_argument('--metric-only', action='store_true') ap.add_argument('--file', type=argparse.FileType('r'), default=sys.stdin) args = ap.parse_args() @@ -64,6 +65,8 @@ def check_json_output(expected_items): 'socket': lambda x: True, 'thread': lambda x: True, 'unit': lambda x: True, + 'insn per cycle': lambda x: isfloat(x), + 'GHz': lambda x: True, # FIXME: it seems unintended for --metric-only } input = '[\n' + ','.join(Lines) + '\n]' for item in json.loads(input): @@ -78,6 +81,8 @@ def check_json_output(expected_items): pass elif count - 1 in expected_items and 'metric-threshold' in item: pass + elif count in expected_items and 'insn per cycle' in item: + pass elif count not in expected_items: raise RuntimeError(f'wrong number of fields. counted {count} expected {expected_items}' f' in \'{item}\'') @@ -95,6 +100,8 @@ try: expected_items = [6, 8] elif args.per_core or args.per_socket or args.per_node or args.per_die or args.per_cluster or args.per_cache: expected_items = [7, 9] + elif args.metric_only: + expected_items = [1, 2] else: # If no option is specified, don't check the number of items. expected_items = -1 diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh index 9a176ceae4a3..4d4aac547f01 100644 --- a/tools/perf/tests/shell/lib/stat_output.sh +++ b/tools/perf/tests/shell/lib/stat_output.sh @@ -148,6 +148,14 @@ check_per_socket() echo "[Success]" } +check_metric_only() +{ + echo -n "Checking $1 output: metric only " + perf stat --metric-only $2 -e instructions,cycles true + commachecker --metric-only + echo "[Success]" +} + # The perf stat options for per-socket, per-core, per-die # and -A ( no_aggr mode ) uses the info fetched from this # directory: "/sys/devices/system/cpu/cpu*/topology". For diff --git a/tools/perf/tests/shell/perftool-testsuite_probe.sh b/tools/perf/tests/shell/perftool-testsuite_probe.sh index 7b1bfd0f888f..3863df16c19b 100755 --- a/tools/perf/tests/shell/perftool-testsuite_probe.sh +++ b/tools/perf/tests/shell/perftool-testsuite_probe.sh @@ -2,6 +2,7 @@ # perftool-testsuite_probe (exclusive) # SPDX-License-Identifier: GPL-2.0 +[ "$(id -u)" = 0 ] || exit 2 test -d "$(dirname "$0")/base_probe" || exit 2 cd "$(dirname "$0")/base_probe" || exit 2 status=0 diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh index 0c5aacc446b3..c51a32931af6 100755 --- a/tools/perf/tests/shell/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/probe_vfs_getname.sh @@ -8,6 +8,7 @@ . "$(dirname $0)"/lib/probe.sh skip_if_no_perf_probe || exit 2 +[ "$(id -u)" = 0 ] || exit 2 # shellcheck source=lib/probe_vfs_getname.sh . "$(dirname $0)"/lib/probe_vfs_getname.sh diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index d5e5193cceb6..c4bab5b5cc59 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -105,6 +105,7 @@ delete_libc_inet_pton_event() { # Check for IPv6 interface existence ip a sh lo | grep -F -q inet6 || exit 2 +[ "$(id -u)" = 0 ] || exit 2 skip_if_no_perf_probe && \ add_libc_inet_pton_event && \ diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh index 5940fdc1df37..fd5b10d46915 100755 --- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh +++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh @@ -13,6 +13,7 @@ . "$(dirname "$0")/lib/probe.sh" skip_if_no_perf_probe || exit 2 +[ "$(id -u)" = 0 ] || exit 2 # shellcheck source=lib/probe_vfs_getname.sh . "$(dirname "$0")/lib/probe_vfs_getname.sh" diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh index 0fc7a909ae9b..ba8d873d3ca7 100755 --- a/tools/perf/tests/shell/record.sh +++ b/tools/perf/tests/shell/record.sh @@ -231,7 +231,7 @@ test_cgroup() { test_leader_sampling() { echo "Basic leader sampling test" - if ! perf record -o "${perfdata}" -e "{instructions,instructions}:Su" -- \ + if ! perf record -o "${perfdata}" -e "{cycles,cycles}:Su" -- \ perf test -w brstack 2> /dev/null then echo "Leader sampling [Failed record]" @@ -243,15 +243,15 @@ test_leader_sampling() { while IFS= read -r line do # Check if the two instruction counts are equal in each record - instructions=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="instructions:") print $(i-1)}') - if [ $(($index%2)) -ne 0 ] && [ ${instructions}x != ${prev_instructions}x ] + cycles=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="cycles:") print $(i-1)}') + if [ $(($index%2)) -ne 0 ] && [ ${cycles}x != ${prev_cycles}x ] then - echo "Leader sampling [Failed inconsistent instructions count]" + echo "Leader sampling [Failed inconsistent cycles count]" err=1 return fi index=$(($index+1)) - prev_instructions=$instructions + prev_cycles=$cycles done < $script_output echo "Basic leader sampling test [Success]" } @@ -273,27 +273,42 @@ test_topdown_leader_sampling() { } test_precise_max() { + local -i skipped=0 + echo "precise_max attribute test" - if ! perf stat -e "cycles,instructions" true 2> /dev/null + # Just to make sure event cycles is supported for sampling + if perf record -o "${perfdata}" -e "cycles" true 2> /dev/null then - echo "precise_max attribute [Skipped no hardware events]" - return + if ! perf record -o "${perfdata}" -e "cycles:P" true 2> /dev/null + then + echo "precise_max attribute [Failed cycles:P event]" + err=1 + return + fi + else + echo "precise_max attribute [Skipped no cycles:P event]" + ((skipped+=1)) fi - # Just to make sure it doesn't fail - if ! perf record -o "${perfdata}" -e "cycles:P" true 2> /dev/null + # On s390 event instructions is not supported for perf record + if perf record -o "${perfdata}" -e "instructions" true 2> /dev/null then - echo "precise_max attribute [Failed cycles:P event]" - err=1 - return + # On AMD, cycles and instructions events are treated differently + if ! perf record -o "${perfdata}" -e "instructions:P" true 2> /dev/null + then + echo "precise_max attribute [Failed instructions:P event]" + err=1 + return + fi + else + echo "precise_max attribute [Skipped no instructions:P event]" + ((skipped+=1)) fi - # On AMD, cycles and instructions events are treated differently - if ! perf record -o "${perfdata}" -e "instructions:P" true 2> /dev/null + if [ $skipped -eq 2 ] then - echo "precise_max attribute [Failed instructions:P event]" - err=1 - return + echo "precise_max attribute [Skipped no hardware events]" + else + echo "precise_max attribute test [Success]" fi - echo "precise_max attribute test [Success]" } # raise the limit of file descriptors to minimum diff --git a/tools/perf/tests/shell/record_bpf_filter.sh b/tools/perf/tests/shell/record_bpf_filter.sh index 1b58ccc1fd88..4d6c3c1b7fb9 100755 --- a/tools/perf/tests/shell/record_bpf_filter.sh +++ b/tools/perf/tests/shell/record_bpf_filter.sh @@ -89,7 +89,7 @@ test_bpf_filter_fail() { test_bpf_filter_group() { echo "Group bpf-filter test" - if ! perf record -e task-clock --filter 'period > 1000 || ip > 0' \ + if ! perf record -e task-clock --filter 'period > 1000, ip > 0' \ -o /dev/null true 2>/dev/null then echo "Group bpf-filter test [Failed should succeed]" @@ -97,7 +97,7 @@ test_bpf_filter_group() { return fi - if ! perf record -e task-clock --filter 'cpu > 0 || ip > 0' \ + if ! perf record -e task-clock --filter 'period > 1000 , cpu > 0 || ip > 0' \ -o /dev/null true 2>&1 | grep -q PERF_SAMPLE_CPU then echo "Group bpf-filter test [Failed forbidden CPU]" diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index fc2d8cc6e5e0..7a6f6e177402 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -44,6 +44,7 @@ function commachecker() ;; "--per-die") exp=8 ;; "--per-cluster") exp=8 ;; "--per-cache") exp=8 + ;; "--metric-only") exp=2 esac while read line @@ -75,6 +76,7 @@ check_interval "CSV" "$perf_cmd" check_event "CSV" "$perf_cmd" check_per_thread "CSV" "$perf_cmd" check_per_node "CSV" "$perf_cmd" +check_metric_only "CSV" "$perf_cmd" if [ $skip_test -ne 1 ] then check_system_wide_no_aggr "CSV" "$perf_cmd" diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index 6b630d33c328..a4f257ea839e 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -173,6 +173,14 @@ check_per_socket() echo "[Success]" } +check_metric_only() +{ + echo -n "Checking json output: metric only " + perf stat -j --metric-only -e instructions,cycles -o "${stat_output}" true + $PYTHON $pythonchecker --metric-only --file "${stat_output}" + echo "[Success]" +} + # The perf stat options for per-socket, per-core, per-die # and -A ( no_aggr mode ) uses the info fetched from this # directory: "/sys/devices/system/cpu/cpu*/topology". For @@ -207,6 +215,7 @@ check_interval check_event check_per_thread check_per_node +check_metric_only if [ $skip_test -ne 1 ] then check_system_wide_no_aggr diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh index 0f7967be60af..6fee67693ba7 100755 --- a/tools/perf/tests/shell/stat+std_output.sh +++ b/tools/perf/tests/shell/stat+std_output.sh @@ -30,6 +30,7 @@ trap trap_cleanup EXIT TERM INT function commachecker() { local prefix=1 + local -i metric_only=0 case "$1" in "--interval") prefix=2 @@ -41,6 +42,7 @@ function commachecker() ;; "--per-die") prefix=3 ;; "--per-cache") prefix=3 ;; "--per-cluster") prefix=3 + ;; "--metric-only") metric_only=1 esac while read line @@ -60,6 +62,9 @@ function commachecker() x=${main_body%#*} [ "$x" = "" ] && continue + # Check metric only - if it has a non-empty result + [ $metric_only -eq 1 ] && return 0 + # Skip metrics without event name y=${main_body#*#} for i in "${!skip_metric[@]}"; do @@ -84,6 +89,8 @@ function commachecker() exit 1; } done < "${stat_output}" + + [ $metric_only -eq 1 ] && exit 1 return 0 } @@ -95,6 +102,7 @@ check_system_wide "STD" "$perf_cmd" check_interval "STD" "$perf_cmd" check_per_thread "STD" "$perf_cmd" check_per_node "STD" "$perf_cmd" +check_metric_only "STD" "$perf_cmd" if [ $skip_test -ne 1 ] then check_system_wide_no_aggr "STD" "$perf_cmd" diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 68323d636fb7..8a100a7f2dc1 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # perf stat tests # SPDX-License-Identifier: GPL-2.0 @@ -67,43 +67,54 @@ test_topdown_groups() { echo "Topdown event group test [Skipped event parsing failed]" return fi - if perf stat -e '{slots,topdown-retiring}' true 2>&1 | grep -E -q "<not supported>" - then - echo "Topdown event group test [Failed events not supported]" - err=1 - return - fi - if perf stat -e 'instructions,topdown-retiring,slots' true 2>&1 | grep -E -q "<not supported>" - then - echo "Topdown event group test [Failed slots not reordered first in no-group case]" - err=1 - return - fi - if perf stat -e '{instructions,topdown-retiring,slots}' true 2>&1 | grep -E -q "<not supported>" - then - echo "Topdown event group test [Failed slots not reordered first in single group case]" - err=1 - return - fi - if perf stat -e '{instructions,slots},topdown-retiring' true 2>&1 | grep -E -q "<not supported>" - then - echo "Topdown event group test [Failed topdown metrics event not move into slots group]" - err=1 - return - fi - if perf stat -e '{instructions,slots},{topdown-retiring}' true 2>&1 | grep -E -q "<not supported>" - then - echo "Topdown event group test [Failed topdown metrics group not merge into slots group]" - err=1 - return - fi - if perf stat -e '{instructions,r400,r8000}' true 2>&1 | grep -E -q "<not supported>" + td_err=0 + do_topdown_group_test() { + events=$1 + failure=$2 + if perf stat -e "$events" true 2>&1 | grep -E -q "<not supported>" + then + echo "Topdown event group test [Failed $failure for '$events']" + td_err=1 + return + fi + } + do_topdown_group_test "{slots,topdown-retiring}" "events not supported" + do_topdown_group_test "{instructions,r400,r8000}" "raw format slots not reordered first" + filler_events=("instructions" "cycles" + "context-switches" "faults") + for ((i = 0; i < ${#filler_events[@]}; i+=2)) + do + filler1=${filler_events[i]} + filler2=${filler_events[i+1]} + do_topdown_group_test "$filler1,topdown-retiring,slots" \ + "slots not reordered first in no-group case" + do_topdown_group_test "slots,$filler1,topdown-retiring" \ + "topdown metrics event not reordered in no-group case" + do_topdown_group_test "{$filler1,topdown-retiring,slots}" \ + "slots not reordered first in single group case" + do_topdown_group_test "{$filler1,slots},topdown-retiring" \ + "topdown metrics event not move into slots group" + do_topdown_group_test "topdown-retiring,{$filler1,slots}" \ + "topdown metrics event not move into slots group last" + do_topdown_group_test "{$filler1,slots},{topdown-retiring}" \ + "topdown metrics group not merge into slots group" + do_topdown_group_test "{topdown-retiring},{$filler1,slots}" \ + "topdown metrics group not merge into slots group last" + do_topdown_group_test "{$filler1,slots},$filler2,topdown-retiring" \ + "non-adjacent topdown metrics group not move into slots group" + do_topdown_group_test "$filler2,topdown-retiring,{$filler1,slots}" \ + "non-adjacent topdown metrics group not move into slots group last" + do_topdown_group_test "{$filler1,slots},{$filler2,topdown-retiring}" \ + "metrics group not merge into slots group" + do_topdown_group_test "{$filler1,topdown-retiring},{$filler2,slots}" \ + "metrics group not merge into slots group last" + done + if test "$td_err" -eq 0 then - echo "Topdown event group test [Failed raw format slots not reordered first]" - err=1 - return + echo "Topdown event group test [Success]" + else + err="$td_err" fi - echo "Topdown event group test [Success]" } test_topdown_weak_groups() { diff --git a/tools/perf/tests/shell/stat_all_metrics.sh b/tools/perf/tests/shell/stat_all_metrics.sh index 73e9347e88a9..ee817c66da06 100755 --- a/tools/perf/tests/shell/stat_all_metrics.sh +++ b/tools/perf/tests/shell/stat_all_metrics.sh @@ -20,7 +20,13 @@ for m in $(perf list --raw-dump metrics); do result_err=$? if [[ $result_err -gt 0 ]] then - if [[ "$result" =~ \ + if [[ "$result" =~ "Cannot resolve IDs for" ]] + then + echo "Metric contains missing events" + echo $result + err=1 # Fail + continue + elif [[ "$result" =~ \ "Access to performance monitoring and observability operations is limited" ]] then echo "Permission failure" diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh index 8b148b300be1..9c466c0efa85 100755 --- a/tools/perf/tests/shell/stat_all_pmu.sh +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -2,7 +2,6 @@ # perf all PMU test (exclusive) # SPDX-License-Identifier: GPL-2.0 -set -e err=0 result="" @@ -16,34 +15,55 @@ trap trap_cleanup EXIT TERM INT # Test all PMU events; however exclude parameterized ones (name contains '?') for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g') do - echo "Testing $p" - result=$(perf stat -e "$p" true 2>&1) - if echo "$result" | grep -q "$p" + echo -n "Testing $p -- " + output=$(perf stat -e "$p" true 2>&1) + stat_result=$? + if echo "$output" | grep -q "$p" then # Event seen in output. - continue - fi - if echo "$result" | grep -q "<not supported>" - then - # Event not supported, so ignore. - continue + if [ $stat_result -eq 0 ] && ! echo "$output" | grep -q "<not supported>" + then + # Event supported. + echo "supported" + continue + elif echo "$output" | grep -q "<not supported>" + then + # Event not supported, so ignore. + echo "not supported" + continue + elif echo "$output" | grep -q "No permission to enable" + then + # No permissions, so ignore. + echo "no permission to enable" + continue + elif echo "$output" | grep -q "Bad event name" + then + # Non-existent event. + echo "Error: Bad event name" + echo "$output" + err=1 + continue + fi fi - if echo "$result" | grep -q "Access to performance monitoring and observability operations is limited." + + if echo "$output" | grep -q "Access to performance monitoring and observability operations is limited." then # Access is limited, so ignore. + echo "access limited" continue fi # We failed to see the event and it is supported. Possibly the workload was # too small so retry with something longer. - result=$(perf stat -e "$p" perf bench internals synthesize 2>&1) - if echo "$result" | grep -q "$p" + output=$(perf stat -e "$p" perf bench internals synthesize 2>&1) + if echo "$output" | grep -q "$p" then # Event seen in output. + echo "supported" continue fi echo "Error: event '$p' not printed in:" - echo "$result" + echo "$output" err=1 done diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh index c86da0235059..bbe8277496ae 100755 --- a/tools/perf/tests/shell/test_data_symbol.sh +++ b/tools/perf/tests/shell/test_data_symbol.sh @@ -5,8 +5,6 @@ # Leo Yan <leo.yan@linaro.org>, 2022 shelldir=$(dirname "$0") -# shellcheck source=lib/waiting.sh -. "${shelldir}"/lib/waiting.sh # shellcheck source=lib/perf_has_symbol.sh . "${shelldir}"/lib/perf_has_symbol.sh @@ -18,7 +16,7 @@ skip_if_no_mem_event() { skip_if_no_mem_event || exit 2 -skip_test_missing_symbol buf1 +skip_test_missing_symbol workload_datasym_buf1 TEST_PROGRAM="perf test -w datasym" PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX) @@ -26,18 +24,19 @@ ERR_FILE=$(mktemp /tmp/__perf_test.stderr.XXXXX) check_result() { # The memory report format is as below: - # 99.92% ... [.] buf1+0x38 + # 99.92% ... [.] workload_datasym_buf1+0x38 result=$(perf mem report -i ${PERF_DATA} -s symbol_daddr -q 2>&1 | - awk '/buf1/ { print $4 }') + awk '/workload_datasym_buf1/ { print $4 }') - # Testing is failed if has no any sample for "buf1" + # Testing is failed if has no any sample for "workload_datasym_buf1" [ -z "$result" ] && return 1 while IFS= read -r line; do - # The "data1" and "data2" fields in structure "buf1" have - # offset "0x0" and "0x38", returns failure if detect any - # other offset value. - if [ "$line" != "buf1+0x0" ] && [ "$line" != "buf1+0x38" ]; then + # The "data1" and "data2" fields in structure + # "workload_datasym_buf1" have offset "0x0" and "0x38", returns + # failure if detect any other offset value. + if [ "$line" != "workload_datasym_buf1+0x0" ] && \ + [ "$line" != "workload_datasym_buf1+0x38" ]; then return 1 fi done <<< "$result" @@ -60,19 +59,10 @@ echo "Recording workload..." # specific CPU and test in per-CPU mode. is_amd=$(grep -E -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo) if (($is_amd >= 1)); then - perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}" & + perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}" else - perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}" & + perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}" fi -PERFPID=$! - -wait_for_perf_to_start ${PERFPID} "${ERR_FILE}" - -sleep 1 - -kill $PERFPID -wait $PERFPID - check_result exit $? diff --git a/tools/perf/tests/shell/test_stat_intel_tpebs.sh b/tools/perf/tests/shell/test_stat_intel_tpebs.sh index f95fc64bf0a7..a330ecdb7ba5 100755 --- a/tools/perf/tests/shell/test_stat_intel_tpebs.sh +++ b/tools/perf/tests/shell/test_stat_intel_tpebs.sh @@ -3,20 +3,83 @@ # SPDX-License-Identifier: GPL-2.0 set -e -grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; } -# Use this event for testing because it should exist in all platforms -event=cache-misses:R +ParanoidAndNotRoot() { + [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ] +} -# Hybrid platforms output like "cpu_atom/cache-misses/R", rather than as above -alt_name=/cache-misses/R +if ! grep -q GenuineIntel /proc/cpuinfo +then + echo "Skipping non-Intel" + exit 2 +fi -# Without this cmd option, default value or zero is returned -#echo "Testing without --record-tpebs" -#result=$(perf stat -e "$event" true 2>&1) -#[[ "$result" =~ $event || "$result" =~ $alt_name ]] || exit 1 +if ParanoidAndNotRoot 0 +then + echo "Skipping paranoid >0 and not root" + exit 2 +fi -# In platforms that do not support TPEBS, it should execute without error. -echo "Testing with --record-tpebs" -result=$(perf stat -e "$event" --record-tpebs -a sleep 0.01 2>&1) -[[ "$result" =~ "perf record" && "$result" =~ $event || "$result" =~ $alt_name ]] || exit 1 +stat_output=$(mktemp /tmp/__perf_stat_tpebs_output.XXXXX) + +cleanup() { + rm -rf "${stat_output}" + trap - EXIT TERM INT +} + +trap_cleanup() { + echo "Unexpected signal in ${FUNCNAME[1]}" + cat "${stat_output}" + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT + +# Event to be used in tests +event=cache-misses + +if ! perf record -e "${event}:p" -a -o /dev/null sleep 0.01 > "${stat_output}" 2>&1 +then + echo "Missing ${event} support" + cleanup + exit 2 +fi + +test_with_record_tpebs() { + echo "Testing with --record-tpebs" + if ! perf stat -e "${event}:R" --record-tpebs -a sleep 0.01 > "${stat_output}" 2>&1 + then + echo "Testing with --record-tpebs [Failed perf stat]" + cat "${stat_output}" + exit 1 + fi + + # Expected output: + # $ perf stat --record-tpebs -e cache-misses:R -a sleep 0.01 + # Events enabled + # [ perf record: Woken up 2 times to write data ] + # [ perf record: Captured and wrote 0.056 MB - ] + # + # Performance counter stats for 'system wide': + # + # 0 cache-misses:R + # + # 0.013963299 seconds time elapsed + if ! grep "perf record" "${stat_output}" + then + echo "Testing with --record-tpebs [Failed missing perf record]" + cat "${stat_output}" + exit 1 + fi + if ! grep "${event}:R" "${stat_output}" && ! grep "/${event}/R" "${stat_output}" + then + echo "Testing with --record-tpebs [Failed missing event name]" + cat "${stat_output}" + exit 1 + fi + echo "Testing with --record-tpebs [Success]" +} + +test_with_record_tpebs +cleanup +exit 0 diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh index 33387c329f92..7adf9755d6de 100755 --- a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -4,12 +4,11 @@ set -e -# Skip if there's no probe command. -if ! perf | grep probe -then - echo "Skip: probe command isn't present" - exit 2 -fi +# shellcheck source=lib/probe.sh +. "$(dirname $0)"/lib/probe.sh + +skip_if_no_perf_probe || exit 2 +[ "$(id -u)" == 0 ] || exit 2 # skip if there's no gcc if ! [ -x "$(command -v gcc)" ]; then diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 708a13f00635..60fccb62c540 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -15,6 +15,7 @@ skip_if_no_perf_probe || exit 2 skip_if_no_perf_trace || exit 2 +[ "$(id -u)" = 0 ] || exit 2 . "$(dirname $0)"/lib/probe_vfs_getname.sh diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh index 8d1e6bbeac90..60b3fa254cf6 100755 --- a/tools/perf/tests/shell/trace_btf_enum.sh +++ b/tools/perf/tests/shell/trace_btf_enum.sh @@ -13,6 +13,7 @@ TESTPROG="perf test -w landlock" # shellcheck source=lib/probe.sh . "$(dirname $0)"/lib/probe.sh skip_if_no_perf_trace || exit 2 +[ "$(id -u)" = 0 ] || exit 2 check_vmlinux() { echo "Checking if vmlinux exists" diff --git a/tools/perf/tests/shell/trace_btf_general.sh b/tools/perf/tests/shell/trace_btf_general.sh index e9ee727f3433..a25d8744695e 100755 --- a/tools/perf/tests/shell/trace_btf_general.sh +++ b/tools/perf/tests/shell/trace_btf_general.sh @@ -76,6 +76,7 @@ trace_config() { skip_if_no_perf_trace || exit 2 check_vmlinux || exit 2 +[ "$(id -u)" = 0 ] || exit 2 trace_config diff --git a/tools/perf/tests/shell/trace_exit_race.sh b/tools/perf/tests/shell/trace_exit_race.sh index fbb0adc33a88..1e247693e756 100755 --- a/tools/perf/tests/shell/trace_exit_race.sh +++ b/tools/perf/tests/shell/trace_exit_race.sh @@ -10,6 +10,7 @@ . "$(dirname $0)"/lib/probe.sh skip_if_no_perf_trace || exit 2 +[ "$(id -u)" = 0 ] || exit 2 if [ "$1" = "-v" ]; then verbose="1" diff --git a/tools/perf/tests/shell/trace_record_replay.sh b/tools/perf/tests/shell/trace_record_replay.sh new file mode 100755 index 000000000000..6b4ed863c1ef --- /dev/null +++ b/tools/perf/tests/shell/trace_record_replay.sh @@ -0,0 +1,21 @@ +#!/bin/sh +# perf trace record and replay +# SPDX-License-Identifier: GPL-2.0 + +# Check that perf trace works with record and replay + +# shellcheck source=lib/probe.sh +. "$(dirname $0)"/lib/probe.sh + +skip_if_no_perf_trace || exit 2 +[ "$(id -u)" = 0 ] || exit 2 + +file=$(mktemp /tmp/temporary_file.XXXXX) + +perf trace record -o ${file} sleep 1 || exit 1 +if ! perf trace -i ${file} 2>&1 | grep nanosleep; then + echo "Failed: cannot find *nanosleep syscall" + exit 1 +fi + +rm -f ${file} diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 290716783ac6..4a2ad7176fa0 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -104,12 +104,14 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) while ((event = perf_mmap__read_event(&md->core)) != NULL) { struct perf_sample sample; + perf_sample__init(&sample, /*all=*/false); if (event->header.type != PERF_RECORD_SAMPLE) goto next_event; err = evlist__parse_sample(evlist, event, &sample); if (err < 0) { pr_debug("Error during parse sample\n"); + perf_sample__exit(&sample); goto out_delete_evlist; } @@ -117,6 +119,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) nr_samples++; next_event: perf_mmap__consume(&md->core); + perf_sample__exit(&sample); } perf_mmap__read_done(&md->core); diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 576f82a15015..8df3f9d9ffd2 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -131,9 +131,11 @@ static int process_sample_event(struct evlist *evlist, pid_t next_tid, prev_tid; int cpu, err; + perf_sample__init(&sample, /*all=*/false); if (evlist__parse_sample(evlist, event, &sample)) { pr_debug("evlist__parse_sample failed\n"); - return -1; + err = -1; + goto out; } evsel = evlist__id2evsel(evlist, sample.id); @@ -145,7 +147,7 @@ static int process_sample_event(struct evlist *evlist, cpu, prev_tid, next_tid); err = check_cpu(switch_tracking, cpu); if (err) - return err; + goto out; /* * Check for no missing sched_switch events i.e. that the * evsel->core.system_wide flag has worked. @@ -153,7 +155,8 @@ static int process_sample_event(struct evlist *evlist, if (switch_tracking->tids[cpu] != -1 && switch_tracking->tids[cpu] != prev_tid) { pr_debug("Missing sched_switch events\n"); - return -1; + err = -1; + goto out; } switch_tracking->tids[cpu] = next_tid; } @@ -169,7 +172,10 @@ static int process_sample_event(struct evlist *evlist, switch_tracking->cycles_after_comm_4 = 1; } - return 0; + err = 0; +out: + perf_sample__exit(&sample); + return err; } static int process_event(struct evlist *evlist, union perf_event *event, diff --git a/tools/perf/tests/tool_pmu.c b/tools/perf/tests/tool_pmu.c index 187942b749b7..1e900ef92e37 100644 --- a/tools/perf/tests/tool_pmu.c +++ b/tools/perf/tests/tool_pmu.c @@ -27,7 +27,7 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu) parse_events_error__init(&err); ret = parse_events(evlist, str, &err); if (ret) { - if (tool_pmu__skip_event(tool_pmu__event_to_str(ev))) { + if (!tool_pmu__event_to_str(ev)) { ret = TEST_OK; goto out; } @@ -59,7 +59,7 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu) } } - if (!found && !tool_pmu__skip_event(tool_pmu__event_to_str(ev))) { + if (!found && tool_pmu__event_to_str(ev)) { pr_debug("FAILED %s:%d Didn't find tool event '%s' in parsed evsels\n", __FILE__, __LINE__, str); ret = TEST_FAIL; diff --git a/tools/perf/tests/workloads/datasym.c b/tools/perf/tests/workloads/datasym.c index 8e08fc75a973..1d0b7d64e1ba 100644 --- a/tools/perf/tests/workloads/datasym.c +++ b/tools/perf/tests/workloads/datasym.c @@ -1,3 +1,6 @@ +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> #include <linux/compiler.h> #include "../tests.h" @@ -7,16 +10,33 @@ typedef struct _buf { char data2; } buf __attribute__((aligned(64))); -static buf buf1 = { +/* volatile to try to avoid the compiler seeing reserved as unused. */ +static volatile buf workload_datasym_buf1 = { /* to have this in the data section */ .reserved[0] = 1, }; -static int datasym(int argc __maybe_unused, const char **argv __maybe_unused) +static volatile sig_atomic_t done; + +static void sighandler(int sig __maybe_unused) +{ + done = 1; +} + +static int datasym(int argc, const char **argv) { - for (;;) { - buf1.data1++; - if (buf1.data1 == 123) { + int sec = 1; + + if (argc > 0) + sec = atoi(argv[0]); + + signal(SIGINT, sighandler); + signal(SIGALRM, sighandler); + alarm(sec); + + while (!done) { + workload_datasym_buf1.data1++; + if (workload_datasym_buf1.data1 == 123) { /* * Add some 'noise' in the loop to work around errata * 1694299 on Arm N1. @@ -30,9 +50,9 @@ static int datasym(int argc __maybe_unused, const char **argv __maybe_unused) * longer a continuous repeating pattern that interacts * badly with the bias. */ - buf1.data1++; + workload_datasym_buf1.data1++; } - buf1.data2 += buf1.data1; + workload_datasym_buf1.data2 += workload_datasym_buf1.data1; } return 0; } diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build index cb3c1399ff40..f50ebdc445b8 100644 --- a/tools/perf/trace/beauty/Build +++ b/tools/perf/trace/beauty/Build @@ -23,14 +23,14 @@ perf-y += tracepoints/ ifdef SHELLCHECK SHELL_TESTS := $(wildcard trace/beauty/*.sh) - TEST_LOGS := $(SHELL_TESTS:trace/beauty/%=%.shellcheck_log) + SHELL_TEST_LOGS := $(SHELL_TESTS:trace/beauty/%=%.shellcheck_log) else SHELL_TESTS := - TEST_LOGS := + SHELL_TEST_LOGS := endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) $(Q)$(call echo-cmd,test)shellcheck -s bash -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) -perf-y += $(TEST_LOGS) +perf-y += $(SHELL_TEST_LOGS) diff --git a/tools/perf/trace/beauty/syscalltbl.sh b/tools/perf/trace/beauty/syscalltbl.sh new file mode 100755 index 000000000000..1199618dc178 --- /dev/null +++ b/tools/perf/trace/beauty/syscalltbl.sh @@ -0,0 +1,274 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate all syscall tables. +# +# Each line of the syscall table should have the following format: +# +# NR ABI NAME [NATIVE] [COMPAT [noreturn]] +# +# NR syscall number +# ABI ABI name +# NAME syscall name +# NATIVE native entry point (optional) +# COMPAT compat entry point (optional) +# noreturn system call doesn't return (optional) +set -e + +usage() { + cat >&2 <<EOF +usage: $0 <TOOLS DIRECTORY> <OUTFILE> + + <TOOLS DIRECTORY> path to kernel tools directory + <OUTFILE> output header file +EOF + exit 1 +} + +if [ $# -ne 2 ]; then + usage +fi +tools_dir=$1 +outfile=$2 + +build_tables() { + infile="$1" + outfile="$2" + abis=$(echo "($3)" | tr ',' '|') + e_machine="$4" + + if [ ! -f "$infile" ] + then + echo "Missing file $infile" + exit 1 + fi + sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) + grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | sort -n > "$sorted_table" + + echo "static const char *const syscall_num_to_name_${e_machine}[] = {" >> "$outfile" + # the params are: nr abi name entry compat + # use _ for intentionally unused variables according to SC2034 + while read -r nr _ name _ _; do + echo " [$nr] = \"$name\"," >> "$outfile" + done < "$sorted_table" + echo "};" >> "$outfile" + + echo "static const uint16_t syscall_sorted_names_${e_machine}[] = {" >> "$outfile" + + # When sorting by name, add a suffix of 0s upto 20 characters so that + # system calls that differ with a numerical suffix don't sort before + # those without. This default behavior of sort differs from that of + # strcmp used at runtime. Use sed to strip the trailing 0s suffix + # afterwards. + grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | awk '{printf $3; for (i = length($3); i < 20; i++) { printf "0"; }; print " " $1}'| sort | sed 's/\([a-zA-Z1-9]\+\)0\+ \([0-9]\+\)/\1 \2/' > "$sorted_table" + while read -r name nr; do + echo " $nr, /* $name */" >> "$outfile" + done < "$sorted_table" + echo "};" >> "$outfile" + + rm -f "$sorted_table" +} + +rm -f "$outfile" +cat >> "$outfile" <<EOF +#include <elf.h> +#include <stdint.h> +#include <asm/bitsperlong.h> +#include <linux/kernel.h> + +struct syscalltbl { + const char *const *num_to_name; + const uint16_t *sorted_names; + uint16_t e_machine; + uint16_t num_to_name_len; + uint16_t sorted_names_len; +}; + +#if defined(ALL_SYSCALLTBL) || defined(__alpha__) +EOF +build_tables "$tools_dir/perf/arch/alpha/entry/syscalls/syscall.tbl" "$outfile" common,64 EM_ALPHA +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__alpha__) + +#if defined(ALL_SYSCALLTBL) || defined(__arm__) || defined(__aarch64__) +EOF +build_tables "$tools_dir/perf/arch/arm/entry/syscalls/syscall.tbl" "$outfile" common,32,oabi EM_ARM +build_tables "$tools_dir/perf/arch/arm64/entry/syscalls/syscall_64.tbl" "$outfile" common,64,renameat,rlimit,memfd_secret EM_AARCH64 +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__arm__) || defined(__aarch64__) + +#if defined(ALL_SYSCALLTBL) || defined(__csky__) +EOF +build_tables "$tools_dir/scripts/syscall.tbl" "$outfile" common,32,csky,time32,stat64,rlimit EM_CSKY +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__csky__) + +#if defined(ALL_SYSCALLTBL) || defined(__mips__) +EOF +build_tables "$tools_dir/perf/arch/mips/entry/syscalls/syscall_n64.tbl" "$outfile" common,64,n64 EM_MIPS +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__mips__) + +#if defined(ALL_SYSCALLTBL) || defined(__hppa__) +#if __BITS_PER_LONG != 64 +EOF +build_tables "$tools_dir/perf/arch/parisc/entry/syscalls/syscall.tbl" "$outfile" common,32 EM_PARISC +echo "#else" >> "$outfile" +build_tables "$tools_dir/perf/arch/parisc/entry/syscalls/syscall.tbl" "$outfile" common,64 EM_PARISC +cat >> "$outfile" <<EOF +#endif //__BITS_PER_LONG != 64 +#endif // defined(ALL_SYSCALLTBL) || defined(__hppa__) + +#if defined(ALL_SYSCALLTBL) || defined(__powerpc__) || defined(__powerpc64__) +EOF +build_tables "$tools_dir/perf/arch/powerpc/entry/syscalls/syscall.tbl" "$outfile" common,32,nospu EM_PPC +build_tables "$tools_dir/perf/arch/powerpc/entry/syscalls/syscall.tbl" "$outfile" common,64,nospu EM_PPC64 +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__powerpc__) || defined(__powerpc64__) + +#if defined(ALL_SYSCALLTBL) || defined(__riscv) +#if __BITS_PER_LONG != 64 +EOF +build_tables "$tools_dir/scripts/syscall.tbl" "$outfile" common,32,riscv,memfd_secret EM_RISCV +echo "#else" >> "$outfile" +build_tables "$tools_dir/scripts/syscall.tbl" "$outfile" common,64,riscv,rlimit,memfd_secret EM_RISCV +cat >> "$outfile" <<EOF +#endif //__BITS_PER_LONG != 64 +#endif // defined(ALL_SYSCALLTBL) || defined(__riscv) +#if defined(ALL_SYSCALLTBL) || defined(__s390x__) +EOF +build_tables "$tools_dir/perf/arch/s390/entry/syscalls/syscall.tbl" "$outfile" common,64,renameat,rlimit,memfd_secret EM_S390 +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__s390x__) + +#if defined(ALL_SYSCALLTBL) || defined(__sh__) +EOF +build_tables "$tools_dir/perf/arch/sh/entry/syscalls/syscall.tbl" "$outfile" common,32 EM_SH +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__sh__) + +#if defined(ALL_SYSCALLTBL) || defined(__sparc64__) || defined(__sparc__) +#if __BITS_PER_LONG != 64 +EOF +build_tables "$tools_dir/perf/arch/sparc/entry/syscalls/syscall.tbl" "$outfile" common,32 EM_SPARC +echo "#else" >> "$outfile" +build_tables "$tools_dir/perf/arch/sparc/entry/syscalls/syscall.tbl" "$outfile" common,64 EM_SPARC +cat >> "$outfile" <<EOF +#endif //__BITS_PER_LONG != 64 +#endif // defined(ALL_SYSCALLTBL) || defined(__sparc64__) || defined(__sparc__) + +#if defined(ALL_SYSCALLTBL) || defined(__i386__) || defined(__x86_64__) +EOF +build_tables "$tools_dir/perf/arch/x86/entry/syscalls/syscall_32.tbl" "$outfile" common,32,i386 EM_386 +build_tables "$tools_dir/perf/arch/x86/entry/syscalls/syscall_64.tbl" "$outfile" common,64 EM_X86_64 +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__i386__) || defined(__x86_64__) + +#if defined(ALL_SYSCALLTBL) || defined(__xtensa__) +EOF +build_tables "$tools_dir/perf/arch/xtensa/entry/syscalls/syscall.tbl" "$outfile" common,32 EM_XTENSA +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__xtensa__) + +#if __BITS_PER_LONG != 64 +EOF +build_tables "$tools_dir/scripts/syscall.tbl" "$outfile" common,32 EM_NONE +echo "#else" >> "$outfile" +build_tables "$tools_dir/scripts/syscall.tbl" "$outfile" common,64 EM_NONE +echo "#endif //__BITS_PER_LONG != 64" >> "$outfile" + +build_outer_table() { + e_machine=$1 + outfile="$2" + cat >> "$outfile" <<EOF + { + .num_to_name = syscall_num_to_name_$e_machine, + .sorted_names = syscall_sorted_names_$e_machine, + .e_machine = $e_machine, + .num_to_name_len = ARRAY_SIZE(syscall_num_to_name_$e_machine), + .sorted_names_len = ARRAY_SIZE(syscall_sorted_names_$e_machine), + }, +EOF +} + +cat >> "$outfile" <<EOF +static const struct syscalltbl syscalltbls[] = { +#if defined(ALL_SYSCALLTBL) || defined(__alpha__) +EOF +build_outer_table EM_ALPHA "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__alpha__) + +#if defined(ALL_SYSCALLTBL) || defined(__arm__) || defined(__aarch64__) +EOF +build_outer_table EM_ARM "$outfile" +build_outer_table EM_AARCH64 "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__arm__) || defined(__aarch64__) + +#if defined(ALL_SYSCALLTBL) || defined(__csky__) +EOF +build_outer_table EM_CSKY "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__csky__) + +#if defined(ALL_SYSCALLTBL) || defined(__mips__) +EOF +build_outer_table EM_MIPS "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__mips__) + +#if defined(ALL_SYSCALLTBL) || defined(__hppa__) +EOF +build_outer_table EM_PARISC "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__hppa__) + +#if defined(ALL_SYSCALLTBL) || defined(__powerpc__) || defined(__powerpc64__) +EOF +build_outer_table EM_PPC "$outfile" +build_outer_table EM_PPC64 "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__powerpc__) || defined(__powerpc64__) + +#if defined(ALL_SYSCALLTBL) || defined(__riscv) +EOF +build_outer_table EM_RISCV "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__riscv) + +#if defined(ALL_SYSCALLTBL) || defined(__s390x__) +EOF +build_outer_table EM_S390 "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__s390x__) + +#if defined(ALL_SYSCALLTBL) || defined(__sh__) +EOF +build_outer_table EM_SH "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__sh__) + +#if defined(ALL_SYSCALLTBL) || defined(__sparc64__) || defined(__sparc__) +EOF +build_outer_table EM_SPARC "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__sparc64__) || defined(__sparc__) + +#if defined(ALL_SYSCALLTBL) || defined(__i386__) || defined(__x86_64__) +EOF +build_outer_table EM_386 "$outfile" +build_outer_table EM_X86_64 "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__i386__) || defined(__x86_64__) + +#if defined(ALL_SYSCALLTBL) || defined(__xtensa__) +EOF +build_outer_table EM_XTENSA "$outfile" +cat >> "$outfile" <<EOF +#endif // defined(ALL_SYSCALLTBL) || defined(__xtensa__) +EOF +build_outer_table EM_NONE "$outfile" +cat >> "$outfile" <<EOF +}; +EOF diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 49ba82bf3391..35c10509b797 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1226,7 +1226,7 @@ int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...) return ret; } -#define __HPP_COLOR_PERCENT_FN(_type, _field) \ +#define __HPP_COLOR_PERCENT_FN(_type, _field, _fmttype) \ static u64 __hpp_get_##_field(struct hist_entry *he) \ { \ return he->stat._field; \ @@ -1238,10 +1238,10 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt, \ struct hist_entry *he) \ { \ return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%", \ - __hpp__slsmg_color_printf, true); \ + __hpp__slsmg_color_printf, _fmttype); \ } -#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ +#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field, _fmttype) \ static u64 __hpp_get_acc_##_field(struct hist_entry *he) \ { \ return he->stat_acc->_field; \ @@ -1262,15 +1262,18 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt, \ return ret; \ } \ return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field, \ - " %*.2f%%", __hpp__slsmg_color_printf, true); \ + " %*.2f%%", __hpp__slsmg_color_printf, \ + _fmttype); \ } -__HPP_COLOR_PERCENT_FN(overhead, period) -__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys) -__HPP_COLOR_PERCENT_FN(overhead_us, period_us) -__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys) -__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us) -__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period) +__HPP_COLOR_PERCENT_FN(overhead, period, PERF_HPP_FMT_TYPE__PERCENT) +__HPP_COLOR_PERCENT_FN(latency, latency, PERF_HPP_FMT_TYPE__LATENCY) +__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, PERF_HPP_FMT_TYPE__PERCENT) +__HPP_COLOR_PERCENT_FN(overhead_us, period_us, PERF_HPP_FMT_TYPE__PERCENT) +__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, PERF_HPP_FMT_TYPE__PERCENT) +__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, PERF_HPP_FMT_TYPE__PERCENT) +__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period, PERF_HPP_FMT_TYPE__PERCENT) +__HPP_COLOR_ACC_PERCENT_FN(latency_acc, latency, PERF_HPP_FMT_TYPE__LATENCY) #undef __HPP_COLOR_PERCENT_FN #undef __HPP_COLOR_ACC_PERCENT_FN @@ -1279,6 +1282,8 @@ void hist_browser__init_hpp(void) { perf_hpp__format[PERF_HPP__OVERHEAD].color = hist_browser__hpp_color_overhead; + perf_hpp__format[PERF_HPP__LATENCY].color = + hist_browser__hpp_color_latency; perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = hist_browser__hpp_color_overhead_sys; perf_hpp__format[PERF_HPP__OVERHEAD_US].color = @@ -1289,6 +1294,8 @@ void hist_browser__init_hpp(void) hist_browser__hpp_color_overhead_guest_us; perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color = hist_browser__hpp_color_overhead_acc; + perf_hpp__format[PERF_HPP__LATENCY_ACC].color = + hist_browser__hpp_color_latency_acc; res_sample_init(); } diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 34fda1d5eccb..ae3b7fe1dadc 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -27,9 +27,10 @@ static int __hpp__fmt_print(struct perf_hpp *hpp, struct hists *hists, u64 val, int nr_samples, const char *fmt, int len, hpp_snprint_fn print_fn, enum perf_hpp_fmt_type fmtype) { - if (fmtype == PERF_HPP_FMT_TYPE__PERCENT) { + if (fmtype == PERF_HPP_FMT_TYPE__PERCENT || fmtype == PERF_HPP_FMT_TYPE__LATENCY) { double percent = 0.0; - u64 total = hists__total_period(hists); + u64 total = fmtype == PERF_HPP_FMT_TYPE__PERCENT ? hists__total_period(hists) : + hists__total_latency(hists); if (total) percent = 100.0 * val / total; @@ -128,7 +129,7 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, print_fn, fmtype); } - if (fmtype == PERF_HPP_FMT_TYPE__PERCENT) + if (fmtype == PERF_HPP_FMT_TYPE__PERCENT || fmtype == PERF_HPP_FMT_TYPE__LATENCY) len -= 2; /* 2 for a space and a % sign */ else len -= 1; @@ -356,7 +357,7 @@ static int hpp_entry_scnprintf(struct perf_hpp *hpp, const char *fmt, ...) return (ret >= ssize) ? (ssize - 1) : ret; } -#define __HPP_COLOR_PERCENT_FN(_type, _field) \ +#define __HPP_COLOR_PERCENT_FN(_type, _field, _fmttype) \ static u64 he_get_##_field(struct hist_entry *he) \ { \ return he->stat._field; \ @@ -366,15 +367,15 @@ static int hpp__color_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \ - hpp_color_scnprintf, PERF_HPP_FMT_TYPE__PERCENT); \ + hpp_color_scnprintf, _fmttype); \ } -#define __HPP_ENTRY_PERCENT_FN(_type, _field) \ +#define __HPP_ENTRY_PERCENT_FN(_type, _field, _fmttype) \ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \ - hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__PERCENT); \ + hpp_entry_scnprintf, _fmttype); \ } #define __HPP_SORT_FN(_type, _field) \ @@ -384,7 +385,7 @@ static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ return __hpp__sort(a, b, he_get_##_field); \ } -#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ +#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field, _fmttype) \ static u64 he_get_acc_##_field(struct hist_entry *he) \ { \ return he->stat_acc->_field; \ @@ -394,15 +395,15 @@ static int hpp__color_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \ - hpp_color_scnprintf, PERF_HPP_FMT_TYPE__PERCENT); \ + hpp_color_scnprintf, _fmttype); \ } -#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \ +#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field, _fmttype) \ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \ struct perf_hpp *hpp, struct hist_entry *he) \ { \ return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \ - hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__PERCENT); \ + hpp_entry_scnprintf, _fmttype); \ } #define __HPP_SORT_ACC_FN(_type, _field) \ @@ -453,14 +454,14 @@ static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ } -#define HPP_PERCENT_FNS(_type, _field) \ -__HPP_COLOR_PERCENT_FN(_type, _field) \ -__HPP_ENTRY_PERCENT_FN(_type, _field) \ +#define HPP_PERCENT_FNS(_type, _field, _fmttype) \ +__HPP_COLOR_PERCENT_FN(_type, _field, _fmttype) \ +__HPP_ENTRY_PERCENT_FN(_type, _field, _fmttype) \ __HPP_SORT_FN(_type, _field) -#define HPP_PERCENT_ACC_FNS(_type, _field) \ -__HPP_COLOR_ACC_PERCENT_FN(_type, _field) \ -__HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \ +#define HPP_PERCENT_ACC_FNS(_type, _field, _fmttype) \ +__HPP_COLOR_ACC_PERCENT_FN(_type, _field, _fmttype) \ +__HPP_ENTRY_ACC_PERCENT_FN(_type, _field, _fmttype) \ __HPP_SORT_ACC_FN(_type, _field) #define HPP_RAW_FNS(_type, _field) \ @@ -471,12 +472,14 @@ __HPP_SORT_RAW_FN(_type, _field) __HPP_ENTRY_AVERAGE_FN(_type, _field) \ __HPP_SORT_AVERAGE_FN(_type, _field) -HPP_PERCENT_FNS(overhead, period) -HPP_PERCENT_FNS(overhead_sys, period_sys) -HPP_PERCENT_FNS(overhead_us, period_us) -HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys) -HPP_PERCENT_FNS(overhead_guest_us, period_guest_us) -HPP_PERCENT_ACC_FNS(overhead_acc, period) +HPP_PERCENT_FNS(overhead, period, PERF_HPP_FMT_TYPE__PERCENT) +HPP_PERCENT_FNS(latency, latency, PERF_HPP_FMT_TYPE__LATENCY) +HPP_PERCENT_FNS(overhead_sys, period_sys, PERF_HPP_FMT_TYPE__PERCENT) +HPP_PERCENT_FNS(overhead_us, period_us, PERF_HPP_FMT_TYPE__PERCENT) +HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys, PERF_HPP_FMT_TYPE__PERCENT) +HPP_PERCENT_FNS(overhead_guest_us, period_guest_us, PERF_HPP_FMT_TYPE__PERCENT) +HPP_PERCENT_ACC_FNS(overhead_acc, period, PERF_HPP_FMT_TYPE__PERCENT) +HPP_PERCENT_ACC_FNS(latency_acc, latency, PERF_HPP_FMT_TYPE__LATENCY) HPP_RAW_FNS(samples, nr_events) HPP_RAW_FNS(period, period) @@ -548,11 +551,13 @@ static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) struct perf_hpp_fmt perf_hpp__format[] = { HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD), + HPP__COLOR_PRINT_FNS("Latency", latency, LATENCY), HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS), HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US), HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS), HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US), HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC), + HPP__COLOR_ACC_PRINT_FNS("Latency", latency_acc, LATENCY_ACC), HPP__PRINT_FNS("Samples", samples, SAMPLES), HPP__PRINT_FNS("Period", period, PERIOD), HPP__PRINT_FNS("Weight1", weight1, WEIGHT1), @@ -601,6 +606,11 @@ static void fmt_free(struct perf_hpp_fmt *fmt) fmt->free(fmt); } +static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + return a->equal && a->equal(a, b); +} + void perf_hpp__init(void) { int i; @@ -621,28 +631,48 @@ void perf_hpp__init(void) if (is_strict_order(field_order)) return; + /* + * Overhead and latency columns are added in setup_overhead(), + * so they are added implicitly here only if they were added + * by setup_overhead() before (have was_taken flag set). + * This is required because setup_overhead() has more complex + * logic, in particular it does not add "overhead" if user + * specified "latency" in sort order, and vise versa. + */ if (symbol_conf.cumulate_callchain) { - hpp_dimension__add_output(PERF_HPP__OVERHEAD_ACC); + /* + * Addition of fields is idempotent, so we add latency + * column twice to get desired order with simpler logic. + */ + if (symbol_conf.prefer_latency) + hpp_dimension__add_output(PERF_HPP__LATENCY_ACC, true); + hpp_dimension__add_output(PERF_HPP__OVERHEAD_ACC, true); + if (symbol_conf.enable_latency) + hpp_dimension__add_output(PERF_HPP__LATENCY_ACC, true); perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self"; } - hpp_dimension__add_output(PERF_HPP__OVERHEAD); + if (symbol_conf.prefer_latency) + hpp_dimension__add_output(PERF_HPP__LATENCY, true); + hpp_dimension__add_output(PERF_HPP__OVERHEAD, true); + if (symbol_conf.enable_latency) + hpp_dimension__add_output(PERF_HPP__LATENCY, true); if (symbol_conf.show_cpu_utilization) { - hpp_dimension__add_output(PERF_HPP__OVERHEAD_SYS); - hpp_dimension__add_output(PERF_HPP__OVERHEAD_US); + hpp_dimension__add_output(PERF_HPP__OVERHEAD_SYS, false); + hpp_dimension__add_output(PERF_HPP__OVERHEAD_US, false); if (perf_guest) { - hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_SYS); - hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_US); + hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_SYS, false); + hpp_dimension__add_output(PERF_HPP__OVERHEAD_GUEST_US, false); } } if (symbol_conf.show_nr_samples) - hpp_dimension__add_output(PERF_HPP__SAMPLES); + hpp_dimension__add_output(PERF_HPP__SAMPLES, false); if (symbol_conf.show_total_period) - hpp_dimension__add_output(PERF_HPP__PERIOD); + hpp_dimension__add_output(PERF_HPP__PERIOD, false); } void perf_hpp_list__column_register(struct perf_hpp_list *list, @@ -671,28 +701,42 @@ static void perf_hpp__column_unregister(struct perf_hpp_fmt *format) void perf_hpp__cancel_cumulate(void) { - struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp; + struct perf_hpp_fmt *fmt, *acc, *ovh, *acc_lat, *tmp; if (is_strict_order(field_order)) return; ovh = &perf_hpp__format[PERF_HPP__OVERHEAD]; acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC]; + acc_lat = &perf_hpp__format[PERF_HPP__LATENCY_ACC]; perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) { - if (acc->equal(acc, fmt)) { + if (fmt_equal(acc, fmt) || fmt_equal(acc_lat, fmt)) { perf_hpp__column_unregister(fmt); continue; } - if (ovh->equal(ovh, fmt)) + if (fmt_equal(ovh, fmt)) fmt->name = "Overhead"; } } -static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +void perf_hpp__cancel_latency(void) { - return a->equal && a->equal(a, b); + struct perf_hpp_fmt *fmt, *lat, *acc, *tmp; + + if (is_strict_order(field_order)) + return; + if (sort_order && strstr(sort_order, "latency")) + return; + + lat = &perf_hpp__format[PERF_HPP__LATENCY]; + acc = &perf_hpp__format[PERF_HPP__LATENCY_ACC]; + + perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) { + if (fmt_equal(lat, fmt) || fmt_equal(acc, fmt)) + perf_hpp__column_unregister(fmt); + } } void perf_hpp__setup_output_field(struct perf_hpp_list *list) @@ -819,6 +863,7 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists) switch (fmt->idx) { case PERF_HPP__OVERHEAD: + case PERF_HPP__LATENCY: case PERF_HPP__OVERHEAD_SYS: case PERF_HPP__OVERHEAD_US: case PERF_HPP__OVERHEAD_ACC: diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 74b2c619c56c..7ac4b98e28bc 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <limits.h> #include <stdio.h> #include <stdlib.h> #include <linux/string.h> @@ -24,6 +25,9 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) int i; int ret = fprintf(fp, " "); + if (left_margin > USHRT_MAX) + left_margin = USHRT_MAX; + for (i = 0; i < left_margin; i++) ret += fprintf(fp, " "); diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 5ec97e8d6b6d..946bce6628f3 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -67,6 +67,7 @@ perf-util-y += maps.o perf-util-y += pstack.o perf-util-y += session.o perf-util-y += tool.o +perf-util-y += sample.o perf-util-y += sample-raw.o perf-util-y += s390-sample-raw.o perf-util-y += amd-sample-raw.o @@ -405,14 +406,39 @@ $(OUTPUT)util/list_sort.o: ../lib/list_sort.c FORCE ifdef SHELLCHECK SHELL_TESTS := generate-cmdlist.sh - TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) + SHELL_TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) else SHELL_TESTS := - TEST_LOGS := + SHELL_TEST_LOGS := endif $(OUTPUT)%.shellcheck_log: % $(call rule_mkdir) $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) -perf-util-y += $(TEST_LOGS) +perf-util-y += $(SHELL_TEST_LOGS) + +PY_TESTS := setup.py +ifdef MYPY + MYPY_TEST_LOGS := $(PY_TESTS:%=%.mypy_log) +else + MYPY_TEST_LOGS := +endif + +$(OUTPUT)%.mypy_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false) + +perf-util-y += $(MYPY_TEST_LOGS) + +ifdef PYLINT + PYLINT_TEST_LOGS := $(PY_TESTS:%=%.pylint_log) +else + PYLINT_TEST_LOGS := +endif + +$(OUTPUT)%.pylint_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false) + +perf-util-y += $(PYLINT_TEST_LOGS) diff --git a/tools/perf/util/addr_location.c b/tools/perf/util/addr_location.c index 51825ef8c0ab..007a2f5df9a6 100644 --- a/tools/perf/util/addr_location.c +++ b/tools/perf/util/addr_location.c @@ -17,6 +17,7 @@ void addr_location__init(struct addr_location *al) al->cpumode = 0; al->cpu = 0; al->socket = 0; + al->parallelism = 1; } /* diff --git a/tools/perf/util/addr_location.h b/tools/perf/util/addr_location.h index d8ac0428dff2..64b551025216 100644 --- a/tools/perf/util/addr_location.h +++ b/tools/perf/util/addr_location.h @@ -17,10 +17,14 @@ struct addr_location { const char *srcline; u64 addr; char level; - u8 filtered; u8 cpumode; + u16 filtered; s32 cpu; s32 socket; + /* Same as machine.parallelism but within [1, nr_cpus]. */ + int parallelism; + /* See he_stat.latency. */ + u64 latency; }; void addr_location__init(struct addr_location *al); diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c index 976abedca09e..1ef2edbc71d9 100644 --- a/tools/perf/util/annotate-data.c +++ b/tools/perf/util/annotate-data.c @@ -314,6 +314,40 @@ static void delete_members(struct annotated_member *member) } } +static int fill_member_name(char *buf, size_t sz, struct annotated_member *m, + int offset, bool first) +{ + struct annotated_member *child; + + if (list_empty(&m->children)) + return 0; + + list_for_each_entry(child, &m->children, node) { + int len; + + if (offset < child->offset || offset >= child->offset + child->size) + continue; + + /* It can have anonymous struct/union members */ + if (child->var_name) { + len = scnprintf(buf, sz, "%s%s", + first ? "" : ".", child->var_name); + first = false; + } else { + len = 0; + } + + return fill_member_name(buf + len, sz - len, child, offset, first) + len; + } + return 0; +} + +int annotated_data_type__get_member_name(struct annotated_data_type *adt, + char *buf, size_t sz, int member_offset) +{ + return fill_member_name(buf, sz, &adt->self, member_offset, /*first=*/true); +} + static struct annotated_data_type *dso__findnew_data_type(struct dso *dso, Dwarf_Die *type_die) { @@ -830,7 +864,7 @@ static void update_var_state(struct type_state *state, struct data_loc_info *dlo if (!dwarf_offdie(dloc->di->dbg, var->die_off, &mem_die)) continue; - if (var->reg == DWARF_REG_FB || var->reg == fbreg) { + if (var->reg == DWARF_REG_FB || var->reg == fbreg || var->reg == state->stack_reg) { int offset = var->offset; struct type_state_stack *stack; @@ -845,8 +879,13 @@ static void update_var_state(struct type_state *state, struct data_loc_info *dlo findnew_stack_state(state, offset, TSR_KIND_TYPE, &mem_die); - pr_debug_dtp("var [%"PRIx64"] -%#x(stack)", - insn_offset, -offset); + if (var->reg == state->stack_reg) { + pr_debug_dtp("var [%"PRIx64"] %#x(reg%d)", + insn_offset, offset, state->stack_reg); + } else { + pr_debug_dtp("var [%"PRIx64"] -%#x(stack)", + insn_offset, -offset); + } pr_debug_type_name(&mem_die, TSR_KIND_TYPE); } else if (has_reg_type(state, var->reg) && var->offset == 0) { struct type_state_reg *reg; @@ -1127,10 +1166,10 @@ again: } check_non_register: - if (reg == dloc->fbreg) { + if (reg == dloc->fbreg || reg == state->stack_reg) { struct type_state_stack *stack; - pr_debug_dtp("fbreg"); + pr_debug_dtp("%s", reg == dloc->fbreg ? "fbreg" : "stack"); stack = find_stack_state(state, dloc->type_offset); if (stack == NULL) { diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h index 98c80b2268dd..541fee1a5f0a 100644 --- a/tools/perf/util/annotate-data.h +++ b/tools/perf/util/annotate-data.h @@ -227,8 +227,13 @@ void annotated_data_type__tree_delete(struct rb_root *root); /* Release all global variable information in the tree */ void global_var_type__tree_delete(struct rb_root *root); +/* Print data type annotation (including members) on stdout */ int hist_entry__annotate_data_tty(struct hist_entry *he, struct evsel *evsel); +/* Get name of member field at the given offset in the data type */ +int annotated_data_type__get_member_name(struct annotated_data_type *adt, + char *buf, size_t sz, int member_offset); + bool has_reg_type(struct type_state *state, int reg); struct type_state_stack *findnew_stack_state(struct type_state *state, int offset, u8 kind, @@ -276,6 +281,14 @@ static inline int hist_entry__annotate_data_tty(struct hist_entry *he __maybe_un return -1; } +static inline int annotated_data_type__get_member_name(struct annotated_data_type *adt __maybe_unused, + char *buf __maybe_unused, + size_t sz __maybe_unused, + int member_offset __maybe_unused) +{ + return -1; +} + #endif /* HAVE_LIBDW_SUPPORT */ #ifdef HAVE_SLANG_SUPPORT diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 31bb326b07a6..1e59b9e5339d 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -87,6 +87,8 @@ struct annotated_data_type canary_type = { }, }; +#define NO_TYPE ((struct annotated_data_type *)-1UL) + /* symbol histogram: key = offset << 16 | evsel->core.idx */ static size_t sym_hist_hash(long key, void *ctx __maybe_unused) { @@ -758,15 +760,31 @@ static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_wi return 0; } +static struct annotated_data_type * +__hist_entry__get_data_type(struct hist_entry *he, struct arch *arch, + struct debuginfo *dbg, struct disasm_line *dl, + int *type_offset); + +struct annotation_print_data { + struct hist_entry *he; + struct evsel *evsel; + struct arch *arch; + struct debuginfo *dbg; + u64 start; + int addr_fmt_width; +}; + static int -annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start, - struct evsel *evsel, u64 len, int min_pcnt, int printed, - int max_lines, struct annotation_line *queue, int addr_fmt_width, - int percent_type) +annotation_line__print(struct annotation_line *al, struct annotation_print_data *apd, + struct annotation_options *opts, int printed, + struct annotation_line *queue) { + struct symbol *sym = apd->he->ms.sym; struct disasm_line *dl = container_of(al, struct disasm_line, al); struct annotation *notes = symbol__annotation(sym); static const char *prev_line; + int max_lines = opts->max_lines; + int percent_type = opts->percent_type; if (al->offset != -1) { double max_percent = 0.0; @@ -786,19 +804,23 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start if (al->data_nr > nr_percent) nr_percent = al->data_nr; - if (max_percent < min_pcnt) + if (max_percent < opts->min_pcnt) return -1; if (max_lines && printed >= max_lines) return 1; if (queue != NULL) { + struct annotation_options queue_opts = { + .max_lines = 1, + .percent_type = percent_type, + }; + list_for_each_entry_from(queue, ¬es->src->source, node) { if (queue == al) break; - annotation_line__print(queue, sym, start, evsel, len, - 0, 0, 1, NULL, addr_fmt_width, - percent_type); + annotation_line__print(queue, apd, &queue_opts, + /*printed=*/0, /*queue=*/NULL); } } @@ -823,7 +845,31 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start printf(" : "); - disasm_line__print(dl, start, addr_fmt_width); + disasm_line__print(dl, apd->start, apd->addr_fmt_width); + + if (opts->code_with_type && apd->dbg) { + struct annotated_data_type *data_type; + int offset = 0; + + data_type = __hist_entry__get_data_type(apd->he, apd->arch, + apd->dbg, dl, &offset); + if (data_type && data_type != NO_TYPE) { + char buf[4096]; + + printf("\t\t# data-type: %s", + data_type->self.type_name); + + if (data_type != &stackop_type && + data_type != &canary_type) + printf(" +%#x", offset); + + if (annotated_data_type__get_member_name(data_type, + buf, + sizeof(buf), + offset)) + printf(" (%s)", buf); + } + } /* * Also color the filename and line if needed, with @@ -849,7 +895,8 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start if (!*al->line) printf(" %*s:\n", width, " "); else - printf(" %*s: %-*d %s\n", width, " ", addr_fmt_width, al->line_nr, al->line); + printf(" %*s: %-*d %s\n", width, " ", apd->addr_fmt_width, + al->line_nr, al->line); } return 0; @@ -1167,8 +1214,9 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) return 0; } -int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) +int hist_entry__annotate_printf(struct hist_entry *he, struct evsel *evsel) { + struct map_symbol *ms = &he->ms; struct map *map = ms->map; struct symbol *sym = ms->sym; struct dso *dso = map__dso(map); @@ -1179,11 +1227,14 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) struct sym_hist *h = annotation__histogram(notes, evsel); struct annotation_line *pos, *queue = NULL; struct annotation_options *opts = &annotate_opts; - u64 start = map__rip_2objdump(map, sym->start); - int printed = 2, queue_len = 0, addr_fmt_width; + struct annotation_print_data apd = { + .he = he, + .evsel = evsel, + .start = map__rip_2objdump(map, sym->start), + }; + int printed = 2, queue_len = 0; int more = 0; bool context = opts->context; - u64 len; int width = annotation__pcnt_width(notes); int graph_dotted_len; char buf[512]; @@ -1197,8 +1248,6 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) else d_filename = basename(filename); - len = symbol__size(sym); - if (evsel__is_group_event(evsel)) { evsel__group_desc(evsel, buf, sizeof(buf)); evsel_name = buf; @@ -1217,7 +1266,10 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) if (verbose > 0) symbol__annotate_hits(sym, evsel); - addr_fmt_width = annotated_source__addr_fmt_width(¬es->src->source, start); + apd.addr_fmt_width = annotated_source__addr_fmt_width(¬es->src->source, + apd.start); + evsel__get_arch(evsel, &apd.arch); + apd.dbg = debuginfo__new(filename); list_for_each_entry(pos, ¬es->src->source, node) { int err; @@ -1227,9 +1279,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) queue_len = 0; } - err = annotation_line__print(pos, sym, start, evsel, len, - opts->min_pcnt, printed, opts->max_lines, - queue, addr_fmt_width, opts->percent_type); + err = annotation_line__print(pos, &apd, opts, printed, queue); switch (err) { case 0: @@ -1260,6 +1310,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) } } + debuginfo__delete(apd.dbg); free(filename); return more; @@ -1597,8 +1648,9 @@ static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root) annotation__calc_lines(notes, ms, root); } -int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel) +int hist_entry__tty_annotate2(struct hist_entry *he, struct evsel *evsel) { + struct map_symbol *ms = &he->ms; struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; @@ -1632,8 +1684,9 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel) return 0; } -int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel) +int hist_entry__tty_annotate(struct hist_entry *he, struct evsel *evsel) { + struct map_symbol *ms = &he->ms; struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; @@ -1657,7 +1710,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel) print_summary(&source_line, dso__long_name(dso)); } - symbol__annotate_printf(ms, evsel); + hist_entry__annotate_printf(he, evsel); annotated_source__purge(symbol__annotation(sym)->src); @@ -2643,6 +2696,92 @@ void debuginfo_cache__delete(void) di_cache.dbg = NULL; } +static struct annotated_data_type * +__hist_entry__get_data_type(struct hist_entry *he, struct arch *arch, + struct debuginfo *dbg, struct disasm_line *dl, + int *type_offset) +{ + struct map_symbol *ms = &he->ms; + struct annotated_insn_loc loc; + struct annotated_op_loc *op_loc; + struct annotated_data_type *mem_type; + struct annotated_item_stat *istat; + int i; + + istat = annotate_data_stat(&ann_insn_stat, dl->ins.name); + if (istat == NULL) { + ann_data_stat.no_insn++; + return NO_TYPE; + } + + if (annotate_get_insn_location(arch, dl, &loc) < 0) { + ann_data_stat.no_insn_ops++; + istat->bad++; + return NO_TYPE; + } + + if (is_stack_operation(arch, dl)) { + istat->good++; + *type_offset = 0; + return &stackop_type; + } + + for_each_insn_op_loc(&loc, i, op_loc) { + struct data_loc_info dloc = { + .arch = arch, + .thread = he->thread, + .ms = ms, + .ip = ms->sym->start + dl->al.offset, + .cpumode = he->cpumode, + .op = op_loc, + .di = dbg, + }; + + if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE) + continue; + + /* PC-relative addressing */ + if (op_loc->reg1 == DWARF_REG_PC) { + dloc.var_addr = annotate_calc_pcrel(ms, dloc.ip, + op_loc->offset, dl); + } + + /* This CPU access in kernel - pretend PC-relative addressing */ + if (dso__kernel(map__dso(ms->map)) && arch__is(arch, "x86") && + op_loc->segment == INSN_SEG_X86_GS && op_loc->imm) { + dloc.var_addr = op_loc->offset; + op_loc->reg1 = DWARF_REG_PC; + } + + mem_type = find_data_type(&dloc); + + if (mem_type == NULL && is_stack_canary(arch, op_loc)) { + istat->good++; + *type_offset = 0; + return &canary_type; + } + + if (mem_type) + istat->good++; + else + istat->bad++; + + if (symbol_conf.annotate_data_sample) { + struct evsel *evsel = hists_to_evsel(he->hists); + + annotated_data_type__update_samples(mem_type, evsel, + dloc.type_offset, + he->stat.nr_events, + he->stat.period); + } + *type_offset = dloc.type_offset; + return mem_type ?: NO_TYPE; + } + + /* retry with a fused instruction */ + return NULL; +} + /** * hist_entry__get_data_type - find data type for given hist entry * @he: hist entry @@ -2658,12 +2797,9 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he) struct evsel *evsel = hists_to_evsel(he->hists); struct arch *arch; struct disasm_line *dl; - struct annotated_insn_loc loc; - struct annotated_op_loc *op_loc; struct annotated_data_type *mem_type; struct annotated_item_stat *istat; u64 ip = he->ip; - int i; ann_data_stat.total++; @@ -2715,77 +2851,10 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he) } retry: - istat = annotate_data_stat(&ann_insn_stat, dl->ins.name); - if (istat == NULL) { - ann_data_stat.no_insn++; - return NULL; - } - - if (annotate_get_insn_location(arch, dl, &loc) < 0) { - ann_data_stat.no_insn_ops++; - istat->bad++; - return NULL; - } - - if (is_stack_operation(arch, dl)) { - istat->good++; - he->mem_type_off = 0; - return &stackop_type; - } - - for_each_insn_op_loc(&loc, i, op_loc) { - struct data_loc_info dloc = { - .arch = arch, - .thread = he->thread, - .ms = ms, - /* Recalculate IP for LOCK prefix or insn fusion */ - .ip = ms->sym->start + dl->al.offset, - .cpumode = he->cpumode, - .op = op_loc, - .di = di_cache.dbg, - }; - - if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE) - continue; - - /* Recalculate IP because of LOCK prefix or insn fusion */ - ip = ms->sym->start + dl->al.offset; - - /* PC-relative addressing */ - if (op_loc->reg1 == DWARF_REG_PC) { - dloc.var_addr = annotate_calc_pcrel(ms, dloc.ip, - op_loc->offset, dl); - } - - /* This CPU access in kernel - pretend PC-relative addressing */ - if (dso__kernel(map__dso(ms->map)) && arch__is(arch, "x86") && - op_loc->segment == INSN_SEG_X86_GS && op_loc->imm) { - dloc.var_addr = op_loc->offset; - op_loc->reg1 = DWARF_REG_PC; - } - - mem_type = find_data_type(&dloc); - - if (mem_type == NULL && is_stack_canary(arch, op_loc)) { - istat->good++; - he->mem_type_off = 0; - return &canary_type; - } - - if (mem_type) - istat->good++; - else - istat->bad++; - - if (symbol_conf.annotate_data_sample) { - annotated_data_type__update_samples(mem_type, evsel, - dloc.type_offset, - he->stat.nr_events, - he->stat.period); - } - he->mem_type_off = dloc.type_offset; - return mem_type; - } + mem_type = __hist_entry__get_data_type(he, arch, di_cache.dbg, dl, + &he->mem_type_off); + if (mem_type) + return mem_type == NO_TYPE ? NULL : mem_type; /* * Some instructions can be fused and the actual memory access came @@ -2805,7 +2874,9 @@ retry: } ann_data_stat.no_mem_ops++; - istat->bad++; + istat = annotate_data_stat(&ann_insn_stat, dl->ins.name); + if (istat) + istat->bad++; return NULL; } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 98db1b88daf4..0e6e3f60a897 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -55,9 +55,11 @@ struct annotation_options { show_asm_raw, show_br_cntr, annotate_src, + code_with_type, full_addr; u8 offset_level; u8 disassemblers[MAX_DISASSEMBLERS]; + u8 disassembler_used; int min_pcnt; int max_lines; int context; @@ -455,7 +457,6 @@ enum symbol_disassemble_errno { int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen); -int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel); void symbol__annotate_zero_histogram(struct symbol *sym, struct evsel *evsel); void symbol__annotate_decay_histogram(struct symbol *sym, struct evsel *evsel); void annotated_source__purge(struct annotated_source *as); @@ -464,9 +465,9 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel); bool ui__has_annotation(void); -int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel); - -int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel); +int hist_entry__annotate_printf(struct hist_entry *he, struct evsel *evsel); +int hist_entry__tty_annotate(struct hist_entry *he, struct evsel *evsel); +int hist_entry__tty_annotate2(struct hist_entry *he, struct evsel *evsel); #ifdef HAVE_SLANG_SUPPORT int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index ba807071d3c1..688fe6d75244 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -28,7 +28,8 @@ static u64 arm_spe_calc_ip(int index, u64 payload) /* Instruction virtual address or Branch target address */ if (index == SPE_ADDR_PKT_HDR_INDEX_INS || - index == SPE_ADDR_PKT_HDR_INDEX_BRANCH) { + index == SPE_ADDR_PKT_HDR_INDEX_BRANCH || + index == SPE_ADDR_PKT_HDR_INDEX_PREV_BRANCH) { ns = SPE_ADDR_PKT_GET_NS(payload); el = SPE_ADDR_PKT_GET_EL(payload); @@ -181,6 +182,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) decoder->record.virt_addr = ip; else if (idx == SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS) decoder->record.phys_addr = ip; + else if (idx == SPE_ADDR_PKT_HDR_INDEX_PREV_BRANCH) + decoder->record.prev_br_tgt = ip; break; case ARM_SPE_COUNTER: if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT) @@ -207,6 +210,18 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) break; case SPE_OP_PKT_HDR_CLASS_BR_ERET: decoder->record.op |= ARM_SPE_OP_BRANCH_ERET; + if (payload & SPE_OP_PKT_COND) + decoder->record.op |= ARM_SPE_OP_BR_COND; + if (payload & SPE_OP_PKT_INDIRECT_BRANCH) + decoder->record.op |= ARM_SPE_OP_BR_INDIRECT; + if (payload & SPE_OP_PKT_GCS) + decoder->record.op |= ARM_SPE_OP_BR_GCS; + if (SPE_OP_PKT_CR_BL(payload)) + decoder->record.op |= ARM_SPE_OP_BR_CR_BL; + if (SPE_OP_PKT_CR_RET(payload)) + decoder->record.op |= ARM_SPE_OP_BR_CR_RET; + if (SPE_OP_PKT_CR_NON_BL_RET(payload)) + decoder->record.op |= ARM_SPE_OP_BR_CR_NON_BL_RET; break; default: pr_err("Get packet error!\n"); @@ -238,6 +253,12 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) if (payload & BIT(EV_MISPRED)) decoder->record.type |= ARM_SPE_BRANCH_MISS; + if (payload & BIT(EV_NOT_TAKEN)) + decoder->record.type |= ARM_SPE_BRANCH_NOT_TAKEN; + + if (payload & BIT(EV_TRANSACTIONAL)) + decoder->record.type |= ARM_SPE_IN_TXN; + if (payload & BIT(EV_PARTIAL_PREDICATE)) decoder->record.type |= ARM_SPE_SVE_PARTIAL_PRED; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 4bcd627e859f..5d232188643b 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -24,6 +24,8 @@ enum arm_spe_sample_type { ARM_SPE_REMOTE_ACCESS = 1 << 7, ARM_SPE_SVE_PARTIAL_PRED = 1 << 8, ARM_SPE_SVE_EMPTY_PRED = 1 << 9, + ARM_SPE_BRANCH_NOT_TAKEN = 1 << 10, + ARM_SPE_IN_TXN = 1 << 11, }; enum arm_spe_op_type { @@ -52,8 +54,12 @@ enum arm_spe_op_type { ARM_SPE_OP_SVE_SG = 1 << 27, /* Second level operation type for BRANCH_ERET */ - ARM_SPE_OP_BR_COND = 1 << 16, - ARM_SPE_OP_BR_INDIRECT = 1 << 17, + ARM_SPE_OP_BR_COND = 1 << 16, + ARM_SPE_OP_BR_INDIRECT = 1 << 17, + ARM_SPE_OP_BR_GCS = 1 << 18, + ARM_SPE_OP_BR_CR_BL = 1 << 19, + ARM_SPE_OP_BR_CR_RET = 1 << 20, + ARM_SPE_OP_BR_CR_NON_BL_RET = 1 << 21, }; enum arm_spe_common_data_source { @@ -83,6 +89,7 @@ struct arm_spe_record { u32 latency; u64 from_ip; u64 to_ip; + u64 prev_br_tgt; u64 timestamp; u64 virt_addr; u64 phys_addr; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index 4cef10a83962..13cadb2f1cea 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -308,6 +308,8 @@ static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet, arm_spe_pkt_out_string(&err, &buf, &buf_len, " REMOTE-ACCESS"); if (payload & BIT(EV_ALIGNMENT)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " ALIGNMENT"); + if (payload & BIT(EV_TRANSACTIONAL)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " TXN"); if (payload & BIT(EV_PARTIAL_PREDICATE)) arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-PARTIAL-PRED"); if (payload & BIT(EV_EMPTY_PREDICATE)) @@ -397,10 +399,16 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, if (payload & SPE_OP_PKT_COND) arm_spe_pkt_out_string(&err, &buf, &buf_len, " COND"); - - if (SPE_OP_PKT_IS_INDIRECT_BRANCH(payload)) + if (payload & SPE_OP_PKT_INDIRECT_BRANCH) arm_spe_pkt_out_string(&err, &buf, &buf_len, " IND"); - + if (payload & SPE_OP_PKT_GCS) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " GCS"); + if (SPE_OP_PKT_CR_BL(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " CR-BL"); + if (SPE_OP_PKT_CR_RET(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " CR-RET"); + if (SPE_OP_PKT_CR_NON_BL_RET(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " CR-NON-BL-RET"); break; default: /* Unknown index */ diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h index 464a912b221c..2cdf9f6da268 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h @@ -7,6 +7,7 @@ #ifndef INCLUDE__ARM_SPE_PKT_DECODER_H__ #define INCLUDE__ARM_SPE_PKT_DECODER_H__ +#include <linux/bitfield.h> #include <stddef.h> #include <stdint.h> @@ -104,6 +105,7 @@ enum arm_spe_events { EV_LLC_MISS = 9, EV_REMOTE_ACCESS = 10, EV_ALIGNMENT = 11, + EV_TRANSACTIONAL = 16, EV_PARTIAL_PREDICATE = 17, EV_EMPTY_PREDICATE = 18, }; @@ -116,8 +118,6 @@ enum arm_spe_events { #define SPE_OP_PKT_IS_OTHER_SVE_OP(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8) -#define SPE_OP_PKT_COND BIT(0) - #define SPE_OP_PKT_LDST_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1)) #define SPE_OP_PKT_LDST_SUBCLASS_GP_REG 0x0 #define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP 0x4 @@ -148,7 +148,13 @@ enum arm_spe_events { #define SPE_OP_PKT_SVE_PRED BIT(2) #define SPE_OP_PKT_SVE_FP BIT(1) -#define SPE_OP_PKT_IS_INDIRECT_BRANCH(v) (((v) & GENMASK_ULL(7, 1)) == 0x2) +#define SPE_OP_PKT_CR_MASK GENMASK_ULL(4, 3) +#define SPE_OP_PKT_CR_BL(v) (FIELD_GET(SPE_OP_PKT_CR_MASK, (v)) == 1) +#define SPE_OP_PKT_CR_RET(v) (FIELD_GET(SPE_OP_PKT_CR_MASK, (v)) == 2) +#define SPE_OP_PKT_CR_NON_BL_RET(v) (FIELD_GET(SPE_OP_PKT_CR_MASK, (v)) == 3) +#define SPE_OP_PKT_GCS BIT(2) +#define SPE_OP_PKT_INDIRECT_BRANCH BIT(1) +#define SPE_OP_PKT_COND BIT(0) const char *arm_spe_pkt_name(enum arm_spe_pkt_type); diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 12761c39788f..2a9775649cc2 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -37,6 +37,8 @@ #include "../../arch/arm64/include/asm/cputype.h" #define MAX_TIMESTAMP (~0ULL) +#define is_ldst_op(op) (!!((op) & ARM_SPE_OP_LDST)) + struct arm_spe { struct auxtrace auxtrace; struct auxtrace_queues queues; @@ -101,6 +103,7 @@ struct arm_spe_queue { struct thread *thread; u64 period_instructions; u32 flags; + struct branch_stack *last_branch; }; struct data_source_handle { @@ -231,6 +234,17 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe, params.get_trace = arm_spe_get_trace; params.data = speq; + if (spe->synth_opts.last_branch) { + size_t sz = sizeof(struct branch_stack); + + /* Allocate up to two entries for PBT + TGT */ + sz += sizeof(struct branch_entry) * + min(spe->synth_opts.last_branch_sz, 2U); + speq->last_branch = zalloc(sz); + if (!speq->last_branch) + goto out_free; + } + /* create new decoder */ speq->decoder = arm_spe_decoder_new(¶ms); if (!speq->decoder) @@ -240,6 +254,7 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe, out_free: zfree(&speq->event_buf); + zfree(&speq->last_branch); free(speq); return NULL; @@ -346,6 +361,88 @@ static void arm_spe_prep_sample(struct arm_spe *spe, event->sample.header.size = sizeof(struct perf_event_header); } +static void arm_spe__prep_branch_stack(struct arm_spe_queue *speq) +{ + struct arm_spe *spe = speq->spe; + struct arm_spe_record *record = &speq->decoder->record; + struct branch_stack *bstack = speq->last_branch; + struct branch_flags *bs_flags; + unsigned int last_branch_sz = spe->synth_opts.last_branch_sz; + bool have_tgt = !!(speq->flags & PERF_IP_FLAG_BRANCH); + bool have_pbt = last_branch_sz >= (have_tgt + 1U) && record->prev_br_tgt; + size_t sz = sizeof(struct branch_stack) + + sizeof(struct branch_entry) * min(last_branch_sz, 2U) /* PBT + TGT */; + int i = 0; + + /* Clean up branch stack */ + memset(bstack, 0x0, sz); + + if (!have_tgt && !have_pbt) + return; + + if (have_tgt) { + bstack->entries[i].from = record->from_ip; + bstack->entries[i].to = record->to_ip; + + bs_flags = &bstack->entries[i].flags; + bs_flags->value = 0; + + if (record->op & ARM_SPE_OP_BR_CR_BL) { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND_CALL; + else + bs_flags->type |= PERF_BR_CALL; + /* + * Indirect branch instruction without link (e.g. BR), + * take this case as function return. + */ + } else if (record->op & ARM_SPE_OP_BR_CR_RET || + record->op & ARM_SPE_OP_BR_INDIRECT) { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND_RET; + else + bs_flags->type |= PERF_BR_RET; + } else if (record->op & ARM_SPE_OP_BR_CR_NON_BL_RET) { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND; + else + bs_flags->type |= PERF_BR_UNCOND; + } else { + if (record->op & ARM_SPE_OP_BR_COND) + bs_flags->type |= PERF_BR_COND; + else + bs_flags->type |= PERF_BR_UNKNOWN; + } + + if (record->type & ARM_SPE_BRANCH_MISS) { + bs_flags->mispred = 1; + bs_flags->predicted = 0; + } else { + bs_flags->mispred = 0; + bs_flags->predicted = 1; + } + + if (record->type & ARM_SPE_BRANCH_NOT_TAKEN) + bs_flags->not_taken = 1; + + if (record->type & ARM_SPE_IN_TXN) + bs_flags->in_tx = 1; + + bs_flags->cycles = min(record->latency, 0xFFFFU); + i++; + } + + if (have_pbt) { + bs_flags = &bstack->entries[i].flags; + bs_flags->type |= PERF_BR_UNKNOWN; + bstack->entries[i].to = record->prev_br_tgt; + i++; + } + + bstack->nr = i; + bstack->hw_idx = -1ULL; +} + static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type) { event->header.size = perf_event__sample_event_size(sample, type, 0); @@ -379,8 +476,10 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; @@ -390,7 +489,9 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, sample.data_src = data_src; sample.weight = record->latency; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, @@ -399,8 +500,10 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; @@ -408,8 +511,11 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, sample.addr = record->to_ip; sample.weight = record->latency; sample.flags = speq->flags; + sample.branch_stack = speq->last_branch; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, @@ -418,7 +524,8 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; /* * Handles perf instruction sampling period. @@ -428,6 +535,7 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, return 0; speq->period_instructions = 0; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; @@ -438,8 +546,11 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, sample.period = spe->instructions_sample_period; sample.weight = record->latency; sample.flags = speq->flags; + sample.branch_stack = speq->last_branch; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static const struct midr_range common_ds_encoding_cpus[] = { @@ -470,6 +581,26 @@ static void arm_spe__sample_flags(struct arm_spe_queue *speq) if (record->type & ARM_SPE_BRANCH_MISS) speq->flags |= PERF_IP_FLAG_BRANCH_MISS; + + if (record->type & ARM_SPE_BRANCH_NOT_TAKEN) + speq->flags |= PERF_IP_FLAG_NOT_TAKEN; + + if (record->type & ARM_SPE_IN_TXN) + speq->flags |= PERF_IP_FLAG_IN_TX; + + if (record->op & ARM_SPE_OP_BR_COND) + speq->flags |= PERF_IP_FLAG_CONDITIONAL; + + if (record->op & ARM_SPE_OP_BR_CR_BL) + speq->flags |= PERF_IP_FLAG_CALL; + else if (record->op & ARM_SPE_OP_BR_CR_RET) + speq->flags |= PERF_IP_FLAG_RETURN; + /* + * Indirect branch instruction without link (e.g. BR), + * take it as a function return. + */ + else if (record->op & ARM_SPE_OP_BR_INDIRECT) + speq->flags |= PERF_IP_FLAG_RETURN; } } @@ -669,6 +800,10 @@ static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq, { union perf_mem_data_src data_src = { .mem_op = PERF_MEM_OP_NA }; + /* Only synthesize data source for LDST operations */ + if (!is_ldst_op(record->op)) + return 0; + if (record->op & ARM_SPE_OP_LD) data_src.mem_op = PERF_MEM_OP_LOAD; else if (record->op & ARM_SPE_OP_ST) @@ -749,6 +884,10 @@ static int arm_spe_sample(struct arm_spe_queue *speq) } } + if (spe->synth_opts.last_branch && + (spe->sample_branch || spe->sample_instructions)) + arm_spe__prep_branch_stack(speq); + if (spe->sample_branch && (record->op & ARM_SPE_OP_BRANCH_ERET)) { err = arm_spe__synth_branch_sample(speq, spe->branch_id); if (err) @@ -767,7 +906,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq) * When data_src is zero it means the record is not a memory operation, * skip to synthesize memory sample for this case. */ - if (spe->sample_memory && data_src) { + if (spe->sample_memory && is_ldst_op(record->op)) { err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src); if (err) return err; @@ -1240,6 +1379,7 @@ static void arm_spe_free_queue(void *priv) thread__zput(speq->thread); arm_spe_decoder_free(speq->decoder); zfree(&speq->event_buf); + zfree(&speq->last_branch); free(speq); } @@ -1459,6 +1599,19 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) id += 1; } + if (spe->synth_opts.last_branch) { + if (spe->synth_opts.last_branch_sz > 2) + pr_debug("Arm SPE supports only two bstack entries (PBT+TGT).\n"); + + attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } + if (spe->synth_opts.branches) { spe->sample_branch = true; diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 4940be4a0569..958afe8b821e 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -4,6 +4,7 @@ #include "event.h" #include "perf_regs.h" // SMPL_REG_MASK #include "unwind.h" +#include <string.h> #define perf_event_arm_regs perf_event_arm64_regs #include "../../arch/arm64/include/uapi/asm/perf_regs.h" @@ -16,8 +17,13 @@ struct entries { static bool get_leaf_frame_caller_enabled(struct perf_sample *sample) { - return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs - && sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR); + struct regs_dump *regs; + + if (callchain_param.record_mode != CALLCHAIN_FP) + return false; + + regs = perf_sample__user_regs(sample); + return regs->regs && regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_LR); } static int add_entry(struct unwind_entry *entry, void *arg) @@ -32,7 +38,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr { int ret; struct entries entries = {}; - struct regs_dump old_regs = sample->user_regs; + struct regs_dump old_regs, *regs; if (!get_leaf_frame_caller_enabled(sample)) return 0; @@ -42,19 +48,20 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr * and set its mask. SP is not used when doing the unwinding but it * still needs to be set to prevent failures. */ - - if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) { - sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC); - sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1]; + regs = perf_sample__user_regs(sample); + memcpy(&old_regs, regs, sizeof(*regs)); + if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) { + regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC); + regs->cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1]; } - if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) { - sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP); - sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; + if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) { + regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP); + regs->cache_regs[PERF_REG_ARM64_SP] = 0; } ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); - sample->user_regs = old_regs; + memcpy(regs, &old_regs, sizeof(*regs)); if (ret || entries.length != 2) return ret; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 4d1633d87eff..03211c2623de 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1173,16 +1173,19 @@ static int auxtrace_queue_data_cb(struct perf_session *session, if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE) return 0; + perf_sample__init(&sample, /*all=*/false); err = evlist__parse_sample(session->evlist, event, &sample); if (err) - return err; - - if (!sample.aux_sample.size) - return 0; + goto out; - offset += sample.aux_sample.data - (void *)event; + if (sample.aux_sample.size) { + offset += sample.aux_sample.data - (void *)event; - return session->auxtrace->queue_data(session, &sample, NULL, offset); + err = session->auxtrace->queue_data(session, &sample, NULL, offset); + } +out: + perf_sample__exit(&sample); + return err; } int auxtrace_queue_data(struct perf_session *session, bool samples, bool events) diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index f313404f95a9..6aa65ade3385 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -76,7 +76,7 @@ static int path_or_error(void) num_dec [0-9]+ num_hex 0[Xx][0-9a-fA-F]+ space [ \t]+ -path [^ \t\n]+ +path [^ \t\n,]+ ident [_a-zA-Z][_a-zA-Z0-9]+ %% diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index 25fc280e414a..7324668cc83e 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -39,6 +39,10 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) skel->rodata->bucket_range = ftrace->bucket_range; skel->rodata->min_latency = ftrace->min_latency; + skel->rodata->bucket_num = ftrace->bucket_num; + if (ftrace->bucket_range && ftrace->bucket_num) { + bpf_map__set_max_entries(skel->maps.latency, ftrace->bucket_num); + } /* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { @@ -124,7 +128,7 @@ int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) return 0; } -int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, +int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace, int buckets[], struct stats *stats) { int i, fd, err; @@ -138,7 +142,7 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, if (hist == NULL) return -ENOMEM; - for (idx = 0; idx < NUM_BUCKET; idx++) { + for (idx = 0; idx < skel->rodata->bucket_num; idx++) { err = bpf_map_lookup_elem(fd, &idx, hist); if (err) { buckets[idx] = 0; @@ -154,6 +158,12 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, stats->n = skel->bss->count; stats->max = skel->bss->max; stats->min = skel->bss->min; + + if (!ftrace->use_nsec) { + stats->mean /= 1000; + stats->max /= 1000; + stats->min /= 1000; + } } free(hist); diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index fc8666222399..5af8f6d1bc95 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -131,10 +131,20 @@ int lock_contention_prepare(struct lock_contention *con) else bpf_map__set_max_entries(skel->maps.task_data, 1); - if (con->save_callstack) + if (con->save_callstack) { bpf_map__set_max_entries(skel->maps.stacks, con->map_nr_entries); - else + if (con->owner) { + bpf_map__set_value_size(skel->maps.stack_buf, con->max_stack * sizeof(u64)); + bpf_map__set_key_size(skel->maps.owner_stacks, + con->max_stack * sizeof(u64)); + bpf_map__set_max_entries(skel->maps.owner_stacks, con->map_nr_entries); + bpf_map__set_max_entries(skel->maps.owner_data, con->map_nr_entries); + bpf_map__set_max_entries(skel->maps.owner_stat, con->map_nr_entries); + skel->rodata->max_stack = con->max_stack; + } + } else { bpf_map__set_max_entries(skel->maps.stacks, 1); + } if (target__has_cpu(target)) { skel->rodata->has_cpu = 1; @@ -450,7 +460,6 @@ static const char *lock_contention_get_name(struct lock_contention *con, { int idx = 0; u64 addr; - const char *name = ""; static char name_buf[KSYM_NAME_LEN]; struct symbol *sym; struct map *kmap; @@ -465,13 +474,14 @@ static const char *lock_contention_get_name(struct lock_contention *con, if (pid) { struct thread *t = machine__findnew_thread(machine, /*pid=*/-1, pid); - if (t == NULL) - return name; - if (!bpf_map_lookup_elem(task_fd, &pid, &task) && - thread__set_comm(t, task.comm, /*timestamp=*/0)) - name = task.comm; + if (t != NULL && + !bpf_map_lookup_elem(task_fd, &pid, &task) && + thread__set_comm(t, task.comm, /*timestamp=*/0)) { + snprintf(name_buf, sizeof(name_buf), "%s", task.comm); + return name_buf; + } } - return name; + return ""; } if (con->aggr_mode == LOCK_AGGR_ADDR) { @@ -539,6 +549,63 @@ static const char *lock_contention_get_name(struct lock_contention *con, return name_buf; } +struct lock_stat *pop_owner_stack_trace(struct lock_contention *con) +{ + int stacks_fd, stat_fd; + u64 *stack_trace = NULL; + s32 stack_id; + struct contention_key ckey = {}; + struct contention_data cdata = {}; + size_t stack_size = con->max_stack * sizeof(*stack_trace); + struct lock_stat *st = NULL; + + stacks_fd = bpf_map__fd(skel->maps.owner_stacks); + stat_fd = bpf_map__fd(skel->maps.owner_stat); + if (!stacks_fd || !stat_fd) + goto out_err; + + stack_trace = zalloc(stack_size); + if (stack_trace == NULL) + goto out_err; + + if (bpf_map_get_next_key(stacks_fd, NULL, stack_trace)) + goto out_err; + + bpf_map_lookup_elem(stacks_fd, stack_trace, &stack_id); + ckey.stack_id = stack_id; + bpf_map_lookup_elem(stat_fd, &ckey, &cdata); + + st = zalloc(sizeof(struct lock_stat)); + if (!st) + goto out_err; + + st->name = strdup(stack_trace[0] ? lock_contention_get_name(con, NULL, stack_trace, 0) : + "unknown"); + if (!st->name) + goto out_err; + + st->flags = cdata.flags; + st->nr_contended = cdata.count; + st->wait_time_total = cdata.total_time; + st->wait_time_max = cdata.max_time; + st->wait_time_min = cdata.min_time; + st->callstack = stack_trace; + + if (cdata.count) + st->avg_wait_time = cdata.total_time / cdata.count; + + bpf_map_delete_elem(stacks_fd, stack_trace); + bpf_map_delete_elem(stat_fd, &ckey); + + return st; + +out_err: + free(stack_trace); + free(st); + + return NULL; +} + int lock_contention_read(struct lock_contention *con) { int fd, stack, err = 0; diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c index fb144811b34f..e731a79a753a 100644 --- a/tools/perf/util/bpf_skel/func_latency.bpf.c +++ b/tools/perf/util/bpf_skel/func_latency.bpf.c @@ -50,6 +50,7 @@ const volatile int use_nsec = 0; const volatile unsigned int bucket_range; const volatile unsigned int min_latency; const volatile unsigned int max_latency; +const volatile unsigned int bucket_num = NUM_BUCKET; SEC("kprobe/func") int BPF_PROG(func_begin) @@ -101,6 +102,7 @@ int BPF_PROG(func_end) start = bpf_map_lookup_elem(&functime, &tid); if (start) { __s64 delta = bpf_ktime_get_ns() - *start; + __u64 val = delta; __u32 key = 0; __u64 *hist; @@ -110,30 +112,27 @@ int BPF_PROG(func_end) return 0; if (bucket_range != 0) { - delta /= cmp_base; + val = delta / cmp_base; if (min_latency > 0) { - if (delta > min_latency) - delta -= min_latency; + if (val > min_latency) + val -= min_latency; else goto do_lookup; } // Less than 1 unit (ms or ns), or, in the future, // than the min latency desired. - if (delta > 0) { // 1st entry: [ 1 unit .. bucket_range units ) - // clang 12 doesn't like s64 / u32 division - key = (__u64)delta / bucket_range + 1; - if (key >= NUM_BUCKET || - delta >= max_latency - min_latency) - key = NUM_BUCKET - 1; + if (val > 0) { // 1st entry: [ 1 unit .. bucket_range units ) + key = val / bucket_range + 1; + if (key >= bucket_num) + key = bucket_num - 1; } - delta += min_latency; goto do_lookup; } // calculate index using delta - for (key = 0; key < (NUM_BUCKET - 1); key++) { + for (key = 0; key < (bucket_num - 1); key++) { if (delta < (cmp_base << key)) break; } @@ -143,12 +142,9 @@ do_lookup: if (!hist) return 0; - *hist += 1; + __sync_fetch_and_add(hist, 1); - if (bucket_range == 0) - delta /= cmp_base; - - __sync_fetch_and_add(&total, delta); + __sync_fetch_and_add(&total, delta); // always in nsec __sync_fetch_and_add(&count, 1); if (delta > max) diff --git a/tools/perf/util/bpf_skel/kwork_trace.bpf.c b/tools/perf/util/bpf_skel/kwork_trace.bpf.c index cbd79bc4b330..9ce9c8dddc4b 100644 --- a/tools/perf/util/bpf_skel/kwork_trace.bpf.c +++ b/tools/perf/util/bpf_skel/kwork_trace.bpf.c @@ -80,7 +80,7 @@ static __always_inline int local_strncmp(const char *s1, for (i = 0; i < sz; i++) { ret = (unsigned char)s1[i] - (unsigned char)s2[i]; - if (ret || !s1[i] || !s2[i]) + if (ret || !s1[i]) break; } diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 6533ea9b044c..69be7a4234e0 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -27,6 +27,38 @@ struct { __uint(max_entries, MAX_ENTRIES); } stacks SEC(".maps"); +/* buffer for owner stacktrace */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u64)); + __uint(max_entries, 1); +} stack_buf SEC(".maps"); + +/* a map for tracing owner stacktrace to owner stack id */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); // owner stacktrace + __uint(value_size, sizeof(__s32)); // owner stack id + __uint(max_entries, 1); +} owner_stacks SEC(".maps"); + +/* a map for tracing lock address to owner data */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); // lock address + __uint(value_size, sizeof(struct owner_tracing_data)); + __uint(max_entries, 1); +} owner_data SEC(".maps"); + +/* a map for contention_key (stores owner stack id) to contention data */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(struct contention_key)); + __uint(value_size, sizeof(struct contention_data)); + __uint(max_entries, 1); +} owner_stat SEC(".maps"); + /* maintain timestamp at the beginning of contention */ struct { __uint(type, BPF_MAP_TYPE_HASH); @@ -143,6 +175,7 @@ const volatile int needs_callstack; const volatile int stack_skip; const volatile int lock_owner; const volatile int use_cgroup_v2; +const volatile int max_stack; /* determine the key of lock stat */ const volatile int aggr_mode; @@ -164,6 +197,9 @@ int data_fail; int task_map_full; int data_map_full; +struct task_struct *bpf_task_from_pid(s32 pid) __ksym __weak; +void bpf_task_release(struct task_struct *p) __ksym __weak; + static inline __u64 get_current_cgroup_id(void) { struct task_struct *task; @@ -387,6 +423,61 @@ static inline struct tstamp_data *get_tstamp_elem(__u32 flags) return pelem; } +static inline s32 get_owner_stack_id(u64 *stacktrace) +{ + s32 *id, new_id; + static s64 id_gen = 1; + + id = bpf_map_lookup_elem(&owner_stacks, stacktrace); + if (id) + return *id; + + new_id = (s32)__sync_fetch_and_add(&id_gen, 1); + + bpf_map_update_elem(&owner_stacks, stacktrace, &new_id, BPF_NOEXIST); + + id = bpf_map_lookup_elem(&owner_stacks, stacktrace); + if (id) + return *id; + + return -1; +} + +static inline void update_contention_data(struct contention_data *data, u64 duration, u32 count) +{ + __sync_fetch_and_add(&data->total_time, duration); + __sync_fetch_and_add(&data->count, count); + + /* FIXME: need atomic operations */ + if (data->max_time < duration) + data->max_time = duration; + if (data->min_time > duration) + data->min_time = duration; +} + +static inline void update_owner_stat(u32 id, u64 duration, u32 flags) +{ + struct contention_key key = { + .stack_id = id, + .pid = 0, + .lock_addr_or_cgroup = 0, + }; + struct contention_data *data = bpf_map_lookup_elem(&owner_stat, &key); + + if (!data) { + struct contention_data first = { + .total_time = duration, + .max_time = duration, + .min_time = duration, + .count = 1, + .flags = flags, + }; + bpf_map_update_elem(&owner_stat, &key, &first, BPF_NOEXIST); + } else { + update_contention_data(data, duration, 1); + } +} + SEC("tp_btf/contention_begin") int contention_begin(u64 *ctx) { @@ -404,6 +495,72 @@ int contention_begin(u64 *ctx) pelem->flags = (__u32)ctx[1]; if (needs_callstack) { + u32 i = 0; + u32 id = 0; + int owner_pid; + u64 *buf; + struct task_struct *task; + struct owner_tracing_data *otdata; + + if (!lock_owner) + goto skip_owner; + + task = get_lock_owner(pelem->lock, pelem->flags); + if (!task) + goto skip_owner; + + owner_pid = BPF_CORE_READ(task, pid); + + buf = bpf_map_lookup_elem(&stack_buf, &i); + if (!buf) + goto skip_owner; + for (i = 0; i < max_stack; i++) + buf[i] = 0x0; + + if (!bpf_task_from_pid) + goto skip_owner; + + task = bpf_task_from_pid(owner_pid); + if (!task) + goto skip_owner; + + bpf_get_task_stack(task, buf, max_stack * sizeof(unsigned long), 0); + bpf_task_release(task); + + otdata = bpf_map_lookup_elem(&owner_data, &pelem->lock); + id = get_owner_stack_id(buf); + + /* + * Contention just happens, or corner case `lock` is owned by process not + * `owner_pid`. For the corner case we treat it as unexpected internal error and + * just ignore the precvious tracing record. + */ + if (!otdata || otdata->pid != owner_pid) { + struct owner_tracing_data first = { + .pid = owner_pid, + .timestamp = pelem->timestamp, + .count = 1, + .stack_id = id, + }; + bpf_map_update_elem(&owner_data, &pelem->lock, &first, BPF_ANY); + } + /* Contention is ongoing and new waiter joins */ + else { + __sync_fetch_and_add(&otdata->count, 1); + + /* + * The owner is the same, but stacktrace might be changed. In this case we + * store/update `owner_stat` based on current owner stack id. + */ + if (id != otdata->stack_id) { + update_owner_stat(id, pelem->timestamp - otdata->timestamp, + pelem->flags); + + otdata->timestamp = pelem->timestamp; + otdata->stack_id = id; + } + } +skip_owner: pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP | stack_skip); if (pelem->stack_id < 0) @@ -440,6 +597,7 @@ int contention_end(u64 *ctx) struct tstamp_data *pelem; struct contention_key key = {}; struct contention_data *data; + __u64 timestamp; __u64 duration; bool need_delete = false; @@ -467,12 +625,88 @@ int contention_end(u64 *ctx) need_delete = true; } - duration = bpf_ktime_get_ns() - pelem->timestamp; + timestamp = bpf_ktime_get_ns(); + duration = timestamp - pelem->timestamp; if ((__s64)duration < 0) { __sync_fetch_and_add(&time_fail, 1); goto out; } + if (needs_callstack && lock_owner) { + struct owner_tracing_data *otdata = bpf_map_lookup_elem(&owner_data, &pelem->lock); + + if (!otdata) + goto skip_owner; + + /* Update `owner_stat` */ + update_owner_stat(otdata->stack_id, timestamp - otdata->timestamp, pelem->flags); + + /* No contention is occurring, delete `lock` entry in `owner_data` */ + if (otdata->count <= 1) + bpf_map_delete_elem(&owner_data, &pelem->lock); + /* + * Contention is still ongoing, with a new owner (current task). `owner_data` + * should be updated accordingly. + */ + else { + u32 i = 0; + s32 ret = (s32)ctx[1]; + u64 *buf; + + otdata->timestamp = timestamp; + __sync_fetch_and_add(&otdata->count, -1); + + buf = bpf_map_lookup_elem(&stack_buf, &i); + if (!buf) + goto skip_owner; + for (i = 0; i < (u32)max_stack; i++) + buf[i] = 0x0; + + /* + * `ret` has the return code of the lock function. + * If `ret` is negative, the current task terminates lock waiting without + * acquiring it. Owner is not changed, but we still need to update the owner + * stack. + */ + if (ret < 0) { + s32 id = 0; + struct task_struct *task; + + if (!bpf_task_from_pid) + goto skip_owner; + + task = bpf_task_from_pid(otdata->pid); + if (!task) + goto skip_owner; + + bpf_get_task_stack(task, buf, + max_stack * sizeof(unsigned long), 0); + bpf_task_release(task); + + id = get_owner_stack_id(buf); + + /* + * If owner stack is changed, update owner stack id for this lock. + */ + if (id != otdata->stack_id) + otdata->stack_id = id; + } + /* + * Otherwise, update tracing data with the current task, which is the new + * owner. + */ + else { + otdata->pid = pid; + /* + * We don't want to retrieve callstack here, since it is where the + * current task acquires the lock and provides no additional + * information. We simply assign -1 to invalidate it. + */ + otdata->stack_id = -1; + } + } + } +skip_owner: switch (aggr_mode) { case LOCK_AGGR_CALLER: key.stack_id = pelem->stack_id; @@ -556,14 +790,7 @@ int contention_end(u64 *ctx) } found: - __sync_fetch_and_add(&data->total_time, duration); - __sync_fetch_and_add(&data->count, 1); - - /* FIXME: need atomic operations */ - if (data->max_time < duration) - data->max_time = duration; - if (data->min_time > duration) - data->min_time = duration; + update_contention_data(data, duration, 1); out: pelem->lock = 0; diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index c15f734d7fc4..15f5743bd409 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -3,6 +3,13 @@ #ifndef UTIL_BPF_SKEL_LOCK_DATA_H #define UTIL_BPF_SKEL_LOCK_DATA_H +struct owner_tracing_data { + u32 pid; // Who has the lock. + u32 count; // How many waiters for this lock. + u64 timestamp; // The time while the owner acquires lock and contention is going on. + s32 stack_id; // Identifier for `owner_stat`, which stores as value in `owner_stacks` +}; + struct tstamp_data { u64 timestamp; u64 lock; diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index b80c12c74bbb..7429530fa774 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -25,7 +25,8 @@ struct branch_flags { u64 spec:2; u64 new_type:4; u64 priv:3; - u64 reserved:31; + u64 not_taken:1; + u64 reserved:30; }; }; }; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 0c7564747a14..d7b7eef740b9 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -589,9 +589,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) return -ENOMEM; } call->ip = cursor_node->ip; - call->ms = cursor_node->ms; - call->ms.map = map__get(call->ms.map); - call->ms.maps = maps__get(call->ms.maps); + map_symbol__copy(&call->ms, &cursor_node->ms); call->srcline = cursor_node->srcline; if (cursor_node->branch) { @@ -1094,9 +1092,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, node->ip = ip; map_symbol__exit(&node->ms); - node->ms = *ms; - node->ms.maps = maps__get(ms->maps); - node->ms.map = map__get(ms->map); + map_symbol__copy(&node->ms, ms); node->branch = branch; node->nr_loop_iter = nr_loop_iter; node->iter_cycles = iter_cycles; @@ -1564,7 +1560,7 @@ int callchain_node__make_parent_list(struct callchain_node *node) goto out; *new = *chain; new->has_children = false; - new->ms.map = map__get(new->ms.map); + map_symbol__copy(&new->ms, &chain->ms); list_add_tail(&new->list, &head); } parent = parent->parent; diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index 9a7248dbe2d7..0319546decca 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -30,11 +30,6 @@ extern int perf_use_color_default; -/* - * Use this instead of perf_default_config if you need the value of color.ui. - */ -int perf_color_default_config(const char *var, const char *value, void *cb); - int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty); int color_vsnprintf(char *bf, size_t size, const char *color, const char *fmt, va_list args); diff --git a/tools/perf/util/color_config.c b/tools/perf/util/color_config.c index dc09ba7cb31e..301031ddc025 100644 --- a/tools/perf/util/color_config.c +++ b/tools/perf/util/color_config.c @@ -35,14 +35,3 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) } return 0; } - -int perf_color_default_config(const char *var, const char *value, - void *cb __maybe_unused) -{ - if (!strcmp(var, "color.ui")) { - perf_use_color_default = perf_config_colorbool(var, value, -1); - return 0; - } - - return 0; -} diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 49b79cf0c5cc..8aa456d7c2cd 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -5,6 +5,8 @@ #include <internal/rc_check.h> #include <linux/refcount.h> #include <linux/zalloc.h> +#include <tools/libc_compat.h> // reallocarray + #include "rwsem.h" DECLARE_RC_STRUCT(comm_str) { diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h index b29109cd3609..6cfecfca16f2 100644 --- a/tools/perf/util/compress.h +++ b/tools/perf/util/compress.h @@ -4,7 +4,9 @@ #include <stdbool.h> #include <stddef.h> +#include <stdio.h> #include <sys/types.h> +#include <linux/compiler.h> #ifdef HAVE_ZSTD_SUPPORT #include <zstd.h> #endif @@ -15,8 +17,26 @@ bool gzip_is_compressed(const char *input); #endif #ifdef HAVE_LZMA_SUPPORT +int lzma_decompress_stream_to_file(FILE *input, int output_fd); int lzma_decompress_to_file(const char *input, int output_fd); bool lzma_is_compressed(const char *input); +#else +static inline +int lzma_decompress_stream_to_file(FILE *input __maybe_unused, + int output_fd __maybe_unused) +{ + return -1; +} +static inline +int lzma_decompress_to_file(const char *input __maybe_unused, + int output_fd __maybe_unused) +{ + return -1; +} +static inline int lzma_is_compressed(const char *input __maybe_unused) +{ + return false; +} #endif struct zstd_data { diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 2d07c9257a1a..ae72b66b6ded 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -856,12 +856,6 @@ void perf_config__exit(void) config_set = NULL; } -void perf_config__refresh(void) -{ - perf_config__exit(); - perf_config__init(); -} - static void perf_config_item__delete(struct perf_config_item *item) { zfree(&item->name); diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index a727c95cb119..987b47cf54c3 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -49,7 +49,6 @@ void perf_config_set__delete(struct perf_config_set *set); int perf_config_set__collect(struct perf_config_set *set, const char *file_name, const char *var, const char *value); void perf_config__exit(void); -void perf_config__refresh(void); int perf_config__set_variable(const char *var, const char *value); /** diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 5c329ad614e9..89570397a4b3 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -67,19 +67,23 @@ static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_m struct perf_cpu_map *map; map = perf_cpu_map__empty_new(data->cpus_data.nr); - if (map) { - unsigned i; - - for (i = 0; i < data->cpus_data.nr; i++) { - /* - * Special treatment for -1, which is not real cpu number, - * and we need to use (int) -1 to initialize map[i], - * otherwise it would become 65535. - */ - if (data->cpus_data.cpu[i] == (u16) -1) - RC_CHK_ACCESS(map)->map[i].cpu = -1; - else - RC_CHK_ACCESS(map)->map[i].cpu = (int) data->cpus_data.cpu[i]; + if (!map) + return NULL; + + for (unsigned int i = 0; i < data->cpus_data.nr; i++) { + /* + * Special treatment for -1, which is not real cpu number, + * and we need to use (int) -1 to initialize map[i], + * otherwise it would become 65535. + */ + if (data->cpus_data.cpu[i] == (u16) -1) { + RC_CHK_ACCESS(map)->map[i].cpu = -1; + } else if (data->cpus_data.cpu[i] < INT16_MAX) { + RC_CHK_ACCESS(map)->map[i].cpu = (int16_t) data->cpus_data.cpu[i]; + } else { + pr_err("Invalid cpumap entry %u\n", data->cpus_data.cpu[i]); + perf_cpu_map__put(map); + return NULL; } } @@ -106,8 +110,15 @@ static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_ int cpu; perf_record_cpu_map_data__read_one_mask(data, i, local_copy); - for_each_set_bit(cpu, local_copy, 64) - RC_CHK_ACCESS(map)->map[j++].cpu = cpu + cpus_per_i; + for_each_set_bit(cpu, local_copy, 64) { + if (cpu + cpus_per_i < INT16_MAX) { + RC_CHK_ACCESS(map)->map[j++].cpu = cpu + cpus_per_i; + } else { + pr_err("Invalid cpumap entry %d\n", cpu + cpus_per_i); + perf_cpu_map__put(map); + return NULL; + } + } } return map; @@ -127,8 +138,15 @@ static struct perf_cpu_map *cpu_map__from_range(const struct perf_record_cpu_map RC_CHK_ACCESS(map)->map[i++].cpu = -1; for (int cpu = data->range_cpu_data.start_cpu; cpu <= data->range_cpu_data.end_cpu; - i++, cpu++) - RC_CHK_ACCESS(map)->map[i].cpu = cpu; + i++, cpu++) { + if (cpu < INT16_MAX) { + RC_CHK_ACCESS(map)->map[i].cpu = cpu; + } else { + pr_err("Invalid cpumap entry %d\n", cpu); + perf_cpu_map__put(map); + return NULL; + } + } return map; } @@ -427,7 +445,7 @@ static void set_max_cpu_num(void) { const char *mnt; char path[PATH_MAX]; - int ret = -1; + int max, ret = -1; /* set up default */ max_cpu_num.cpu = 4096; @@ -444,10 +462,12 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_cpu_num.cpu); + ret = get_max_num(path, &max); if (ret) goto out; + max_cpu_num.cpu = max; + /* get the highest present cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt); if (ret >= PATH_MAX) { @@ -455,8 +475,14 @@ static void set_max_cpu_num(void) goto out; } - ret = get_max_num(path, &max_present_cpu_num.cpu); + ret = get_max_num(path, &max); + if (!ret && max > INT16_MAX) { + pr_err("Read out of bounds max cpus of %d\n", max); + ret = -1; + } + if (!ret) + max_present_cpu_num.cpu = (int16_t)max; out: if (ret) pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu); @@ -606,7 +632,7 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) #define COMMA first ? "" : "," for (i = 0; i < perf_cpu_map__nr(map) + 1; i++) { - struct perf_cpu cpu = { .cpu = INT_MAX }; + struct perf_cpu cpu = { .cpu = INT16_MAX }; bool last = i == perf_cpu_map__nr(map); if (!last) @@ -696,7 +722,7 @@ struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ if (!online) online = perf_cpu_map__new_online_cpus(); /* from /sys/devices/system/cpu/online */ - return online; + return perf_cpu_map__get(online); } bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 0bf9e5c27b59..30f4bb3e7fa3 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -506,20 +506,27 @@ static int cs_etm__process_aux_output_hw_id(struct perf_session *session, evsel = evlist__event2evsel(session->evlist, event); if (!evsel) return -EINVAL; + perf_sample__init(&sample, /*all=*/false); err = evsel__parse_sample(evsel, event, &sample); if (err) - return err; + goto out; cpu = sample.cpu; if (cpu == -1) { /* no CPU in the sample - possibly recorded with an old version of perf */ pr_err("CS_ETM: no CPU AUX_OUTPUT_HW_ID sample. Use compatible perf to record."); - return -EINVAL; + err = -EINVAL; + goto out; } - if (FIELD_GET(CS_AUX_HW_ID_MINOR_VERSION_MASK, hw_id) == 0) - return cs_etm__process_trace_id_v0(etm, cpu, hw_id); + if (FIELD_GET(CS_AUX_HW_ID_MINOR_VERSION_MASK, hw_id) == 0) { + err = cs_etm__process_trace_id_v0(etm, cpu, hw_id); + goto out; + } - return cs_etm__process_trace_id_v0_1(etm, cpu, hw_id); + err = cs_etm__process_trace_id_v0_1(etm, cpu, hw_id); +out: + perf_sample__exit(&sample); + return err; } void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, @@ -1560,8 +1567,9 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, int ret = 0; struct cs_etm_auxtrace *etm = etmq->etm; union perf_event *event = tidq->event_buf; - struct perf_sample sample = {.ip = 0,}; + struct perf_sample sample; + perf_sample__init(&sample, /*all=*/true); event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = cs_etm__cpu_mode(etmq, addr, tidq->el); event->sample.header.size = sizeof(struct perf_event_header); @@ -1598,6 +1606,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, "CS ETM Trace: failed to deliver instruction event, error %d\n", ret); + perf_sample__exit(&sample); return ret; } @@ -3151,9 +3160,10 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf evsel = evlist__event2evsel(session->evlist, event); if (!evsel) return -EINVAL; + perf_sample__init(&sample, /*all=*/false); ret = evsel__parse_sample(evsel, event, &sample); if (ret) - return ret; + goto out; /* * Loop through the auxtrace index to find the buffer that matches up with this aux event. @@ -3168,7 +3178,7 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf * 1 ('not found') */ if (ret != 1) - return ret; + goto out; } } @@ -3178,7 +3188,10 @@ static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf */ pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64 " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu); - return 0; + ret = 0; +out: + perf_sample__exit(&sample); + return ret; } static int cs_etm__queue_aux_records(struct perf_session *session) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 98661ede2a73..164eb45a0b36 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -158,26 +158,6 @@ out_err: return ret; } -int perf_data__update_dir(struct perf_data *data) -{ - int i; - - if (WARN_ON(!data->is_dir)) - return -EINVAL; - - for (i = 0; i < data->dir.nr; i++) { - struct perf_data_file *file = &data->dir.files[i]; - struct stat st; - - if (fstat(file->fd, &st)) - return -1; - - file->size = st.st_size; - } - - return 0; -} - static bool check_pipe(struct perf_data *data) { struct stat st; diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 110f3ebde30f..1438e32e0451 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -97,7 +97,6 @@ int perf_data__switch(struct perf_data *data, int perf_data__create_dir(struct perf_data *data, int nr); int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); -int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); bool has_kcore_dir(const char *path); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 995f6bb05b5f..f9ef7d045c92 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -46,8 +46,8 @@ int debug_type_profile; FILE *debug_file(void) { if (!_debug_file) { - pr_warning_once("debug_file not set"); debug_set_file(stderr); + pr_warning_once("debug_file not set"); } return _debug_file; } diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c index 19acf4775d35..b5deea7cbdf2 100644 --- a/tools/perf/util/debuginfo.c +++ b/tools/perf/util/debuginfo.c @@ -125,8 +125,12 @@ struct debuginfo *debuginfo__new(const char *path) dso__put(dso); out: + if (dinfo) + return dinfo; + /* if failed to open all distro debuginfo, open given binary */ - return dinfo ? : __debuginfo__new(path); + symbol__join_symfs(buf, path); + return __debuginfo__new(buf); } void debuginfo__delete(struct debuginfo *dbg) diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index 50c5c206b70e..8f0eb56c6fc6 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -48,7 +48,7 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size, static void ins__sort(struct arch *arch); static int disasm_line__parse(char *line, const char **namep, char **rawp); -static int disasm_line__parse_powerpc(struct disasm_line *dl); +static int disasm_line__parse_powerpc(struct disasm_line *dl, struct annotate_args *args); static char *expand_tabs(char *line, char **storage, size_t *storage_len); static __attribute__((constructor)) void symbol__init_regexpr(void) @@ -968,24 +968,25 @@ out: #define PPC_OP(op) (((op) >> 26) & 0x3F) #define RAW_BYTES 11 -static int disasm_line__parse_powerpc(struct disasm_line *dl) +static int disasm_line__parse_powerpc(struct disasm_line *dl, struct annotate_args *args) { char *line = dl->al.line; const char **namep = &dl->ins.name; char **rawp = &dl->ops.raw; char *tmp_raw_insn, *name_raw_insn = skip_spaces(line); char *name = skip_spaces(name_raw_insn + RAW_BYTES); - int objdump = 0; + int disasm = 0; + int ret = 0; - if (strlen(line) > RAW_BYTES) - objdump = 1; + if (args->options->disassembler_used) + disasm = 1; if (name_raw_insn[0] == '\0') return -1; - if (objdump) { - disasm_line__parse(name, namep, rawp); - } else + if (disasm) + ret = disasm_line__parse(name, namep, rawp); + else *namep = ""; tmp_raw_insn = strndup(name_raw_insn, 11); @@ -995,10 +996,10 @@ static int disasm_line__parse_powerpc(struct disasm_line *dl) remove_spaces(tmp_raw_insn); sscanf(tmp_raw_insn, "%x", &dl->raw.raw_insn); - if (objdump) + if (disasm) dl->raw.raw_insn = be32_to_cpu(dl->raw.raw_insn); - return 0; + return ret; } static void annotation_line__init(struct annotation_line *al, @@ -1054,7 +1055,7 @@ struct disasm_line *disasm_line__new(struct annotate_args *args) if (args->offset != -1) { if (arch__is(args->arch, "powerpc")) { - if (disasm_line__parse_powerpc(dl) < 0) + if (disasm_line__parse_powerpc(dl, args) < 0) goto out_free_line; } else if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) goto out_free_line; @@ -2289,16 +2290,20 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) switch (dis) { case PERF_DISASM_LLVM: + args->options->disassembler_used = PERF_DISASM_LLVM; err = symbol__disassemble_llvm(symfs_filename, sym, args); break; case PERF_DISASM_CAPSTONE: + args->options->disassembler_used = PERF_DISASM_CAPSTONE; err = symbol__disassemble_capstone(symfs_filename, sym, args); break; case PERF_DISASM_OBJDUMP: + args->options->disassembler_used = PERF_DISASM_OBJDUMP; err = symbol__disassemble_objdump(symfs_filename, sym, args); break; case PERF_DISASM_UNKNOWN: /* End of disassemblers. */ default: + args->options->disassembler_used = PERF_DISASM_UNKNOWN; goto out_remove_tmp; } if (err == 0) diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 5c6e85fdae0d..8619b6eea62d 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -67,6 +67,7 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', [DSO_BINARY_TYPE__GUEST_KMODULE_COMP] = 'M', [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', + [DSO_BINARY_TYPE__GNU_DEBUGDATA] = 'n', }; if (dso == NULL || dso__symtab_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) @@ -93,6 +94,7 @@ bool dso__is_object_file(const struct dso *dso) case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: case DSO_BINARY_TYPE__GUEST_KMODULE: case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: @@ -224,6 +226,7 @@ int dso__read_binary_type_filename(const struct dso *dso, case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: __symbol__join_symfs(filename, size, dso__long_name(dso)); break; @@ -490,11 +493,25 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, /* * Global list of open DSOs and the counter. */ +struct mutex _dso__data_open_lock; static LIST_HEAD(dso__data_open); -static long dso__data_open_cnt; -static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER; +static long dso__data_open_cnt GUARDED_BY(_dso__data_open_lock); -static void dso__list_add(struct dso *dso) +static void dso__data_open_lock_init(void) +{ + mutex_init(&_dso__data_open_lock); +} + +static struct mutex *dso__data_open_lock(void) LOCK_RETURNED(_dso__data_open_lock) +{ + static pthread_once_t data_open_lock_once = PTHREAD_ONCE_INIT; + + pthread_once(&data_open_lock_once, dso__data_open_lock_init); + + return &_dso__data_open_lock; +} + +static void dso__list_add(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { list_add_tail(&dso__data(dso)->open_entry, &dso__data_open); #ifdef REFCNT_CHECKING @@ -505,11 +522,13 @@ static void dso__list_add(struct dso *dso) dso__data_open_cnt++; } -static void dso__list_del(struct dso *dso) +static void dso__list_del(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { list_del_init(&dso__data(dso)->open_entry); #ifdef REFCNT_CHECKING + mutex_unlock(dso__data_open_lock()); dso__put(dso__data(dso)->dso); + mutex_lock(dso__data_open_lock()); #endif WARN_ONCE(dso__data_open_cnt <= 0, "DSO data fd counter out of bounds."); @@ -518,7 +537,7 @@ static void dso__list_del(struct dso *dso) static void close_first_dso(void); -static int do_open(char *name) +static int do_open(char *name) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { int fd; char sbuf[STRERR_BUFSIZE]; @@ -545,6 +564,7 @@ char *dso__filename_with_chroot(const struct dso *dso, const char *filename) } static int __open_dso(struct dso *dso, struct machine *machine) + EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { int fd = -EINVAL; char *root_dir = (char *)""; @@ -610,6 +630,7 @@ static void check_data_close(void); * list/count of open DSO objects. */ static int open_dso(struct dso *dso, struct machine *machine) + EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { int fd; struct nscookie nsc; @@ -635,7 +656,7 @@ static int open_dso(struct dso *dso, struct machine *machine) return fd; } -static void close_data_fd(struct dso *dso) +static void close_data_fd(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { if (dso__data(dso)->fd >= 0) { close(dso__data(dso)->fd); @@ -652,12 +673,12 @@ static void close_data_fd(struct dso *dso) * Close @dso's data file descriptor and updates * list/count of open DSO objects. */ -static void close_dso(struct dso *dso) +static void close_dso(struct dso *dso) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { close_data_fd(dso); } -static void close_first_dso(void) +static void close_first_dso(void) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { struct dso_data *dso_data; struct dso *dso; @@ -702,7 +723,7 @@ void reset_fd_limit(void) fd_limit = 0; } -static bool may_cache_fd(void) +static bool may_cache_fd(void) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { if (!fd_limit) fd_limit = get_fd_limit(); @@ -718,7 +739,7 @@ static bool may_cache_fd(void) * for opened dso file descriptors. The limit is half * of the RLIMIT_NOFILE files opened. */ -static void check_data_close(void) +static void check_data_close(void) EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { bool cache_fd = may_cache_fd(); @@ -734,12 +755,13 @@ static void check_data_close(void) */ void dso__data_close(struct dso *dso) { - pthread_mutex_lock(&dso__data_open_lock); + mutex_lock(dso__data_open_lock()); close_dso(dso); - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); } static void try_to_open_dso(struct dso *dso, struct machine *machine) + EXCLUSIVE_LOCKS_REQUIRED(_dso__data_open_lock) { enum dso_binary_type binary_type_data[] = { DSO_BINARY_TYPE__BUILD_ID_CACHE, @@ -781,25 +803,27 @@ out: * returns file descriptor. It should be paired with * dso__data_put_fd() if it returns non-negative value. */ -int dso__data_get_fd(struct dso *dso, struct machine *machine) +bool dso__data_get_fd(struct dso *dso, struct machine *machine, int *fd) { + *fd = -1; if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR) - return -1; + return false; - if (pthread_mutex_lock(&dso__data_open_lock) < 0) - return -1; + mutex_lock(dso__data_open_lock()); try_to_open_dso(dso, machine); - if (dso__data(dso)->fd < 0) - pthread_mutex_unlock(&dso__data_open_lock); + *fd = dso__data(dso)->fd; + if (*fd >= 0) + return true; - return dso__data(dso)->fd; + mutex_unlock(dso__data_open_lock()); + return false; } void dso__data_put_fd(struct dso *dso __maybe_unused) { - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); } bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by) @@ -951,7 +975,7 @@ static ssize_t file_read(struct dso *dso, struct machine *machine, { ssize_t ret; - pthread_mutex_lock(&dso__data_open_lock); + mutex_lock(dso__data_open_lock()); /* * dso__data(dso)->fd might be closed if other thread opened another @@ -967,7 +991,7 @@ static ssize_t file_read(struct dso *dso, struct machine *machine, ret = pread(dso__data(dso)->fd, data, DSO__DATA_CACHE_SIZE, offset); out: - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); return ret; } @@ -1075,7 +1099,7 @@ static int file_size(struct dso *dso, struct machine *machine) struct stat st; char sbuf[STRERR_BUFSIZE]; - pthread_mutex_lock(&dso__data_open_lock); + mutex_lock(dso__data_open_lock()); /* * dso__data(dso)->fd might be closed if other thread opened another @@ -1099,7 +1123,7 @@ static int file_size(struct dso *dso, struct machine *machine) dso__data(dso)->file_size = st.st_size; out: - pthread_mutex_unlock(&dso__data_open_lock); + mutex_unlock(dso__data_open_lock()); return ret; } @@ -1170,6 +1194,68 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, return data_read_write_offset(dso, machine, offset, data, size, true); } +uint16_t dso__e_machine(struct dso *dso, struct machine *machine) +{ + uint16_t e_machine = EM_NONE; + int fd; + + switch (dso__binary_type(dso)) { + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: + case DSO_BINARY_TYPE__KCORE: + case DSO_BINARY_TYPE__GUEST_KCORE: + case DSO_BINARY_TYPE__BPF_PROG_INFO: + case DSO_BINARY_TYPE__BPF_IMAGE: + case DSO_BINARY_TYPE__OOL: + case DSO_BINARY_TYPE__JAVA_JIT: + return EM_HOST; + case DSO_BINARY_TYPE__DEBUGLINK: + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + break; + case DSO_BINARY_TYPE__NOT_FOUND: + default: + return EM_NONE; + } + + mutex_lock(dso__data_open_lock()); + + /* + * dso__data(dso)->fd might be closed if other thread opened another + * file (dso) due to open file limit (RLIMIT_NOFILE). + */ + try_to_open_dso(dso, machine); + fd = dso__data(dso)->fd; + if (fd >= 0) { + _Static_assert(offsetof(Elf32_Ehdr, e_machine) == 18, "Unexpected offset"); + _Static_assert(offsetof(Elf64_Ehdr, e_machine) == 18, "Unexpected offset"); + if (dso__needs_swap(dso) == DSO_SWAP__UNSET) { + unsigned char eidata; + + if (pread(fd, &eidata, sizeof(eidata), EI_DATA) == sizeof(eidata)) + dso__swap_init(dso, eidata); + } + if (dso__needs_swap(dso) != DSO_SWAP__UNSET && + pread(fd, &e_machine, sizeof(e_machine), 18) == sizeof(e_machine)) + e_machine = DSO__SWAP(dso, uint16_t, e_machine); + } + mutex_unlock(dso__data_open_lock()); + return e_machine; +} + /** * dso__data_read_addr - Read data from dso address * @dso: dso object @@ -1525,6 +1611,33 @@ void dso__put(struct dso *dso) RC_CHK_PUT(dso); } +int dso__swap_init(struct dso *dso, unsigned char eidata) +{ + static unsigned int const endian = 1; + + dso__set_needs_swap(dso, DSO_SWAP__NO); + + switch (eidata) { + case ELFDATA2LSB: + /* We are big endian, DSO is little endian. */ + if (*(unsigned char const *)&endian != 1) + dso__set_needs_swap(dso, DSO_SWAP__YES); + break; + + case ELFDATA2MSB: + /* We are little endian, DSO is big endian. */ + if (*(unsigned char const *)&endian != 0) + dso__set_needs_swap(dso, DSO_SWAP__YES); + break; + + default: + pr_err("unrecognized DSO data encoding %d\n", eidata); + return -EINVAL; + } + + return 0; +} + void dso__set_build_id(struct dso *dso, struct build_id *bid) { RC_CHK_ACCESS(dso)->bid = *bid; @@ -1608,11 +1721,10 @@ size_t dso__fprintf(struct dso *dso, FILE *fp) enum dso_type dso__type(struct dso *dso, struct machine *machine) { - int fd; + int fd = -1; enum dso_type type = DSO__TYPE_UNKNOWN; - fd = dso__data_get_fd(dso, machine); - if (fd >= 0) { + if (dso__data_get_fd(dso, machine, &fd)) { type = dso__type_fd(fd); dso__data_put_fd(dso); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bb8e8f444054..c87564471f9b 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -20,30 +20,88 @@ struct perf_env; #define DSO__NAME_KALLSYMS "[kernel.kallsyms]" #define DSO__NAME_KCORE "[kernel.kcore]" +/** + * enum dso_binary_type - The kind of DSO generally associated with a memory + * region (struct map). + */ enum dso_binary_type { + /** @DSO_BINARY_TYPE__KALLSYMS: Symbols from /proc/kallsyms file. */ DSO_BINARY_TYPE__KALLSYMS = 0, + /** @DSO_BINARY_TYPE__GUEST_KALLSYMS: Guest /proc/kallsyms file. */ DSO_BINARY_TYPE__GUEST_KALLSYMS, + /** @DSO_BINARY_TYPE__VMLINUX: Path to kernel /boot/vmlinux file. */ DSO_BINARY_TYPE__VMLINUX, + /** @DSO_BINARY_TYPE__GUEST_VMLINUX: Path to guest kernel /boot/vmlinux file. */ DSO_BINARY_TYPE__GUEST_VMLINUX, + /** @DSO_BINARY_TYPE__JAVA_JIT: Symbols from /tmp/perf.map file. */ DSO_BINARY_TYPE__JAVA_JIT, + /** + * @DSO_BINARY_TYPE__DEBUGLINK: Debug file readable from the file path + * in the .gnu_debuglink ELF section of the dso. + */ DSO_BINARY_TYPE__DEBUGLINK, + /** + * @DSO_BINARY_TYPE__BUILD_ID_CACHE: File named after buildid located in + * the buildid cache with an elf filename. + */ DSO_BINARY_TYPE__BUILD_ID_CACHE, + /** + * @DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: File named after buildid + * located in the buildid cache with a debug filename. + */ DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__FEDORA_DEBUGINFO: Debug file in /usr/lib/debug + * with .debug suffix. + */ DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + /** @DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: Debug file in /usr/lib/debug. */ DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: dso__long_name debuginfo + * file in /usr/lib/debug/lib rather than the expected + * /usr/lib/debug/usr/lib. + */ DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__BUILDID_DEBUGINFO: File named after buildid located + * in /usr/lib/debug/.build-id/. + */ DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + /** + * @DSO_BINARY_TYPE__GNU_DEBUGDATA: MiniDebuginfo where a compressed + * ELF file is placed in a .gnu_debugdata section. + */ + DSO_BINARY_TYPE__GNU_DEBUGDATA, + /** @DSO_BINARY_TYPE__SYSTEM_PATH_DSO: A regular executable/shared-object file. */ DSO_BINARY_TYPE__SYSTEM_PATH_DSO, + /** @DSO_BINARY_TYPE__GUEST_KMODULE: Guest kernel module .ko file. */ DSO_BINARY_TYPE__GUEST_KMODULE, + /** @DSO_BINARY_TYPE__GUEST_KMODULE_COMP: Guest kernel module .ko.gz file. */ DSO_BINARY_TYPE__GUEST_KMODULE_COMP, + /** @DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: Kernel module .ko file. */ DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + /** @DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: Kernel module .ko.gz file. */ DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP, + /** @DSO_BINARY_TYPE__KCORE: /proc/kcore file. */ DSO_BINARY_TYPE__KCORE, + /** @DSO_BINARY_TYPE__GUEST_KCORE: Guest /proc/kcore file. */ DSO_BINARY_TYPE__GUEST_KCORE, + /** + * @DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: Openembedded/Yocto -dbg + * package debug info. + */ DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + /** @DSO_BINARY_TYPE__BPF_PROG_INFO: jitted BPF code. */ DSO_BINARY_TYPE__BPF_PROG_INFO, + /** @DSO_BINARY_TYPE__BPF_IMAGE: jitted BPF trampoline or dispatcher code. */ DSO_BINARY_TYPE__BPF_IMAGE, + /** + * @DSO_BINARY_TYPE__OOL: out of line code such as kprobe-replaced + * instructions or optimized kprobes or ftrace trampolines. + */ DSO_BINARY_TYPE__OOL, + /** @DSO_BINARY_TYPE__NOT_FOUND: Unknown DSO kind. */ DSO_BINARY_TYPE__NOT_FOUND, }; @@ -154,10 +212,12 @@ struct dso_data { int status; u32 status_seen; u64 file_size; +#ifdef HAVE_LIBUNWIND_SUPPORT u64 elf_base_addr; u64 debug_frame_offset; u64 eh_frame_hdr_addr; u64 eh_frame_hdr_offset; +#endif }; struct dso_bpf_prog { @@ -231,6 +291,8 @@ DECLARE_RC_STRUCT(dso) { char name[]; }; +extern struct mutex _dso__data_open_lock; + /* dso__for_each_symbol - iterate over the symbols of given type * * @dso: the 'struct dso *' in which symbols are iterated @@ -652,7 +714,7 @@ void __dso__inject_id(struct dso *dso, const struct dso_id *id); int dso__name_len(const struct dso *dso); struct dso *dso__get(struct dso *dso); -void dso__put(struct dso *dso); +void dso__put(struct dso *dso) LOCKS_EXCLUDED(_dso__data_open_lock); static inline void __dso__zput(struct dso **dso) { @@ -675,6 +737,8 @@ bool dso__sorted_by_name(const struct dso *dso); void dso__set_sorted_by_name(struct dso *dso); void dso__sort_by_name(struct dso *dso); +int dso__swap_init(struct dso *dso, unsigned char eidata); + void dso__set_build_id(struct dso *dso, struct build_id *bid); bool dso__build_id_equal(const struct dso *dso, struct build_id *bid); void dso__read_running_kernel_build_id(struct dso *dso, @@ -732,8 +796,8 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, * The current usage of the dso__data_* interface is as follows: * * Get DSO's fd: - * int fd = dso__data_get_fd(dso, machine); - * if (fd >= 0) { + * int fd; + * if (dso__data_get_fd(dso, machine, &fd)) { * USE 'fd' SOMEHOW * dso__data_put_fd(dso); * } @@ -755,14 +819,16 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, * * TODO */ -int dso__data_get_fd(struct dso *dso, struct machine *machine); -void dso__data_put_fd(struct dso *dso); -void dso__data_close(struct dso *dso); +bool dso__data_get_fd(struct dso *dso, struct machine *machine, int *fd) + EXCLUSIVE_TRYLOCK_FUNCTION(true, _dso__data_open_lock); +void dso__data_put_fd(struct dso *dso) UNLOCK_FUNCTION(_dso__data_open_lock); +void dso__data_close(struct dso *dso) LOCKS_EXCLUDED(_dso__data_open_lock); int dso__data_file_size(struct dso *dso, struct machine *machine); off_t dso__data_size(struct dso *dso, struct machine *machine); ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine, u64 offset, u8 *data, ssize_t size); +uint16_t dso__e_machine(struct dso *dso, struct machine *machine); ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size); @@ -808,7 +874,9 @@ static inline bool dso__is_kcore(const struct dso *dso) static inline bool dso__is_kallsyms(const struct dso *dso) { - return RC_CHK_ACCESS(dso)->kernel && RC_CHK_ACCESS(dso)->long_name[0] != '/'; + enum dso_binary_type bt = dso__binary_type(dso); + + return bt == DSO_BINARY_TYPE__KALLSYMS || bt == DSO_BINARY_TYPE__GUEST_KALLSYMS; } bool dso__is_object_file(const struct dso *dso); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index cae4f6d63318..36411749e007 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -543,7 +543,7 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu) for (i = 0; i < env->nr_numa_nodes; i++) { nn = &env->numa_nodes[i]; - nr = max(nr, perf_cpu_map__max(nn->map).cpu); + nr = max(nr, (int)perf_cpu_map__max(nn->map).cpu); } nr++; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index aac96d5d1917..c23b77f8f854 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -767,6 +767,17 @@ int machine__resolve(struct machine *machine, struct addr_location *al, al->socket = env->cpu[al->cpu].socket_id; } + /* Account for possible out-of-order switch events. */ + al->parallelism = max(1, min(machine->parallelism, machine__nr_cpus_avail(machine))); + if (test_bit(al->parallelism, symbol_conf.parallelism_filter)) + al->filtered |= (1 << HIST_FILTER__PARALLELISM); + /* + * Multiply it by some const to avoid precision loss or dealing + * with floats. The multiplier does not matter otherwise since + * we only print it as percents. + */ + al->latency = sample->period * 1000 / al->parallelism; + if (al->map) { if (symbol_conf.dso_list && (!dso || !(strlist__has_entry(symbol_conf.dso_list, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 2744c54f404e..664bf39567ce 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -67,9 +67,15 @@ enum { PERF_IP_FLAG_INTR_DISABLE = 1ULL << 13, PERF_IP_FLAG_INTR_TOGGLE = 1ULL << 14, PERF_IP_FLAG_BRANCH_MISS = 1ULL << 15, + PERF_IP_FLAG_NOT_TAKEN = 1ULL << 16, }; -#define PERF_IP_FLAG_CHARS "bcrosyiABExghDt" +#define PERF_IP_FLAG_CHARS "bcrosyiABExghDtmn" + +#define PERF_ADDITIONAL_STATE_MASK \ + (PERF_IP_FLAG_IN_TX | \ + PERF_IP_FLAG_INTR_DISABLE | \ + PERF_IP_FLAG_INTR_TOGGLE) #define PERF_BRANCH_MASK (\ PERF_IP_FLAG_BRANCH |\ @@ -85,6 +91,10 @@ enum { PERF_IP_FLAG_VMENTRY |\ PERF_IP_FLAG_VMEXIT) +#define PERF_IP_FLAG_BRANCH_EVENT_MASK \ + (PERF_IP_FLAG_BRANCH_MISS | \ + PERF_IP_FLAG_NOT_TAKEN) + #define PERF_MEM_DATA_SRC_NONE \ (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ diff --git a/tools/perf/util/events_stats.h b/tools/perf/util/events_stats.h index eabd7913c309..dcff697ed252 100644 --- a/tools/perf/util/events_stats.h +++ b/tools/perf/util/events_stats.h @@ -57,6 +57,8 @@ struct events_stats { struct hists_stats { u64 total_period; u64 total_non_filtered_period; + u64 total_latency; + u64 total_non_filtered_latency; u32 nr_samples; u32 nr_non_filtered_samples; u32 nr_lost_samples; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f0dd174e2deb..c1a04141aed0 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1373,19 +1373,18 @@ static int evlist__create_syswide_maps(struct evlist *evlist) */ cpus = perf_cpu_map__new_online_cpus(); if (!cpus) - goto out; + return -ENOMEM; threads = perf_thread_map__new_dummy(); - if (!threads) - goto out_put; + if (!threads) { + perf_cpu_map__put(cpus); + return -ENOMEM; + } perf_evlist__set_maps(&evlist->core, cpus, threads); - perf_thread_map__put(threads); -out_put: perf_cpu_map__put(cpus); -out: - return -ENOMEM; + return 0; } int evlist__open(struct evlist *evlist) @@ -2535,10 +2534,10 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis return; evlist__for_each_entry(evlist, pos) { - struct perf_cpu_map *intersect, *to_test; + struct perf_cpu_map *intersect, *to_test, *online = cpu_map__online(); const struct perf_pmu *pmu = evsel__find_pmu(pos); - to_test = pmu && pmu->is_core ? pmu->cpus : cpu_map__online(); + to_test = pmu && pmu->is_core ? pmu->cpus : online; intersect = perf_cpu_map__intersect(to_test, user_requested_cpus); if (!perf_cpu_map__equal(intersect, user_requested_cpus)) { char buf[128]; @@ -2548,6 +2547,7 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis cpu_list, pmu ? pmu->name : "cpu", buf, evsel__name(pos)); } perf_cpu_map__put(intersect); + perf_cpu_map__put(online); } perf_cpu_map__put(user_requested_cpus); } @@ -2594,3 +2594,17 @@ bool evlist__has_bpf_output(struct evlist *evlist) return false; } + +bool evlist__needs_bpf_sb_event(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_dummy_event(evsel)) + continue; + if (!evsel->core.attr.exclude_kernel) + return true; + } + + return false; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index adddb1db1ad2..edcbf1c10e92 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -435,5 +435,6 @@ void evlist__check_mem_load_aux(struct evlist *evlist); void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list); void evlist__uniquify_name(struct evlist *evlist); bool evlist__has_bpf_output(struct evlist *evlist); +bool evlist__needs_bpf_sb_event(struct evlist *evlist); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index bc144388f892..1974395492d7 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -237,6 +237,16 @@ set_methods: return 0; } +const char *evsel__pmu_name(const struct evsel *evsel) +{ + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu) + return pmu->name; + + return event_type(evsel->core.attr.type); +} + #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) int __evsel__sample_size(u64 sample_type) @@ -511,6 +521,16 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) } evsel->cgrp = cgroup__get(orig->cgrp); #ifdef HAVE_LIBTRACEEVENT + if (orig->tp_sys) { + evsel->tp_sys = strdup(orig->tp_sys); + if (evsel->tp_sys == NULL) + goto out_err; + } + if (orig->tp_name) { + evsel->tp_name = strdup(orig->tp_name); + if (evsel->tp_name == NULL) + goto out_err; + } evsel->tp_format = orig->tp_format; #endif evsel->handler = orig->handler; @@ -634,7 +654,11 @@ struct tep_event *evsel__tp_format(struct evsel *evsel) if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return NULL; - tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + if (!evsel->tp_sys) + tp_format = trace_event__tp_format_id(evsel->core.attr.config); + else + tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + if (IS_ERR(tp_format)) { int err = -PTR_ERR(evsel->tp_format); @@ -3164,17 +3188,19 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_REGS_USER) { + struct regs_dump *regs = perf_sample__user_regs(data); + OVERFLOW_CHECK_u64(array); - data->user_regs.abi = *array; + regs->abi = *array; array++; - if (data->user_regs.abi) { + if (regs->abi) { u64 mask = evsel->core.attr.sample_regs_user; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); - data->user_regs.mask = mask; - data->user_regs.regs = (u64 *)array; + regs->mask = mask; + regs->regs = (u64 *)array; array = (void *)array + sz; } } @@ -3218,19 +3244,20 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } - data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE; if (type & PERF_SAMPLE_REGS_INTR) { + struct regs_dump *regs = perf_sample__intr_regs(data); + OVERFLOW_CHECK_u64(array); - data->intr_regs.abi = *array; + regs->abi = *array; array++; - if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { + if (regs->abi != PERF_SAMPLE_REGS_ABI_NONE) { u64 mask = evsel->core.attr.sample_regs_intr; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); - data->intr_regs.mask = mask; - data->intr_regs.regs = (u64 *)array; + regs->mask = mask; + regs->regs = (u64 *)array; array = (void *)array + sz; } } @@ -3856,10 +3883,10 @@ void evsel__zero_per_pkg(struct evsel *evsel) */ bool evsel__is_hybrid(const struct evsel *evsel) { - if (perf_pmus__num_core_pmus() == 1) + if (!evsel->core.is_pmu_core) return false; - return evsel->core.is_pmu_core; + return perf_pmus__num_core_pmus() > 1; } struct evsel *evsel__leader(const struct evsel *evsel) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 5e789fa80590..aae431d63d64 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -119,6 +119,7 @@ struct evsel { bool errored; bool needs_auxtrace_mmap; bool default_metricgroup; /* A member of the Default metricgroup */ + bool needs_uniquify; struct hashmap *per_pkg_mask; int err; int script_output_type; @@ -236,6 +237,7 @@ int evsel__object_config(size_t object_size, void (*fini)(struct evsel *evsel)); struct perf_pmu *evsel__find_pmu(const struct evsel *evsel); +const char *evsel__pmu_name(const struct evsel *evsel); bool evsel__is_aux_event(const struct evsel *evsel); struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx); diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index c221dcce6666..6413537442aa 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -215,6 +215,8 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data) { + if (!ctx || !id) + return -1; return hashmap__find(ctx->ids, id, data) ? 0 : -1; } diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h index 5dee2caba0fe..a9bc47da83a5 100644 --- a/tools/perf/util/ftrace.h +++ b/tools/perf/util/ftrace.h @@ -24,6 +24,8 @@ struct perf_ftrace { unsigned int bucket_range; unsigned int min_latency; unsigned int max_latency; + unsigned int bucket_num; + bool hide_empty; int graph_depth; int func_stack_trace; int func_irq_info; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d06aa86352d3..e3cdc3b7b4ab 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -44,6 +44,7 @@ #include "build-id.h" #include "data.h" #include <api/fs/fs.h> +#include <api/io_dir.h> #include "asm/bug.h" #include "tool.h" #include "time-utils.h" @@ -1311,11 +1312,11 @@ static int memory_node__read(struct memory_node *n, unsigned long idx) { unsigned int phys, size = 0; char path[PATH_MAX]; - struct dirent *ent; - DIR *dir; + struct io_dirent64 *ent; + struct io_dir dir; #define for_each_memory(mem, dir) \ - while ((ent = readdir(dir))) \ + while ((ent = io_dir__readdir(&dir)) != NULL) \ if (strcmp(ent->d_name, ".") && \ strcmp(ent->d_name, "..") && \ sscanf(ent->d_name, "memory%u", &mem) == 1) @@ -1324,9 +1325,9 @@ static int memory_node__read(struct memory_node *n, unsigned long idx) "%s/devices/system/node/node%lu", sysfs__mountpoint(), idx); - dir = opendir(path); - if (!dir) { - pr_warning("failed: can't open memory sysfs data\n"); + io_dir__init(&dir, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (dir.dirfd < 0) { + pr_warning("failed: can't open memory sysfs data '%s'\n", path); return -1; } @@ -1338,20 +1339,20 @@ static int memory_node__read(struct memory_node *n, unsigned long idx) n->set = bitmap_zalloc(size); if (!n->set) { - closedir(dir); + close(dir.dirfd); return -ENOMEM; } n->node = idx; n->size = size; - rewinddir(dir); + io_dir__rewinddir(&dir); for_each_memory(phys, dir) { __set_bit(phys, n->set); } - closedir(dir); + close(dir.dirfd); return 0; } @@ -1374,8 +1375,8 @@ static int memory_node__sort(const void *a, const void *b) static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) { char path[PATH_MAX]; - struct dirent *ent; - DIR *dir; + struct io_dirent64 *ent; + struct io_dir dir; int ret = 0; size_t cnt = 0, size = 0; struct memory_node *nodes = NULL; @@ -1383,14 +1384,14 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) scnprintf(path, PATH_MAX, "%s/devices/system/node/", sysfs__mountpoint()); - dir = opendir(path); - if (!dir) { + io_dir__init(&dir, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (dir.dirfd < 0) { pr_debug2("%s: couldn't read %s, does this arch have topology information?\n", __func__, path); return -1; } - while (!ret && (ent = readdir(dir))) { + while (!ret && (ent = io_dir__readdir(&dir))) { unsigned int idx; int r; @@ -1419,7 +1420,7 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) cnt += 1; } out: - closedir(dir); + close(dir.dirfd); if (!ret) { *cntp = cnt; *nodesp = nodes; @@ -2769,6 +2770,8 @@ static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) free(name); pmu_num--; } + /* AMD may set it by evlist__has_amd_ibs() from perf_session__new() */ + free(ff->ph->env.pmu_mappings); ff->ph->env.pmu_mappings = strbuf_detach(&sb, NULL); return 0; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0f30f843c566..d65228c11412 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -43,6 +43,8 @@ static bool hists__filter_entry_by_symbol(struct hists *hists, struct hist_entry *he); static bool hists__filter_entry_by_socket(struct hists *hists, struct hist_entry *he); +static bool hists__filter_entry_by_parallelism(struct hists *hists, + struct hist_entry *he); u16 hists__col_len(struct hists *hists, enum hist_column col) { @@ -207,6 +209,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_CGROUP, 6); hists__new_col_len(hists, HISTC_CGROUP_ID, 20); + hists__new_col_len(hists, HISTC_PARALLELISM, 11); hists__new_col_len(hists, HISTC_CPU, 3); hists__new_col_len(hists, HISTC_SOCKET, 6); hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); @@ -302,9 +305,10 @@ static long hist_time(unsigned long htime) return htime; } -static void he_stat__add_period(struct he_stat *he_stat, u64 period) +static void he_stat__add_period(struct he_stat *he_stat, u64 period, u64 latency) { he_stat->period += period; + he_stat->latency += latency; he_stat->nr_events += 1; } @@ -319,6 +323,7 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->weight2 += src->weight2; dest->weight3 += src->weight3; dest->nr_events += src->nr_events; + dest->latency += src->latency; } static void he_stat__decay(struct he_stat *he_stat) @@ -328,6 +333,7 @@ static void he_stat__decay(struct he_stat *he_stat) he_stat->weight1 = (he_stat->weight1 * 7) / 8; he_stat->weight2 = (he_stat->weight2 * 7) / 8; he_stat->weight3 = (he_stat->weight3 * 7) / 8; + he_stat->latency = (he_stat->latency * 7) / 8; } static void hists__delete_entry(struct hists *hists, struct hist_entry *he); @@ -335,7 +341,7 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he); static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) { u64 prev_period = he->stat.period; - u64 diff; + u64 prev_latency = he->stat.latency; if (prev_period == 0) return true; @@ -345,12 +351,16 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) he_stat__decay(he->stat_acc); decay_callchain(he->callchain); - diff = prev_period - he->stat.period; - if (!he->depth) { - hists->stats.total_period -= diff; - if (!he->filtered) - hists->stats.total_non_filtered_period -= diff; + u64 period_diff = prev_period - he->stat.period; + u64 latency_diff = prev_latency - he->stat.latency; + + hists->stats.total_period -= period_diff; + hists->stats.total_latency -= latency_diff; + if (!he->filtered) { + hists->stats.total_non_filtered_period -= period_diff; + hists->stats.total_non_filtered_latency -= latency_diff; + } } if (!he->leaf) { @@ -365,7 +375,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) } } - return he->stat.period == 0; + return he->stat.period == 0 && he->stat.latency == 0; } static void hists__delete_entry(struct hists *hists, struct hist_entry *he) @@ -584,21 +594,24 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, return he; } -static u8 symbol__parent_filter(const struct symbol *parent) +static filter_mask_t symbol__parent_filter(const struct symbol *parent) { if (symbol_conf.exclude_other && parent == NULL) return 1 << HIST_FILTER__PARENT; return 0; } -static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period) +static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period, u64 latency) { if (!hist_entry__has_callchains(he) || !symbol_conf.use_callchain) return; he->hists->callchain_period += period; - if (!he->filtered) + he->hists->callchain_latency += latency; + if (!he->filtered) { he->hists->callchain_non_filtered_period += period; + he->hists->callchain_non_filtered_latency += latency; + } } static struct hist_entry *hists__findnew_entry(struct hists *hists, @@ -611,6 +624,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, struct hist_entry *he; int64_t cmp; u64 period = entry->stat.period; + u64 latency = entry->stat.latency; bool leftmost = true; p = &hists->entries_in->rb_root.rb_node; @@ -629,10 +643,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (!cmp) { if (sample_self) { he_stat__add_stat(&he->stat, &entry->stat); - hist_entry__add_callchain_period(he, period); + hist_entry__add_callchain_period(he, period, latency); } if (symbol_conf.cumulate_callchain) - he_stat__add_period(he->stat_acc, period); + he_stat__add_period(he->stat_acc, period, latency); block_info__delete(entry->block_info); @@ -669,7 +683,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, return NULL; if (sample_self) - hist_entry__add_callchain_period(he, period); + hist_entry__add_callchain_period(he, period, latency); hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); @@ -741,12 +755,14 @@ __hists__add_entry(struct hists *hists, .ip = al->addr, .level = al->level, .code_page_size = sample->code_page_size, + .parallelism = al->parallelism, .stat = { .nr_events = 1, .period = sample->period, .weight1 = sample->weight, .weight2 = sample->ins_lat, .weight3 = sample->p_stage_cyc, + .latency = al->latency, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent) | al->filtered, @@ -975,8 +991,6 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a if (he == NULL) return -ENOMEM; - hists__inc_nr_samples(hists, he->filtered); - out: iter->he = he; iter->curr++; @@ -995,9 +1009,15 @@ static int iter_finish_branch_entry(struct hist_entry_iter *iter, struct addr_location *al __maybe_unused) { + struct evsel *evsel = iter->evsel; + struct hists *hists = evsel__hists(evsel); + for (int i = 0; i < iter->total; i++) branch_info__exit(&iter->bi[i]); + if (iter->he) + hists__inc_nr_samples(hists, iter->he->filtered); + zfree(&iter->bi); iter->he = NULL; @@ -1365,6 +1385,16 @@ void hist_entry__delete(struct hist_entry *he) { struct hist_entry_ops *ops = he->ops; + if (symbol_conf.report_hierarchy) { + struct rb_root *root = &he->hroot_out.rb_root; + struct hist_entry *child, *tmp; + + rbtree_postorder_for_each_entry_safe(child, tmp, root, rb_node) + hist_entry__delete(child); + + *root = RB_ROOT; + } + thread__zput(he->thread); map_symbol__exit(&he->ms); @@ -1455,6 +1485,10 @@ static void hist_entry__check_and_remove_filter(struct hist_entry *he, if (symbol_conf.sym_list == NULL) return; break; + case HIST_FILTER__PARALLELISM: + if (__bitmap_weight(symbol_conf.parallelism_filter, MAX_NR_CPUS + 1) == 0) + return; + break; case HIST_FILTER__PARENT: case HIST_FILTER__GUEST: case HIST_FILTER__HOST: @@ -1513,6 +1547,9 @@ static void hist_entry__apply_hierarchy_filters(struct hist_entry *he) hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL, perf_hpp__is_sym_entry); + hist_entry__check_and_remove_filter(he, HIST_FILTER__PARALLELISM, + perf_hpp__is_parallelism_entry); + hists__apply_filters(he->hists, he); } @@ -1709,6 +1746,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he) hists__filter_entry_by_thread(hists, he); hists__filter_entry_by_symbol(hists, he); hists__filter_entry_by_socket(hists, he); + hists__filter_entry_by_parallelism(hists, he); } int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) @@ -1756,12 +1794,14 @@ static void hists__reset_filter_stats(struct hists *hists) { hists->nr_non_filtered_entries = 0; hists->stats.total_non_filtered_period = 0; + hists->stats.total_non_filtered_latency = 0; } void hists__reset_stats(struct hists *hists) { hists->nr_entries = 0; hists->stats.total_period = 0; + hists->stats.total_latency = 0; hists__reset_filter_stats(hists); } @@ -1770,6 +1810,7 @@ static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h) { hists->nr_non_filtered_entries++; hists->stats.total_non_filtered_period += h->stat.period; + hists->stats.total_non_filtered_latency += h->stat.latency; } void hists__inc_stats(struct hists *hists, struct hist_entry *h) @@ -1779,6 +1820,7 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h) hists->nr_entries++; hists->stats.total_period += h->stat.period; + hists->stats.total_latency += h->stat.latency; } static void hierarchy_recalc_total_periods(struct hists *hists) @@ -1790,6 +1832,8 @@ static void hierarchy_recalc_total_periods(struct hists *hists) hists->stats.total_period = 0; hists->stats.total_non_filtered_period = 0; + hists->stats.total_latency = 0; + hists->stats.total_non_filtered_latency = 0; /* * recalculate total period using top-level entries only @@ -1801,8 +1845,11 @@ static void hierarchy_recalc_total_periods(struct hists *hists) node = rb_next(node); hists->stats.total_period += he->stat.period; - if (!he->filtered) + hists->stats.total_latency += he->stat.latency; + if (!he->filtered) { hists->stats.total_non_filtered_period += he->stat.period; + hists->stats.total_non_filtered_latency += he->stat.latency; + } } } @@ -2195,6 +2242,16 @@ static bool hists__filter_entry_by_socket(struct hists *hists, return false; } +static bool hists__filter_entry_by_parallelism(struct hists *hists, + struct hist_entry *he) +{ + if (test_bit(he->parallelism, hists->parallelism_filter)) { + he->filtered |= (1 << HIST_FILTER__PARALLELISM); + return true; + } + return false; +} + typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he); static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter) @@ -2364,6 +2421,16 @@ void hists__filter_by_socket(struct hists *hists) hists__filter_entry_by_socket); } +void hists__filter_by_parallelism(struct hists *hists) +{ + if (symbol_conf.report_hierarchy) + hists__filter_hierarchy(hists, HIST_FILTER__PARALLELISM, + hists->parallelism_filter); + else + hists__filter_by_type(hists, HIST_FILTER__PARALLELISM, + hists__filter_entry_by_parallelism); +} + void events_stats__inc(struct events_stats *stats, u32 type) { ++stats->nr_events[0]; @@ -2759,6 +2826,12 @@ u64 hists__total_period(struct hists *hists) hists->stats.total_period; } +u64 hists__total_latency(struct hists *hists) +{ + return symbol_conf.filter_relative ? hists->stats.total_non_filtered_latency : + hists->stats.total_latency; +} + int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq) { char unit; @@ -2870,6 +2943,7 @@ int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list) hists->entries = RB_ROOT_CACHED; mutex_init(&hists->lock); hists->socket_filter = -1; + hists->parallelism_filter = symbol_conf.parallelism_filter; hists->hpp_list = hpp_list; INIT_LIST_HEAD(&hists->hpp_formats); return 0; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 46c8373e3146..317d06cca8b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -31,8 +31,11 @@ enum hist_filter { HIST_FILTER__HOST, HIST_FILTER__SOCKET, HIST_FILTER__C2C, + HIST_FILTER__PARALLELISM, }; +typedef u16 filter_mask_t; + enum hist_column { HISTC_SYMBOL, HISTC_TIME, @@ -42,6 +45,7 @@ enum hist_column { HISTC_CGROUP_ID, HISTC_CGROUP, HISTC_PARENT, + HISTC_PARALLELISM, HISTC_CPU, HISTC_SOCKET, HISTC_SRCLINE, @@ -105,10 +109,13 @@ struct hists { u64 nr_non_filtered_entries; u64 callchain_period; u64 callchain_non_filtered_period; + u64 callchain_latency; + u64 callchain_non_filtered_latency; struct thread *thread_filter; const struct dso *dso_filter; const char *uid_filter_str; const char *symbol_filter_str; + unsigned long *parallelism_filter; struct mutex lock; struct hists_stats stats; u64 event_stream; @@ -165,6 +172,12 @@ struct res_sample { struct he_stat { u64 period; + /* + * Period re-scaled from CPU time to wall-clock time (divided by the + * parallelism at the time of the sample). This represents effect of + * the event on latency rather than CPU consumption. + */ + u64 latency; u64 period_sys; u64 period_us; u64 period_guest_sys; @@ -226,15 +239,16 @@ struct hist_entry { u64 cgroup; u64 ip; u64 transaction; - s32 socket; - s32 cpu; u64 code_page_size; u64 weight; u64 ins_lat; u64 p_stage_cyc; + s32 socket; + s32 cpu; + int parallelism; + int mem_type_off; u8 cpumode; u8 depth; - int mem_type_off; struct simd_flags simd_flags; /* We are added by hists__add_dummy_entry. */ @@ -242,7 +256,7 @@ struct hist_entry { bool leaf; char level; - u8 filtered; + filter_mask_t filtered; u16 callchain_size; union { @@ -368,6 +382,7 @@ void hists__output_recalc_col_len(struct hists *hists, int max_rows); struct hist_entry *hists__get_entry(struct hists *hists, int idx); u64 hists__total_period(struct hists *hists); +u64 hists__total_latency(struct hists *hists); void hists__reset_stats(struct hists *hists); void hists__inc_stats(struct hists *hists, struct hist_entry *h); void hists__inc_nr_events(struct hists *hists); @@ -384,11 +399,13 @@ void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); void hists__filter_by_symbol(struct hists *hists); void hists__filter_by_socket(struct hists *hists); +void hists__filter_by_parallelism(struct hists *hists); static inline bool hists__has_filter(struct hists *hists) { return hists->thread_filter || hists->dso_filter || - hists->symbol_filter_str || (hists->socket_filter > -1); + hists->symbol_filter_str || (hists->socket_filter > -1) || + hists->parallelism_filter; } u16 hists__col_len(struct hists *hists, enum hist_column col); @@ -547,11 +564,13 @@ extern struct perf_hpp_fmt perf_hpp__format[]; enum { /* Matches perf_hpp__format array. */ PERF_HPP__OVERHEAD, + PERF_HPP__LATENCY, PERF_HPP__OVERHEAD_SYS, PERF_HPP__OVERHEAD_US, PERF_HPP__OVERHEAD_GUEST_SYS, PERF_HPP__OVERHEAD_GUEST_US, PERF_HPP__OVERHEAD_ACC, + PERF_HPP__LATENCY_ACC, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, PERF_HPP__WEIGHT1, @@ -563,6 +582,7 @@ enum { void perf_hpp__init(void); void perf_hpp__cancel_cumulate(void); +void perf_hpp__cancel_latency(void); void perf_hpp__setup_output_field(struct perf_hpp_list *list); void perf_hpp__reset_output_field(struct perf_hpp_list *list); void perf_hpp__append_sort_keys(struct perf_hpp_list *list); @@ -580,6 +600,7 @@ bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt); bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt); +bool perf_hpp__is_parallelism_entry(struct perf_hpp_fmt *fmt); struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt); @@ -606,6 +627,7 @@ void hists__reset_column_width(struct hists *hists); enum perf_hpp_fmt_type { PERF_HPP_FMT_TYPE__RAW, PERF_HPP_FMT_TYPE__PERCENT, + PERF_HPP_FMT_TYPE__LATENCY, PERF_HPP_FMT_TYPE__AVERAGE, }; diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c index 4acb9bb19b84..3cce77fc8004 100644 --- a/tools/perf/util/hwmon_pmu.c +++ b/tools/perf/util/hwmon_pmu.c @@ -11,13 +11,13 @@ #include <sys/types.h> #include <assert.h> #include <ctype.h> -#include <dirent.h> #include <fcntl.h> #include <stddef.h> #include <stdlib.h> #include <string.h> #include <api/fs/fs.h> #include <api/io.h> +#include <api/io_dir.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/zalloc.h> @@ -108,20 +108,6 @@ struct hwmon_pmu { }; /** - * union hwmon_pmu_event_key: Key for hwmon_pmu->events as such each key - * represents an event. - * - * Related hwmon files start <type><number> that this key represents. - */ -union hwmon_pmu_event_key { - long type_and_num; - struct { - int num :16; - enum hwmon_type type :8; - }; -}; - -/** * struct hwmon_pmu_event_value: Value in hwmon_pmu->events. * * Hwmon files are of the form <type><number>_<item> and may have a suffix @@ -249,31 +235,22 @@ static void fix_name(char *p) static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) { - DIR *dir; - struct dirent *ent; - int dup_fd, err = 0; + int err = 0; struct hashmap_entry *cur, *tmp; size_t bkt; + struct io_dirent64 *ent; + struct io_dir dir; if (pmu->pmu.sysfs_aliases_loaded) return 0; - /* - * Use a dup-ed fd as closedir will close it. Use openat so that the - * directory contents are refreshed. - */ - dup_fd = openat(pmu->hwmon_dir_fd, ".", O_DIRECTORY); - - if (dup_fd == -1) - return -ENOMEM; + /* Use openat so that the directory contents are refreshed. */ + io_dir__init(&dir, openat(pmu->hwmon_dir_fd, ".", O_CLOEXEC | O_DIRECTORY | O_RDONLY)); - dir = fdopendir(dup_fd); - if (!dir) { - close(dup_fd); - return -ENOMEM; - } + if (dir.dirfd < 0) + return -ENOENT; - while ((ent = readdir(dir)) != NULL) { + while ((ent = io_dir__readdir(&dir)) != NULL) { enum hwmon_type type; int number; enum hwmon_item item; @@ -361,7 +338,7 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) pmu->pmu.sysfs_aliases_loaded = true; err_out: - closedir(dir); + close(dir.dirfd); return err; } @@ -716,8 +693,8 @@ int hwmon_pmu__check_alias(struct parse_events_terms *terms, struct perf_pmu_inf int perf_pmus__read_hwmon_pmus(struct list_head *pmus) { char *line = NULL; - DIR *class_hwmon_dir; - struct dirent *class_hwmon_ent; + struct io_dirent64 *class_hwmon_ent; + struct io_dir class_hwmon_dir; char buf[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); @@ -725,11 +702,12 @@ int perf_pmus__read_hwmon_pmus(struct list_head *pmus) return 0; scnprintf(buf, sizeof(buf), "%s/class/hwmon/", sysfs); - class_hwmon_dir = opendir(buf); - if (!class_hwmon_dir) + io_dir__init(&class_hwmon_dir, open(buf, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + + if (class_hwmon_dir.dirfd < 0) return 0; - while ((class_hwmon_ent = readdir(class_hwmon_dir)) != NULL) { + while ((class_hwmon_ent = io_dir__readdir(&class_hwmon_dir)) != NULL) { size_t line_len; int hwmon_dir, name_fd; struct io io; @@ -759,7 +737,7 @@ int perf_pmus__read_hwmon_pmus(struct list_head *pmus) close(name_fd); } free(line); - closedir(class_hwmon_dir); + close(class_hwmon_dir.dirfd); return 0; } diff --git a/tools/perf/util/hwmon_pmu.h b/tools/perf/util/hwmon_pmu.h index 882566846df4..b3329774d2b2 100644 --- a/tools/perf/util/hwmon_pmu.h +++ b/tools/perf/util/hwmon_pmu.h @@ -91,6 +91,22 @@ enum hwmon_item { HWMON_ITEM__MAX, }; +/** + * union hwmon_pmu_event_key: Key for hwmon_pmu->events as such each key + * represents an event. + * union is exposed for testing to ensure problems are avoided on big + * endian machines. + * + * Related hwmon files start <type><number> that this key represents. + */ +union hwmon_pmu_event_key { + long type_and_num; + struct { + int num :16; + enum hwmon_type type :8; + }; +}; + bool perf_pmu__is_hwmon(const struct perf_pmu *pmu); bool evsel__is_hwmon(const struct evsel *evsel); diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index a7c589fecb98..3625c6224750 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -275,12 +275,13 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, int ret; struct intel_bts *bts = btsq->bts; union perf_event event; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; if (bts->synth_opts.initial_skip && bts->num_events++ <= bts->synth_opts.initial_skip) return 0; + perf_sample__init(&sample, /*all=*/true); sample.ip = le64_to_cpu(branch->from); sample.cpumode = intel_bts_cpumode(bts, sample.ip); sample.pid = btsq->pid; @@ -312,6 +313,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, pr_err("Intel BTS: failed to deliver branch event, error %d\n", ret); + perf_sample__exit(&sample); return ret; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 30be6dfe09eb..4e8a9b172fbc 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1764,12 +1764,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct dummy_branch_stack { u64 nr; u64 hw_idx; struct branch_entry entries; } dummy_bs; + int ret; if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; @@ -1777,6 +1778,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_b_sample(pt, ptq, event, &sample); sample.id = ptq->pt->branches_id; @@ -1806,8 +1808,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt; } - return intel_pt_deliver_synth_event(pt, event, &sample, + perf_sample__exit(&sample); + ret = intel_pt_deliver_synth_event(pt, event, &sample, pt->branches_sample_type); + return ret; } static void intel_pt_prep_sample(struct intel_pt *pt, @@ -1835,11 +1839,13 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_sample(pt, ptq, event, &sample); sample.id = ptq->pt->instructions_id; @@ -1859,16 +1865,19 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) ptq->last_insn_cnt = ptq->state->tot_insn_cnt; - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->instructions_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->instructions_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; u64 period = 0; + int ret; if (ptq->sample_ipc) period = ptq->ipc_cyc_cnt - ptq->last_cy_cyc_cnt; @@ -1876,6 +1885,7 @@ static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq) if (!period || intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_sample(pt, ptq, event, &sample); sample.id = ptq->pt->cycles_id; @@ -1887,25 +1897,31 @@ static int intel_pt_synth_cycle_sample(struct intel_pt_queue *ptq) ptq->last_cy_insn_cnt = ptq->ipc_insn_cnt; ptq->last_cy_cyc_cnt = ptq->ipc_cyc_cnt; - return intel_pt_deliver_synth_event(pt, event, &sample, pt->cycles_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, pt->cycles_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_sample(pt, ptq, event, &sample); sample.id = ptq->pt->transactions_id; sample.stream_id = ptq->pt->transactions_id; - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->transactions_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->transactions_sample_type); + perf_sample__exit(&sample); + return ret; } static void intel_pt_prep_p_sample(struct intel_pt *pt, @@ -1953,15 +1969,17 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_cbr raw; u32 flags; + int ret; if (intel_pt_skip_cbr_event(pt)) return 0; ptq->cbr_seen = ptq->state->cbr; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->cbr_id; @@ -1975,20 +1993,24 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_psb_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_psb raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->psb_id; @@ -2001,20 +2023,24 @@ static int intel_pt_synth_psb_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_mwait raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->mwait_id; @@ -2026,20 +2052,24 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_pwre raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->pwre_id; @@ -2051,20 +2081,24 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_exstop raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->exstop_id; @@ -2076,20 +2110,24 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_pwrx raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->pwrx_id; @@ -2101,8 +2139,10 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->pwr_events_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->pwr_events_sample_type); + perf_sample__exit(&sample); + return ret; } /* @@ -2235,16 +2275,18 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack, static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id) { const struct intel_pt_blk_items *items = &ptq->state->items; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; union perf_event *event = ptq->event_buf; struct intel_pt *pt = ptq->pt; u64 sample_type = evsel->core.attr.sample_type; u8 cpumode; - u64 regs[8 * sizeof(sample.intr_regs.mask)]; + u64 regs[8 * sizeof(sample.intr_regs->mask)]; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_a_sample(ptq, event, &sample); sample.id = id; @@ -2291,15 +2333,16 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse items->mask[INTEL_PT_XMM_POS])) { u64 regs_mask = evsel->core.attr.sample_regs_intr; u64 *pos; + struct regs_dump *intr_regs = perf_sample__intr_regs(&sample); - sample.intr_regs.abi = items->is_32_bit ? + intr_regs->abi = items->is_32_bit ? PERF_SAMPLE_REGS_ABI_32 : PERF_SAMPLE_REGS_ABI_64; - sample.intr_regs.regs = regs; + intr_regs->regs = regs; - pos = intel_pt_add_gp_regs(&sample.intr_regs, regs, items, regs_mask); + pos = intel_pt_add_gp_regs(intr_regs, regs, items, regs_mask); - intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask); + intel_pt_add_xmm(intr_regs, pos, items, regs_mask); } if (sample_type & PERF_SAMPLE_BRANCH_STACK) { @@ -2361,7 +2404,9 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse sample.transaction = txn; } - return intel_pt_deliver_synth_event(pt, event, &sample, sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq) @@ -2407,16 +2452,17 @@ static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct { struct perf_synth_intel_evt cfe; struct perf_synth_intel_evd evd[INTEL_PT_MAX_EVDS]; } raw; - int i; + int i, ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->evt_id; @@ -2438,20 +2484,24 @@ static int intel_pt_synth_events_sample(struct intel_pt_queue *ptq) ptq->state->evd_cnt * sizeof(struct perf_synth_intel_evd); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->evt_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->evt_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; struct perf_synth_intel_iflag_chg raw; + int ret; if (intel_pt_skip_event(pt)) return 0; + perf_sample__init(&sample, /*all=*/true); intel_pt_prep_p_sample(pt, ptq, event, &sample); sample.id = ptq->pt->iflag_chg_id; @@ -2471,8 +2521,10 @@ static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq) sample.raw_size = perf_synth__raw_size(raw); sample.raw_data = perf_synth__raw_data(&raw); - return intel_pt_deliver_synth_event(pt, event, &sample, - pt->iflag_chg_sample_type); + ret = intel_pt_deliver_synth_event(pt, event, &sample, + pt->iflag_chg_sample_type); + perf_sample__exit(&sample); + return ret; } static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, diff --git a/tools/perf/util/intel-tpebs.c b/tools/perf/util/intel-tpebs.c index 50a3c3e07160..2c421b475b3b 100644 --- a/tools/perf/util/intel-tpebs.c +++ b/tools/perf/util/intel-tpebs.c @@ -254,7 +254,7 @@ int tpebs_start(struct evlist *evsel_list) new = zalloc(sizeof(*new)); if (!new) { ret = -1; - zfree(name); + zfree(&name); goto err; } new->name = name; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index f23e21502bf8..624964f01b5f 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -516,7 +516,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) * create pseudo sample to induce dso hit increment * use first address as sample address */ - memset(&sample, 0, sizeof(sample)); + perf_sample__init(&sample, /*all=*/true); sample.cpumode = PERF_RECORD_MISC_USER; sample.pid = pid; sample.tid = tid; @@ -535,6 +535,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine); out: + perf_sample__exit(&sample); free(event); return ret; } @@ -611,7 +612,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) * create pseudo sample to induce dso hit increment * use first address as sample address */ - memset(&sample, 0, sizeof(sample)); + perf_sample__init(&sample, /*all=*/true); sample.cpumode = PERF_RECORD_MISC_USER; sample.pid = pid; sample.tid = tid; @@ -620,12 +621,13 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) ret = perf_event__process_mmap2(tool, event, &sample, jd->machine); if (ret) - return ret; + goto out; ret = jit_inject_event(jd, event); if (!ret) build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine); - +out: + perf_sample__exit(&sample); return ret; } diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index a09f7fe877df..b5d916aa49df 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -168,6 +168,8 @@ int lock_contention_stop(void); int lock_contention_read(struct lock_contention *con); int lock_contention_finish(struct lock_contention *con); +struct lock_stat *pop_owner_stack_trace(struct lock_contention *con); + #else /* !HAVE_BPF_SKEL */ static inline int lock_contention_prepare(struct lock_contention *con __maybe_unused) @@ -187,6 +189,11 @@ static inline int lock_contention_read(struct lock_contention *con __maybe_unuse return 0; } +static inline struct lock_stat *pop_owner_stack_trace(struct lock_contention *con __maybe_unused) +{ + return NULL; +} + #endif /* HAVE_BPF_SKEL */ #endif /* PERF_LOCK_CONTENTION_H */ diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index af9a97612f9d..bbcd2ffcf4bd 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -32,7 +32,7 @@ static const char *lzma_strerror(lzma_ret ret) } } -int lzma_decompress_to_file(const char *input, int output_fd) +int lzma_decompress_stream_to_file(FILE *infile, int output_fd) { lzma_action action = LZMA_RUN; lzma_stream strm = LZMA_STREAM_INIT; @@ -41,18 +41,11 @@ int lzma_decompress_to_file(const char *input, int output_fd) u8 buf_in[BUFSIZE]; u8 buf_out[BUFSIZE]; - FILE *infile; - - infile = fopen(input, "rb"); - if (!infile) { - pr_debug("lzma: fopen failed on %s: '%s'\n", input, strerror(errno)); - return -1; - } ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED); if (ret != LZMA_OK) { pr_debug("lzma: lzma_stream_decoder failed %s (%d)\n", lzma_strerror(ret), ret); - goto err_fclose; + return err; } strm.next_in = NULL; @@ -100,11 +93,25 @@ int lzma_decompress_to_file(const char *input, int output_fd) err = 0; err_lzma_end: lzma_end(&strm); -err_fclose: - fclose(infile); return err; } +int lzma_decompress_to_file(const char *input, int output_fd) +{ + FILE *infile; + int ret; + + infile = fopen(input, "rb"); + if (!infile) { + pr_debug("lzma: fopen failed on %s: '%s'\n", input, strerror(errno)); + return -1; + } + + ret = lzma_decompress_stream_to_file(infile, output_fd); + fclose(infile); + return ret; +} + bool lzma_is_compressed(const char *input) { int fd = open(input, O_RDONLY); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2d51badfbf2e..2531b373f2cf 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -37,6 +37,7 @@ #include <internal/lib.h> // page_size #include "cgroup.h" #include "arm64-frame-pointer-unwind-support.h" +#include <api/io_dir.h> #include <linux/ctype.h> #include <symbol/kallsyms.h> @@ -94,6 +95,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->comm_exec = false; machine->kernel_start = 0; machine->vmlinux_map = NULL; + /* There is no initial context switch in, so we start at 1. */ + machine->parallelism = 1; machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) @@ -677,8 +680,11 @@ int machine__process_aux_output_hw_id_event(struct machine *machine __maybe_unus int machine__process_switch_event(struct machine *machine __maybe_unused, union perf_event *event) { + bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT; + if (dump_trace) perf_event__fprintf_switch(event, stdout); + machine->parallelism += out ? -1 : 1; return 0; } @@ -712,7 +718,7 @@ static int machine__process_ksymbol_register(struct machine *machine, map__set_start(map, event->ksymbol.addr); map__set_end(map, map__start(map) + event->ksymbol.len); - err = maps__insert(machine__kernel_maps(machine), map); + err = maps__fixup_overlap_and_insert(machine__kernel_maps(machine), map); if (err) { err = -ENOMEM; goto out; @@ -773,6 +779,10 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused, if (dump_trace) perf_event__fprintf_ksymbol(event, stdout); + /* no need to process non-JIT BPF as it cannot get samples */ + if (event->ksymbol.len == 0) + return 0; + if (event->ksymbol.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER) return machine__process_ksymbol_unregister(machine, event, sample); @@ -886,26 +896,6 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, return ret; } -size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) -{ - int i; - size_t printed = 0; - struct dso *kdso = machine__kernel_dso(machine); - - if (dso__has_build_id(kdso)) { - char filename[PATH_MAX]; - - if (dso__build_id_filename(kdso, filename, sizeof(filename), false)) - printed += fprintf(fp, "[0] %s\n", filename); - } - - for (i = 0; i < vmlinux_path__nr_entries; ++i) { - printed += fprintf(fp, "[%d] %s\n", i + dso__has_build_id(kdso), - vmlinux_path[i]); - } - return printed; -} - struct machine_fprintf_cb_args { FILE *fp; size_t printed; @@ -1352,27 +1342,24 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo return 0; } -static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, int depth) +static int maps__set_modules_path_dir(struct maps *maps, char *path, size_t path_size, int depth) { - struct dirent *dent; - DIR *dir = opendir(dir_name); + struct io_dirent64 *dent; + struct io_dir iod; + size_t root_len = strlen(path); int ret = 0; - if (!dir) { - pr_debug("%s: cannot open %s dir\n", __func__, dir_name); + io_dir__init(&iod, open(path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (iod.dirfd < 0) { + pr_debug("%s: cannot open %s dir\n", __func__, path); return -1; } - - while ((dent = readdir(dir)) != NULL) { - char path[PATH_MAX]; - struct stat st; - - /*sshfs might return bad dent->d_type, so we have to stat*/ - path__join(path, sizeof(path), dir_name, dent->d_name); - if (stat(path, &st)) - continue; - - if (S_ISDIR(st.st_mode)) { + /* Bounds check, should never happen. */ + if (root_len >= path_size) + return -1; + path[root_len++] = '/'; + while ((dent = io_dir__readdir(&iod)) != NULL) { + if (io_dir__is_dir(&iod, dent)) { if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) continue; @@ -1384,7 +1371,12 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i continue; } - ret = maps__set_modules_path_dir(maps, path, depth + 1); + /* Bounds check, should never happen. */ + if (root_len + strlen(dent->d_name) >= path_size) + continue; + + strcpy(path + root_len, dent->d_name); + ret = maps__set_modules_path_dir(maps, path, path_size, depth + 1); if (ret < 0) goto out; } else { @@ -1394,9 +1386,14 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i if (ret) goto out; - if (m.kmod) - ret = maps__set_module_path(maps, path, &m); + if (m.kmod) { + /* Bounds check, should never happen. */ + if (root_len + strlen(dent->d_name) < path_size) { + strcpy(path + root_len, dent->d_name); + ret = maps__set_module_path(maps, path, &m); + } + } zfree(&m.name); if (ret) @@ -1405,7 +1402,7 @@ static int maps__set_modules_path_dir(struct maps *maps, const char *dir_name, i } out: - closedir(dir); + close(iod.dirfd); return ret; } @@ -1422,7 +1419,8 @@ static int machine__set_modules_path(struct machine *machine) machine->root_dir, version); free(version); - return maps__set_modules_path_dir(machine__kernel_maps(machine), modules_path, 0); + return maps__set_modules_path_dir(machine__kernel_maps(machine), + modules_path, sizeof(modules_path), 0); } int __weak arch__fix_module_text_start(u64 *start __maybe_unused, u64 *size __maybe_unused, @@ -1468,8 +1466,6 @@ static int machine__create_modules(struct machine *machine) if (modules__parse(modules, machine, machine__create_module)) return -1; - maps__fixup_end(machine__kernel_maps(machine)); - if (!machine__set_modules_path(machine)) return 0; @@ -1563,6 +1559,8 @@ int machine__create_kernel_maps(struct machine *machine) } } + maps__fixup_end(machine__kernel_maps(machine)); + out_put: dso__put(kernel); return ret; @@ -1900,6 +1898,8 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event if (dump_trace) perf_event__fprintf_task(event, stdout); + /* There is no context switch out before exit, so we decrement here. */ + machine->parallelism--; if (thread != NULL) { if (symbol_conf.keep_exited_threads) thread__set_exited(thread, /*exited=*/true); @@ -2929,8 +2929,8 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; /* Bail out if nothing was captured. */ - if ((!sample->user_regs.regs) || - (!sample->user_stack.size)) + if (!sample->user_regs || !sample->user_regs->regs || + !sample->user_stack.size) return 0; if (!symbols) diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 2e5a4cb342d8..b56abec84fed 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -50,6 +50,12 @@ struct machine { u64 text_start; u64 text_end; } sched, lock, traceiter, trace; + /* + * The current parallelism level (number of threads that run on CPUs). + * This value can be less than 1, or larger than the total number + * of CPUs, if events are poorly ordered. + */ + int parallelism; pid_t *current_tid; size_t current_tid_sz; union { /* Tool specific area */ @@ -266,8 +272,6 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid); int machines__create_guest_kernel_maps(struct machines *machines); void machines__destroy_kernel_maps(struct machines *machines); -size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); - typedef int (*machine__dso_t)(struct dso *dso, struct machine *machine, void *priv); int machine__for_each_dso(struct machine *machine, machine__dso_t fn, diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 09c9cc326c08..0b40d901675e 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -428,11 +428,29 @@ static unsigned int maps__by_name_index(const struct maps *maps, const struct ma return -1; } +static void map__set_kmap_maps(struct map *map, struct maps *maps) +{ + struct dso *dso; + + if (map == NULL) + return; + + dso = map__dso(map); + + if (dso && dso__kernel(dso)) { + struct kmap *kmap = map__kmap(map); + + if (kmap) + kmap->kmaps = maps; + else + pr_err("Internal error: kernel dso with non kernel map\n"); + } +} + static int __maps__insert(struct maps *maps, struct map *new) { struct map **maps_by_address = maps__maps_by_address(maps); struct map **maps_by_name = maps__maps_by_name(maps); - const struct dso *dso = map__dso(new); unsigned int nr_maps = maps__nr_maps(maps); unsigned int nr_allocate = RC_CHK_ACCESS(maps)->nr_maps_allocated; @@ -483,14 +501,9 @@ static int __maps__insert(struct maps *maps, struct map *new) } if (map__end(new) < map__start(new)) RC_CHK_ACCESS(maps)->ends_broken = true; - if (dso && dso__kernel(dso)) { - struct kmap *kmap = map__kmap(new); - if (kmap) - kmap->kmaps = maps; - else - pr_err("Internal error: kernel dso with non kernel map\n"); - } + map__set_kmap_maps(new, maps); + return 0; } @@ -785,6 +798,9 @@ static int __maps__insert_sorted(struct maps *maps, unsigned int first_after_ind } RC_CHK_ACCESS(maps)->nr_maps = nr_maps + to_add; maps__set_maps_by_name_sorted(maps, false); + map__set_kmap_maps(new1, maps); + map__set_kmap_maps(new2, maps); + check_invariants(maps); return 0; } @@ -797,7 +813,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) { int err = 0; FILE *fp = debug_file(); - unsigned int i; + unsigned int i, ni = INT_MAX; // Some gcc complain, but depends on maps_by_name... if (!maps__maps_by_address_sorted(maps)) __maps__sort_by_address(maps); @@ -808,6 +824,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ for (i = first_ending_after(maps, new); i < maps__nr_maps(maps); ) { struct map **maps_by_address = maps__maps_by_address(maps); + struct map **maps_by_name = maps__maps_by_name(maps); struct map *pos = maps_by_address[i]; struct map *before = NULL, *after = NULL; @@ -827,6 +844,9 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) map__fprintf(pos, fp); } + if (maps_by_name) + ni = maps__by_name_index(maps, pos); + /* * Now check if we need to create new maps for areas not * overlapped by the new map: @@ -871,6 +891,12 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) if (before) { map__put(maps_by_address[i]); maps_by_address[i] = before; + + if (maps_by_name) { + map__put(maps_by_name[ni]); + maps_by_name[ni] = map__get(before); + } + /* Maps are still ordered, go to next one. */ i++; if (after) { @@ -892,6 +918,12 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + + if (maps_by_name) { + map__put(maps_by_name[ni]); + maps_by_name[ni] = map__get(new); + } + err = __maps__insert_sorted(maps, i + 1, after, NULL); map__put(after); check_invariants(maps); @@ -910,6 +942,14 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + + if (maps_by_name) { + map__put(maps_by_name[ni]); + maps_by_name[ni] = map__get(new); + } + + map__set_kmap_maps(new, maps); + check_invariants(maps); return err; } diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 3692e988c86e..884d9aebce91 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -31,9 +31,6 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { bool perf_mem_record[PERF_MEM_EVENTS__MAX] = { 0 }; -static char mem_loads_name[100]; -static char mem_stores_name[100]; - struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i) { if (i >= PERF_MEM_EVENTS__MAX || !pmu) @@ -81,7 +78,8 @@ int perf_pmu__mem_events_num_mem_pmus(struct perf_pmu *pmu) return num; } -static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu) +static const char *perf_pmu__mem_events_name(struct perf_pmu *pmu, int i, + char *buf, size_t buf_size) { struct perf_mem_event *e; @@ -96,31 +94,31 @@ static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu) if (e->ldlat) { if (!e->aux_event) { /* ARM and Most of Intel */ - scnprintf(mem_loads_name, sizeof(mem_loads_name), + scnprintf(buf, buf_size, e->name, pmu->name, perf_mem_events__loads_ldlat); } else { /* Intel with mem-loads-aux event */ - scnprintf(mem_loads_name, sizeof(mem_loads_name), + scnprintf(buf, buf_size, e->name, pmu->name, pmu->name, perf_mem_events__loads_ldlat); } } else { if (!e->aux_event) { /* AMD and POWER */ - scnprintf(mem_loads_name, sizeof(mem_loads_name), + scnprintf(buf, buf_size, e->name, pmu->name); - } else + } else { return NULL; + } } - - return mem_loads_name; + return buf; } if (i == PERF_MEM_EVENTS__STORE) { - scnprintf(mem_stores_name, sizeof(mem_stores_name), + scnprintf(buf, buf_size, e->name, pmu->name); - return mem_stores_name; + return buf; } return NULL; @@ -189,7 +187,7 @@ static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu if (!e->event_name) return true; - scnprintf(path, PATH_MAX, "%s/devices/%s/events/%s", mnt, pmu->name, e->event_name); + scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/%s", mnt, pmu->name, e->event_name); return !stat(path, &st); } @@ -238,69 +236,87 @@ void perf_pmu__mem_events_list(struct perf_pmu *pmu) int j; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { + char buf[128]; struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j); fprintf(stderr, "%-*s%-*s%s", e->tag ? 13 : 0, e->tag ? : "", e->tag && verbose > 0 ? 25 : 0, - e->tag && verbose > 0 ? perf_pmu__mem_events_name(j, pmu) : "", + e->tag && verbose > 0 + ? perf_pmu__mem_events_name(pmu, j, buf, sizeof(buf)) + : "", e->supported ? ": available\n" : ""); } } -int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) +int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, char **event_name_storage_out) { const char *mnt = sysfs__mount(); struct perf_pmu *pmu = NULL; - struct perf_mem_event *e; int i = *argv_nr; - const char *s; - char *copy; struct perf_cpu_map *cpu_map = NULL; - int ret; + size_t event_name_storage_size = + perf_pmu__mem_events_num_mem_pmus(NULL) * PERF_MEM_EVENTS__MAX * 128; + size_t event_name_storage_remaining = event_name_storage_size; + char *event_name_storage = malloc(event_name_storage_size); + char *event_name_storage_ptr = event_name_storage; + + if (!event_name_storage) + return -ENOMEM; + *event_name_storage_out = NULL; while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) { for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - e = perf_pmu__mem_events_ptr(pmu, j); + const char *s; + struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j); + int ret; if (!perf_mem_record[j]) continue; if (!e->supported) { + char buf[128]; + pr_err("failed: event '%s' not supported\n", - perf_pmu__mem_events_name(j, pmu)); + perf_pmu__mem_events_name(pmu, j, buf, sizeof(buf))); + free(event_name_storage); return -1; } - s = perf_pmu__mem_events_name(j, pmu); + s = perf_pmu__mem_events_name(pmu, j, event_name_storage_ptr, + event_name_storage_remaining); if (!s || !perf_pmu__mem_events_supported(mnt, pmu, e)) continue; - copy = strdup(s); - if (!copy) - return -1; - rec_argv[i++] = "-e"; - rec_argv[i++] = copy; + rec_argv[i++] = event_name_storage_ptr; + event_name_storage_remaining -= strlen(event_name_storage_ptr) + 1; + event_name_storage_ptr += strlen(event_name_storage_ptr) + 1; ret = perf_cpu_map__merge(&cpu_map, pmu->cpus); - if (ret < 0) + if (ret < 0) { + free(event_name_storage); return ret; + } } } if (cpu_map) { - if (!perf_cpu_map__equal(cpu_map, cpu_map__online())) { + struct perf_cpu_map *online = cpu_map__online(); + + if (!perf_cpu_map__equal(cpu_map, online)) { char buf[200]; cpu_map__snprint(cpu_map, buf, sizeof(buf)); pr_warning("Memory events are enabled on a subset of CPUs: %s\n", buf); } + perf_cpu_map__put(online); perf_cpu_map__put(cpu_map); } *argv_nr = i; + *event_name_storage_out = event_name_storage; return 0; } diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 8dc27db9fd52..a5c19d39ee37 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -38,7 +38,8 @@ int perf_pmu__mem_events_num_mem_pmus(struct perf_pmu *pmu); bool is_mem_loads_aux_event(struct evsel *leader); void perf_pmu__mem_events_list(struct perf_pmu *pmu); -int perf_mem_events__record_args(const char **rec_argv, int *argv_nr); +int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, + char **event_name_storage_out); int perf_mem__tlb_scnprintf(char *out, size_t sz, const struct mem_info *mem_info); int perf_mem__lvl_scnprintf(char *out, size_t sz, const struct mem_info *mem_info); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 43b02293f1d2..a34726219af3 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -244,9 +244,8 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask) { int idx, nr_cpus; struct perf_cpu cpu; - const struct perf_cpu_map *cpu_map = NULL; + struct perf_cpu_map *cpu_map = cpu_map__online(); - cpu_map = cpu_map__online(); if (!cpu_map) return; @@ -256,6 +255,7 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask) if (cpu__get_node(cpu) == node) __set_bit(cpu.cpu, mask->bits); } + perf_cpu_map__put(cpu_map); } static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) @@ -356,14 +356,3 @@ int perf_mmap__push(struct mmap *md, void *to, out: return rc; } - -int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, struct mmap_cpu_mask *clone) -{ - clone->nbits = original->nbits; - clone->bits = bitmap_zalloc(original->nbits); - if (!clone->bits) - return -ENOMEM; - - memcpy(clone->bits, original->bits, MMAP_CPU_MASK_BYTES(original)); - return 0; -} diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index 0df6e1621c7e..4d72c5fa5084 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -61,7 +61,4 @@ size_t mmap__mmap_len(struct mmap *map); void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag); -int mmap_cpu_mask__duplicate(struct mmap_cpu_mask *original, - struct mmap_cpu_mask *clone); - #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/mutex.h b/tools/perf/util/mutex.h index 40661120cacc..62d258c71ded 100644 --- a/tools/perf/util/mutex.h +++ b/tools/perf/util/mutex.h @@ -33,6 +33,12 @@ /* Documents if a type is a lockable type. */ #define LOCKABLE __attribute__((lockable)) +/* Documents a function that expects a lock not to be held prior to entry. */ +#define LOCKS_EXCLUDED(...) __attribute__((locks_excluded(__VA_ARGS__))) + +/* Documents a function that returns a lock. */ +#define LOCK_RETURNED(x) __attribute__((lock_returned(x))) + /* Documents functions that acquire a lock in the body of a function, and do not release it. */ #define EXCLUSIVE_LOCK_FUNCTION(...) __attribute__((exclusive_lock_function(__VA_ARGS__))) @@ -57,6 +63,8 @@ #define GUARDED_BY(x) #define PT_GUARDED_BY(x) #define LOCKABLE +#define LOCKS_EXCLUDED(...) +#define LOCK_RETURNED(x) #define EXCLUSIVE_LOCK_FUNCTION(...) #define UNLOCK_FUNCTION(...) #define EXCLUSIVE_TRYLOCK_FUNCTION(...) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 1e23faa364b1..5152fd5a6ead 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -17,6 +17,7 @@ #include "strbuf.h" #include "debug.h" #include <api/fs/tracing_path.h> +#include <api/io_dir.h> #include <perf/cpumap.h> #include <util/parse-events-bison.h> #include <util/parse-events-flex.h> @@ -554,8 +555,8 @@ static int add_tracepoint_multi_event(struct parse_events_state *parse_state, struct parse_events_terms *head_config, YYLTYPE *loc) { char *evt_path; - struct dirent *evt_ent; - DIR *evt_dir; + struct io_dirent64 *evt_ent; + struct io_dir evt_dir; int ret = 0, found = 0; evt_path = get_events_file(sys_name); @@ -563,14 +564,14 @@ static int add_tracepoint_multi_event(struct parse_events_state *parse_state, tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); return -1; } - evt_dir = opendir(evt_path); - if (!evt_dir) { + io_dir__init(&evt_dir, open(evt_path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (evt_dir.dirfd < 0) { put_events_file(evt_path); tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); return -1; } - while (!ret && (evt_ent = readdir(evt_dir))) { + while (!ret && (evt_ent = io_dir__readdir(&evt_dir))) { if (!strcmp(evt_ent->d_name, ".") || !strcmp(evt_ent->d_name, "..") || !strcmp(evt_ent->d_name, "enable") @@ -592,7 +593,7 @@ static int add_tracepoint_multi_event(struct parse_events_state *parse_state, } put_events_file(evt_path); - closedir(evt_dir); + close(evt_dir.dirfd); return ret; } @@ -615,17 +616,23 @@ static int add_tracepoint_multi_sys(struct parse_events_state *parse_state, struct parse_events_error *err, struct parse_events_terms *head_config, YYLTYPE *loc) { - struct dirent *events_ent; - DIR *events_dir; + struct io_dirent64 *events_ent; + struct io_dir events_dir; int ret = 0; + char *events_dir_path = get_tracing_file("events"); - events_dir = tracing_events__opendir(); - if (!events_dir) { + if (!events_dir_path) { + tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); + return -1; + } + io_dir__init(&events_dir, open(events_dir_path, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + put_events_file(events_dir_path); + if (events_dir.dirfd < 0) { tracepoint_error(err, errno, sys_name, evt_name, loc->first_column); return -1; } - while (!ret && (events_ent = readdir(events_dir))) { + while (!ret && (events_ent = io_dir__readdir(&events_dir))) { if (!strcmp(events_ent->d_name, ".") || !strcmp(events_ent->d_name, "..") || !strcmp(events_ent->d_name, "enable") @@ -639,8 +646,7 @@ static int add_tracepoint_multi_sys(struct parse_events_state *parse_state, ret = add_tracepoint_event(parse_state, list, events_ent->d_name, evt_name, err, head_config, loc); } - - closedir(events_dir); + close(events_dir.dirfd); return ret; } @@ -1660,7 +1666,7 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state /* Failed to add, try wildcard expansion of event_or_pmu as a PMU name. */ while ((pmu = perf_pmus__scan(pmu)) != NULL) { if (!parse_events__filter_pmu(parse_state, pmu) && - perf_pmu__match(pmu, event_or_pmu)) { + perf_pmu__wildcard_match(pmu, event_or_pmu)) { bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu); if (!parse_events_add_pmu(parse_state, *listp, pmu, @@ -1974,48 +1980,55 @@ static int evlist__cmp(void *_fg_idx, const struct list_head *l, const struct li int *force_grouped_idx = _fg_idx; int lhs_sort_idx, rhs_sort_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; - bool lhs_has_group, rhs_has_group; /* - * First sort by grouping/leader. Read the leader idx only if the evsel - * is part of a group, by default ungrouped events will be sorted - * relative to grouped events based on where the first ungrouped event - * occurs. If both events don't have a group we want to fall-through to - * the arch specific sorting, that can reorder and fix things like - * Intel's topdown events. + * Get the indexes of the 2 events to sort. If the events are + * in groups then the leader's index is used otherwise the + * event's index is used. An index may be forced for events that + * must be in the same group, namely Intel topdown events. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { - lhs_has_group = true; - lhs_sort_idx = lhs_core->leader->idx; + if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs)) { + lhs_sort_idx = *force_grouped_idx; } else { - lhs_has_group = false; - lhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs) - ? *force_grouped_idx - : lhs_core->idx; - } - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { - rhs_has_group = true; - rhs_sort_idx = rhs_core->leader->idx; + bool lhs_has_group = lhs_core->leader != lhs_core || lhs_core->nr_members > 1; + + lhs_sort_idx = lhs_has_group ? lhs_core->leader->idx : lhs_core->idx; + } + if (*force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs)) { + rhs_sort_idx = *force_grouped_idx; } else { - rhs_has_group = false; - rhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs) - ? *force_grouped_idx - : rhs_core->idx; + bool rhs_has_group = rhs_core->leader != rhs_core || rhs_core->nr_members > 1; + + rhs_sort_idx = rhs_has_group ? rhs_core->leader->idx : rhs_core->idx; } + /* If the indices differ then respect the insertion order. */ if (lhs_sort_idx != rhs_sort_idx) return lhs_sort_idx - rhs_sort_idx; - /* Group by PMU if there is a group. Groups can't span PMUs. */ - if (lhs_has_group && rhs_has_group) { - lhs_pmu_name = lhs->group_pmu_name; - rhs_pmu_name = rhs->group_pmu_name; - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; - } + /* + * Ignoring forcing, lhs_sort_idx == rhs_sort_idx so lhs and rhs should + * be in the same group. Events in the same group need to be ordered by + * their grouping PMU name as the group will be broken to ensure only + * events on the same PMU are programmed together. + * + * With forcing the lhs_sort_idx == rhs_sort_idx shows that one or both + * events are being forced to be at force_group_index. If only one event + * is being forced then the other event is the group leader of the group + * we're trying to force the event into. Ensure for the force grouped + * case that the PMU name ordering is also respected. + */ + lhs_pmu_name = lhs->group_pmu_name; + rhs_pmu_name = rhs->group_pmu_name; + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; - /* Architecture specific sorting. */ + /* + * Architecture specific sorting, by default sort events in the same + * group with the same PMU by their insertion index. On Intel topdown + * constraints must be adhered to - slots first, etc. + */ return arch_evlist__cmp(lhs, rhs); } @@ -2024,9 +2037,11 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) int idx = 0, force_grouped_idx = -1; struct evsel *pos, *cur_leader = NULL; struct perf_evsel *cur_leaders_grp = NULL; - bool idx_changed = false, cur_leader_force_grouped = false; + bool idx_changed = false; int orig_num_leaders = 0, num_leaders = 0; int ret; + struct evsel *force_grouped_leader = NULL; + bool last_event_was_forced_leader = false; /* * Compute index to insert ungrouped events at. Place them where the @@ -2049,10 +2064,13 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) */ pos->core.idx = idx++; - /* Remember an index to sort all forced grouped events together to. */ - if (force_grouped_idx == -1 && pos == pos_leader && pos->core.nr_members < 2 && - arch_evsel__must_be_in_group(pos)) - force_grouped_idx = pos->core.idx; + /* + * Remember an index to sort all forced grouped events + * together to. Use the group leader as some events + * must appear first within the group. + */ + if (force_grouped_idx == -1 && arch_evsel__must_be_in_group(pos)) + force_grouped_idx = pos_leader->core.idx; } /* Sort events. */ @@ -2080,31 +2098,66 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) * Set the group leader respecting the given groupings and that * groups can't span PMUs. */ - if (!cur_leader) + if (!cur_leader) { cur_leader = pos; + cur_leaders_grp = &pos->core; + if (pos_force_grouped) + force_grouped_leader = pos; + } cur_leader_pmu_name = cur_leader->group_pmu_name; - if ((cur_leaders_grp != pos->core.leader && - (!pos_force_grouped || !cur_leader_force_grouped)) || - strcmp(cur_leader_pmu_name, pos_pmu_name)) { - /* Event is for a different group/PMU than last. */ + if (strcmp(cur_leader_pmu_name, pos_pmu_name)) { + /* PMU changed so the group/leader must change. */ cur_leader = pos; - /* - * Remember the leader's group before it is overwritten, - * so that later events match as being in the same - * group. - */ cur_leaders_grp = pos->core.leader; + if (pos_force_grouped && force_grouped_leader == NULL) + force_grouped_leader = pos; + } else if (cur_leaders_grp != pos->core.leader) { + bool split_even_if_last_leader_was_forced = true; + /* - * Avoid forcing events into groups with events that - * don't need to be in the group. + * Event is for a different group. If the last event was + * the forced group leader then subsequent group events + * and forced events should be in the same group. If + * there are no other forced group events then the + * forced group leader wasn't really being forced into a + * group, it just set arch_evsel__must_be_in_group, and + * we don't want the group to split here. */ - cur_leader_force_grouped = pos_force_grouped; + if (force_grouped_idx != -1 && last_event_was_forced_leader) { + struct evsel *pos2 = pos; + /* + * Search the whole list as the group leaders + * aren't currently valid. + */ + list_for_each_entry_continue(pos2, list, core.node) { + if (pos->core.leader == pos2->core.leader && + arch_evsel__must_be_in_group(pos2)) { + split_even_if_last_leader_was_forced = false; + break; + } + } + } + if (!last_event_was_forced_leader || split_even_if_last_leader_was_forced) { + if (pos_force_grouped) { + if (force_grouped_leader) { + cur_leader = force_grouped_leader; + cur_leaders_grp = force_grouped_leader->core.leader; + } else { + cur_leader = force_grouped_leader = pos; + cur_leaders_grp = &pos->core; + } + } else { + cur_leader = pos; + cur_leaders_grp = pos->core.leader; + } + } } if (pos_leader != cur_leader) { /* The leader changed so update it. */ evsel__set_leader(pos, cur_leader); } + last_event_was_forced_leader = (force_grouped_leader == pos); } list_for_each_entry(pos, list, core.node) { struct evsel *pos_leader = evsel__leader(pos); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index bf7f73548605..7ed86e3e34e3 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -53,21 +53,25 @@ static int str(yyscan_t scanner, int token) YYSTYPE *yylval = parse_events_get_lval(scanner); char *text = parse_events_get_text(scanner); - if (text[0] != '\'') { - yylval->str = strdup(text); - } else { - /* - * If a text tag specified on the command line - * contains opening single quite ' then it is - * expected that the tag ends with single quote - * as well, like this: - * name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\' - * quotes need to be escaped to bypass shell - * processing. - */ - yylval->str = strndup(&text[1], strlen(text) - 2); - } + yylval->str = strdup(text); + return token; +} + +static int quoted_str(yyscan_t scanner, int token) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + /* + * If a text tag specified on the command line + * contains opening single quite ' then it is + * expected that the tag ends with single quote + * as well, like this: + * name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\' + * quotes need to be escaped to bypass shell + * processing. + */ + yylval->str = strndup(&text[1], strlen(text) - 2); return token; } @@ -235,9 +239,16 @@ event [^,{}/]+ num_dec [0-9]+ num_hex 0x[a-fA-F0-9]{1,16} num_raw_hex [a-fA-F0-9]{1,16} -name [a-zA-Z0-9_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]* -name_tag [\'][a-zA-Z0-9_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] -name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* +/* Regular pattern to match the token PE_NAME. */ +name_start [a-zA-Z0-9_*?\[\]] +name {name_start}[a-zA-Z0-9_*?.\[\]!\-]* +/* PE_NAME token when inside a config term list, allows ':'. */ +term_name {name_start}[a-zA-Z0-9_*?.\[\]!\-:]* +/* + * PE_NAME token when quoted, allows ':,.='. + * Matches the RHS of terms like: name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'. + */ +quoted_name [\']{name_start}[a-zA-Z0-9_*?.\[\]!\-:,\.=]*[\'] drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* * If you add a modifier you need to update check_modifier(). @@ -341,7 +352,9 @@ r0x{num_raw_hex} { return str(yyscanner, PE_RAW); } {lc_type} { return lc_str(yyscanner, _parse_state); } {lc_type}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } {lc_type}-{lc_op_result}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } -{name_minus} { return str(yyscanner, PE_NAME); } +{num_dec} { return value(_parse_state, yyscanner, 10); } +{num_hex} { return value(_parse_state, yyscanner, 16); } +{term_name} { return str(yyscanner, PE_NAME); } @{drv_cfg_term} { return drv_str(yyscanner, PE_DRV_CFG_TERM); } } @@ -410,7 +423,7 @@ r{num_raw_hex} { return str(yyscanner, PE_RAW); } {modifier_event} { return modifiers(_parse_state, yyscanner); } {name} { return str(yyscanner, PE_NAME); } -{name_tag} { return str(yyscanner, PE_NAME); } +{quoted_name} { return quoted_str(yyscanner, PE_NAME); } "/" { BEGIN(config); return '/'; } , { BEGIN(event); return ','; } : { return ':'; } diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index c7f3543b9921..66b666d9ce64 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -79,24 +79,22 @@ static void __p_read_format(char *buf, size_t size, u64 value) #define ENUM_ID_TO_STR_CASE(x) case x: return (#x); static const char *stringify_perf_type_id(struct perf_pmu *pmu, u32 type) { - if (pmu) - return pmu->name; - switch (type) { ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE) ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE) ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT) ENUM_ID_TO_STR_CASE(PERF_TYPE_HW_CACHE) - ENUM_ID_TO_STR_CASE(PERF_TYPE_RAW) ENUM_ID_TO_STR_CASE(PERF_TYPE_BREAKPOINT) + case PERF_TYPE_RAW: + return pmu ? pmu->name : "PERF_TYPE_RAW"; default: - return NULL; + return pmu ? pmu->name : NULL; } } static const char *stringify_perf_hw_id(u64 value) { - switch (value) { + switch (value & PERF_HW_EVENT_MASK) { ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CPU_CYCLES) ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_INSTRUCTIONS) ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_REFERENCES) @@ -169,79 +167,100 @@ static const char *stringify_perf_sw_id(u64 value) } #undef ENUM_ID_TO_STR_CASE -#define PRINT_ID(_s, _f) \ -do { \ - const char *__s = _s; \ - if (__s == NULL) \ - snprintf(buf, size, _f, value); \ - else \ - snprintf(buf, size, _f" (%s)", value, __s); \ -} while (0) -#define print_id_unsigned(_s) PRINT_ID(_s, "%"PRIu64) -#define print_id_hex(_s) PRINT_ID(_s, "%#"PRIx64) +static void print_id_unsigned(char *buf, size_t size, u64 value, const char *s) +{ + if (s == NULL) + snprintf(buf, size, "%"PRIu64, value); + else + snprintf(buf, size, "%"PRIu64" (%s)", value, s); +} + +static void print_id_hex(char *buf, size_t size, u64 value, const char *s) +{ + if (s == NULL) + snprintf(buf, size, "%#"PRIx64, value); + else + snprintf(buf, size, "%#"PRIx64" (%s)", value, s); +} -static void __p_type_id(struct perf_pmu *pmu, char *buf, size_t size, u64 value) +static void __p_type_id(char *buf, size_t size, struct perf_pmu *pmu, u32 type) { - print_id_unsigned(stringify_perf_type_id(pmu, value)); + print_id_unsigned(buf, size, type, stringify_perf_type_id(pmu, type)); } -static void __p_config_hw_id(char *buf, size_t size, u64 value) +static void __p_config_hw_id(char *buf, size_t size, struct perf_pmu *pmu, u64 config) { - print_id_hex(stringify_perf_hw_id(value)); + const char *name = stringify_perf_hw_id(config); + + if (name == NULL) { + if (pmu == NULL) { + snprintf(buf, size, "%#"PRIx64, config); + } else { + snprintf(buf, size, "%#"PRIx64" (%s/config=%#"PRIx64"/)", config, pmu->name, + config); + } + } else { + if (pmu == NULL) + snprintf(buf, size, "%#"PRIx64" (%s)", config, name); + else + snprintf(buf, size, "%#"PRIx64" (%s/%s/)", config, pmu->name, name); + } } -static void __p_config_sw_id(char *buf, size_t size, u64 value) +static void __p_config_sw_id(char *buf, size_t size, u64 id) { - print_id_hex(stringify_perf_sw_id(value)); + print_id_hex(buf, size, id, stringify_perf_sw_id(id)); } -static void __p_config_hw_cache_id(char *buf, size_t size, u64 value) +static void __p_config_hw_cache_id(char *buf, size_t size, struct perf_pmu *pmu, u64 config) { - const char *hw_cache_str = stringify_perf_hw_cache_id(value & 0xff); + const char *hw_cache_str = stringify_perf_hw_cache_id(config & 0xff); const char *hw_cache_op_str = - stringify_perf_hw_cache_op_id((value & 0xff00) >> 8); + stringify_perf_hw_cache_op_id((config & 0xff00) >> 8); const char *hw_cache_op_result_str = - stringify_perf_hw_cache_op_result_id((value & 0xff0000) >> 16); - - if (hw_cache_str == NULL || hw_cache_op_str == NULL || - hw_cache_op_result_str == NULL) { - snprintf(buf, size, "%#"PRIx64, value); + stringify_perf_hw_cache_op_result_id((config & 0xff0000) >> 16); + + if (hw_cache_str == NULL || hw_cache_op_str == NULL || hw_cache_op_result_str == NULL) { + if (pmu == NULL) { + snprintf(buf, size, "%#"PRIx64, config); + } else { + snprintf(buf, size, "%#"PRIx64" (%s/config=%#"PRIx64"/)", config, pmu->name, + config); + } } else { - snprintf(buf, size, "%#"PRIx64" (%s | %s | %s)", value, - hw_cache_op_result_str, hw_cache_op_str, hw_cache_str); + if (pmu == NULL) { + snprintf(buf, size, "%#"PRIx64" (%s | %s | %s)", config, + hw_cache_op_result_str, hw_cache_op_str, hw_cache_str); + } else { + snprintf(buf, size, "%#"PRIx64" (%s/%s | %s | %s/)", config, pmu->name, + hw_cache_op_result_str, hw_cache_op_str, hw_cache_str); + } } } -static void __p_config_tracepoint_id(char *buf, size_t size, u64 value) +static void __p_config_tracepoint_id(char *buf, size_t size, u64 id) { - char *str = tracepoint_id_to_name(value); + char *str = tracepoint_id_to_name(id); - print_id_hex(str); + print_id_hex(buf, size, id, str); free(str); } -static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value) +static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 config) { - const char *name = perf_pmu__name_from_config(pmu, value); - - if (name) { - print_id_hex(name); - return; - } switch (type) { case PERF_TYPE_HARDWARE: - return __p_config_hw_id(buf, size, value); + return __p_config_hw_id(buf, size, pmu, config); case PERF_TYPE_SOFTWARE: - return __p_config_sw_id(buf, size, value); + return __p_config_sw_id(buf, size, config); case PERF_TYPE_HW_CACHE: - return __p_config_hw_cache_id(buf, size, value); + return __p_config_hw_cache_id(buf, size, pmu, config); case PERF_TYPE_TRACEPOINT: - return __p_config_tracepoint_id(buf, size, value); + return __p_config_tracepoint_id(buf, size, config); case PERF_TYPE_RAW: case PERF_TYPE_BREAKPOINT: default: - snprintf(buf, size, "%#"PRIx64, value); - return; + return print_id_hex(buf, size, config, perf_pmu__name_from_config(pmu, config)); } } @@ -253,7 +272,7 @@ static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type #define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) #define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) #define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) -#define p_type_id(val) __p_type_id(pmu, buf, BUF_SIZE, val) +#define p_type_id(val) __p_type_id(buf, BUF_SIZE, pmu, val) #define p_config_id(val) __p_config_id(pmu, buf, BUF_SIZE, attr->type, val) #define PRINT_ATTRn(_n, _f, _p, _a) \ @@ -273,6 +292,13 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, char buf[BUF_SIZE]; int ret = 0; + if (!pmu && (attr->type == PERF_TYPE_HARDWARE || attr->type == PERF_TYPE_HW_CACHE)) { + u32 extended_type = attr->config >> PERF_PMU_TYPE_SHIFT; + + if (extended_type) + pmu = perf_pmus__find_by_type(extended_type); + } + PRINT_ATTRn("type", type, p_type_id, true); PRINT_ATTRf(size, p_unsigned); PRINT_ATTRn("config", config, p_config_id, true); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 6206c8fe2bf9..b7ebac5ab1d1 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -13,6 +13,7 @@ #include <dirent.h> #include <api/fs/fs.h> #include <api/io.h> +#include <api/io_dir.h> #include <locale.h> #include <fnmatch.h> #include <math.h> @@ -36,12 +37,12 @@ #define UNIT_MAX_LEN 31 /* max length for event unit name */ enum event_source { - /* An event loaded from /sys/devices/<pmu>/events. */ + /* An event loaded from /sys/bus/event_source/devices/<pmu>/events. */ EVENT_SRC_SYSFS, /* An event loaded from a CPUID matched json file. */ EVENT_SRC_CPU_JSON, /* - * An event loaded from a /sys/devices/<pmu>/identifier matched json + * An event loaded from a /sys/bus/event_source/devices/<pmu>/identifier matched json * file. */ EVENT_SRC_SYS_JSON, @@ -195,19 +196,17 @@ static void perf_pmu_format__load(const struct perf_pmu *pmu, struct perf_pmu_fo */ static int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load) { - struct dirent *evt_ent; - DIR *format_dir; + struct io_dirent64 *evt_ent; + struct io_dir format_dir; int ret = 0; - format_dir = fdopendir(dirfd); - if (!format_dir) - return -EINVAL; + io_dir__init(&format_dir, dirfd); - while ((evt_ent = readdir(format_dir)) != NULL) { + while ((evt_ent = io_dir__readdir(&format_dir)) != NULL) { struct perf_pmu_format *format; char *name = evt_ent->d_name; - if (!strcmp(name, ".") || !strcmp(name, "..")) + if (io_dir__is_dir(&format_dir, evt_ent)) continue; format = perf_pmu__new_format(&pmu->format, name); @@ -234,7 +233,7 @@ static int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_lo } } - closedir(format_dir); + close(format_dir.dirfd); return ret; } @@ -596,7 +595,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, }; if (pmu_events_table__find_event(pmu->events_table, pmu, name, update_alias, &data) == 0) - pmu->cpu_json_aliases++; + pmu->cpu_common_json_aliases++; } pmu->sysfs_aliases++; break; @@ -635,14 +634,12 @@ static inline bool pmu_alias_info_file(const char *name) */ static int __pmu_aliases_parse(struct perf_pmu *pmu, int events_dir_fd) { - struct dirent *evt_ent; - DIR *event_dir; + struct io_dirent64 *evt_ent; + struct io_dir event_dir; - event_dir = fdopendir(events_dir_fd); - if (!event_dir) - return -EINVAL; + io_dir__init(&event_dir, events_dir_fd); - while ((evt_ent = readdir(event_dir))) { + while ((evt_ent = io_dir__readdir(&event_dir))) { char *name = evt_ent->d_name; int fd; FILE *file; @@ -674,7 +671,6 @@ static int __pmu_aliases_parse(struct perf_pmu *pmu, int events_dir_fd) fclose(file); } - closedir(event_dir); pmu->sysfs_aliases_loaded = true; return 0; } @@ -783,7 +779,7 @@ static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *pmu_name, bool is } /* Nothing found, for core PMUs assume this means all CPUs. */ - return is_core ? perf_cpu_map__get(cpu_map__online()) : NULL; + return is_core ? cpu_map__online() : NULL; } static bool pmu_is_uncore(int dirfd, const char *name) @@ -847,21 +843,23 @@ static size_t pmu_deduped_name_len(const struct perf_pmu *pmu, const char *name, } /** - * perf_pmu__match_ignoring_suffix - Does the pmu_name match tok ignoring any - * trailing suffix? The Suffix must be in form - * tok_{digits}, or tok{digits}. + * perf_pmu__match_wildcard - Does the pmu_name start with tok and is then only + * followed by nothing or a suffix? tok may contain + * part of a suffix. * @pmu_name: The pmu_name with possible suffix. - * @tok: The possible match to pmu_name without suffix. + * @tok: The wildcard argument to match. */ -static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *tok) +static bool perf_pmu__match_wildcard(const char *pmu_name, const char *tok) { const char *p, *suffix; bool has_hex = false; + size_t tok_len = strlen(tok); - if (strncmp(pmu_name, tok, strlen(tok))) + /* Check start of pmu_name for equality. */ + if (strncmp(pmu_name, tok, tok_len)) return false; - suffix = p = pmu_name + strlen(tok); + suffix = p = pmu_name + tok_len; if (*p == 0) return true; @@ -887,60 +885,84 @@ static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *to } /** - * pmu_uncore_alias_match - does name match the PMU name? - * @pmu_name: the json struct pmu_event name. This may lack a suffix (which + * perf_pmu__match_ignoring_suffix_uncore - Does the pmu_name match tok ignoring + * any trailing suffix on pmu_name and + * tok? The Suffix must be in form + * tok_{digits}, or tok{digits}. + * @pmu_name: The pmu_name with possible suffix. + * @tok: The possible match to pmu_name. + */ +static bool perf_pmu__match_ignoring_suffix_uncore(const char *pmu_name, const char *tok) +{ + size_t pmu_name_len, tok_len; + + /* For robustness, check for NULL. */ + if (pmu_name == NULL) + return tok == NULL; + + /* uncore_ prefixes are ignored. */ + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; + if (!strncmp(tok, "uncore_", 7)) + tok += 7; + + pmu_name_len = pmu_name_len_no_suffix(pmu_name); + tok_len = pmu_name_len_no_suffix(tok); + if (pmu_name_len != tok_len) + return false; + + return strncmp(pmu_name, tok, pmu_name_len) == 0; +} + + +/** + * perf_pmu__match_wildcard_uncore - does to_match match the PMU's name? + * @pmu_name: The pmu->name or pmu->alias to match against. + * @to_match: the json struct pmu_event name. This may lack a suffix (which * matches) or be of the form "socket,pmuname" which will match * "socketX_pmunameY". - * @name: a real full PMU name as from sysfs. */ -static bool pmu_uncore_alias_match(const char *pmu_name, const char *name) +static bool perf_pmu__match_wildcard_uncore(const char *pmu_name, const char *to_match) { - char *tmp = NULL, *tok, *str; - bool res; - - if (strchr(pmu_name, ',') == NULL) - return perf_pmu__match_ignoring_suffix(name, pmu_name); + char *mutable_to_match, *tok, *tmp; - str = strdup(pmu_name); - if (!str) + if (!pmu_name) return false; - /* - * uncore alias may be from different PMU with common prefix - */ - tok = strtok_r(str, ",", &tmp); - if (strncmp(pmu_name, tok, strlen(tok))) { - res = false; - goto out; - } + /* uncore_ prefixes are ignored. */ + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; + if (!strncmp(to_match, "uncore_", 7)) + to_match += 7; - /* - * Match more complex aliases where the alias name is a comma-delimited - * list of tokens, orderly contained in the matching PMU name. - * - * Example: For alias "socket,pmuname" and PMU "socketX_pmunameY", we - * match "socket" in "socketX_pmunameY" and then "pmuname" in - * "pmunameY". - */ - while (1) { - char *next_tok = strtok_r(NULL, ",", &tmp); + if (strchr(to_match, ',') == NULL) + return perf_pmu__match_wildcard(pmu_name, to_match); - name = strstr(name, tok); - if (!name || - (!next_tok && !perf_pmu__match_ignoring_suffix(name, tok))) { - res = false; - goto out; + /* Process comma separated list of PMU name components. */ + mutable_to_match = strdup(to_match); + if (!mutable_to_match) + return false; + + tok = strtok_r(mutable_to_match, ",", &tmp); + while (tok) { + size_t tok_len = strlen(tok); + + if (strncmp(pmu_name, tok, tok_len)) { + /* Mismatch between part of pmu_name and tok. */ + free(mutable_to_match); + return false; } - if (!next_tok) - break; - tok = next_tok; - name += strlen(tok); + /* Move pmu_name forward over tok and suffix. */ + pmu_name += tok_len; + while (*pmu_name != '\0' && isdigit(*pmu_name)) + pmu_name++; + if (*pmu_name == '_') + pmu_name++; + + tok = strtok_r(NULL, ",", &tmp); } - - res = true; -out: - free(str); - return res; + free(mutable_to_match); + return *pmu_name == '\0'; } bool pmu_uncore_identifier_match(const char *compat, const char *id) @@ -1003,11 +1025,19 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, { struct perf_pmu *pmu = vdata; - if (!pe->compat || !pe->pmu) + if (!pe->compat || !pe->pmu) { + /* No data to match. */ + return 0; + } + + if (!perf_pmu__match_wildcard_uncore(pmu->name, pe->pmu) && + !perf_pmu__match_wildcard_uncore(pmu->alias_name, pe->pmu)) { + /* PMU name/alias_name don't match. */ return 0; + } - if (pmu_uncore_alias_match(pe->pmu, pmu->name) && - pmu_uncore_identifier_match(pe->compat, pmu->id)) { + if (pmu_uncore_identifier_match(pe->compat, pmu->id)) { + /* Id matched. */ perf_pmu__new_alias(pmu, pe->name, pe->desc, @@ -1016,7 +1046,6 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, pe, EVENT_SRC_SYS_JSON); } - return 0; } @@ -1851,9 +1880,10 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu) if (pmu->cpu_aliases_added) nr += pmu->cpu_json_aliases; else if (pmu->events_table) - nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases; + nr += pmu_events_table__num_events(pmu->events_table, pmu) - + pmu->cpu_common_json_aliases; else - assert(pmu->cpu_json_aliases == 0); + assert(pmu->cpu_json_aliases == 0 && pmu->cpu_common_json_aliases == 0); if (perf_pmu__is_tool(pmu)) nr -= tool_pmu__num_skip_events(); @@ -1974,15 +2004,82 @@ out: return ret; } -bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name) +static bool perf_pmu___name_match(const struct perf_pmu *pmu, const char *to_match, bool wildcard) { - return !strcmp(pmu->name, pmu_name) || - (pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name)) || + const char *names[2] = { + pmu->name, + pmu->alias_name, + }; + if (pmu->is_core) { + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (!name) + continue; + + if (!strcmp(name, to_match)) { + /* Exact name match. */ + return true; + } + } + if (!strcmp(to_match, "default_core")) { + /* + * jevents and tests use default_core as a marker for any core + * PMU as the PMU name varies across architectures. + */ + return true; + } + return false; + } + if (!pmu->is_uncore) { /* - * jevents and tests use default_core as a marker for any core - * PMU as the PMU name varies across architectures. + * PMU isn't core or uncore, some kind of broken CPU mask + * situation. Only match exact name. */ - (pmu->is_core && !strcmp(pmu_name, "default_core")); + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (!name) + continue; + + if (!strcmp(name, to_match)) { + /* Exact name match. */ + return true; + } + } + return false; + } + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (wildcard && perf_pmu__match_wildcard_uncore(name, to_match)) + return true; + if (!wildcard && perf_pmu__match_ignoring_suffix_uncore(name, to_match)) + return true; + } + return false; +} + +/** + * perf_pmu__name_wildcard_match - Called by the jevents generated code to see + * if pmu matches the json to_match string. + * @pmu: The pmu whose name/alias to match. + * @to_match: The possible match to pmu_name. + */ +bool perf_pmu__name_wildcard_match(const struct perf_pmu *pmu, const char *to_match) +{ + return perf_pmu___name_match(pmu, to_match, /*wildcard=*/true); +} + +/** + * perf_pmu__name_no_suffix_match - Does pmu's name match to_match ignoring any + * trailing suffix on the pmu_name and/or tok? + * @pmu: The pmu whose name/alias to match. + * @to_match: The possible match to pmu_name. + */ +bool perf_pmu__name_no_suffix_match(const struct perf_pmu *pmu, const char *to_match) +{ + return perf_pmu___name_match(pmu, to_match, /*wildcard=*/false); } bool perf_pmu__is_software(const struct perf_pmu *pmu) @@ -2121,10 +2218,9 @@ static void perf_pmu__del_caps(struct perf_pmu *pmu) */ int perf_pmu__caps_parse(struct perf_pmu *pmu) { - struct stat st; char caps_path[PATH_MAX]; - DIR *caps_dir; - struct dirent *evt_ent; + struct io_dir caps_dir; + struct io_dirent64 *evt_ent; int caps_fd; if (pmu->caps_initialized) @@ -2135,24 +2231,21 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) if (!perf_pmu__pathname_scnprintf(caps_path, sizeof(caps_path), pmu->name, "caps")) return -1; - if (stat(caps_path, &st) < 0) { + caps_fd = open(caps_path, O_CLOEXEC | O_DIRECTORY | O_RDONLY); + if (caps_fd == -1) { pmu->caps_initialized = true; return 0; /* no error if caps does not exist */ } - caps_dir = opendir(caps_path); - if (!caps_dir) - return -EINVAL; + io_dir__init(&caps_dir, caps_fd); - caps_fd = dirfd(caps_dir); - - while ((evt_ent = readdir(caps_dir)) != NULL) { + while ((evt_ent = io_dir__readdir(&caps_dir)) != NULL) { char *name = evt_ent->d_name; char value[128]; FILE *file; int fd; - if (!strcmp(name, ".") || !strcmp(name, "..")) + if (io_dir__is_dir(&caps_dir, evt_ent)) continue; fd = openat(caps_fd, name, O_RDONLY); @@ -2174,7 +2267,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) fclose(file); } - closedir(caps_dir); + close(caps_fd); pmu->caps_initialized = true; return pmu->nr_caps; @@ -2229,29 +2322,31 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, name ?: "N/A", buf, config_name, config); } -bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok) +bool perf_pmu__wildcard_match(const struct perf_pmu *pmu, const char *wildcard_to_match) { - const char *name = pmu->name; - bool need_fnmatch = strisglob(tok); + const char *names[2] = { + pmu->name, + pmu->alias_name, + }; + bool need_fnmatch = strisglob(wildcard_to_match); - if (!strncmp(tok, "uncore_", 7)) - tok += 7; - if (!strncmp(name, "uncore_", 7)) - name += 7; + if (!strncmp(wildcard_to_match, "uncore_", 7)) + wildcard_to_match += 7; - if (perf_pmu__match_ignoring_suffix(name, tok) || - (need_fnmatch && !fnmatch(tok, name, 0))) - return true; + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *pmu_name = names[i]; - name = pmu->alias_name; - if (!name) - return false; + if (!pmu_name) + continue; - if (!strncmp(name, "uncore_", 7)) - name += 7; + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; - return perf_pmu__match_ignoring_suffix(name, tok) || - (need_fnmatch && !fnmatch(tok, name, 0)); + if (perf_pmu__match_wildcard(pmu_name, wildcard_to_match) || + (need_fnmatch && !fnmatch(wildcard_to_match, pmu_name, 0))) + return true; + } + return false; } int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size) diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index dbed6c243a5e..b93014cc3670 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -37,6 +37,8 @@ struct perf_pmu_caps { }; enum { + PERF_PMU_TYPE_PE_START = 0, + PERF_PMU_TYPE_PE_END = 0xFFFEFFFF, PERF_PMU_TYPE_HWMON_START = 0xFFFF0000, PERF_PMU_TYPE_HWMON_END = 0xFFFFFFFD, PERF_PMU_TYPE_TOOL = 0xFFFFFFFE, @@ -134,6 +136,11 @@ struct perf_pmu { uint32_t cpu_json_aliases; /** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */ uint32_t sys_json_aliases; + /** + * @cpu_common_json_aliases: Number of json events that overlapped with sysfs when + * loading all sysfs events. + */ + uint32_t cpu_common_json_aliases; /** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */ bool sysfs_aliases_loaded; /** @@ -238,7 +245,8 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name); size_t perf_pmu__num_events(struct perf_pmu *pmu); int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, void *state, pmu_event_callback cb); -bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name); +bool perf_pmu__name_wildcard_match(const struct perf_pmu *pmu, const char *to_match); +bool perf_pmu__name_no_suffix_match(const struct perf_pmu *pmu, const char *to_match); /** * perf_pmu_is_software - is the PMU a software PMU as in it uses the @@ -273,7 +281,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, const char *config_name); void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); -bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok); +bool perf_pmu__wildcard_match(const struct perf_pmu *pmu, const char *wildcard_to_match); int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size); int perf_pmu__pathname_scnprintf(char *buf, size_t size, diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index b493da0d22ef..b99292de7669 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -3,10 +3,10 @@ #include <linux/list_sort.h> #include <linux/string.h> #include <linux/zalloc.h> +#include <api/io_dir.h> #include <subcmd/pager.h> #include <sys/types.h> #include <ctype.h> -#include <dirent.h> #include <pthread.h> #include <string.h> #include <unistd.h> @@ -37,10 +37,25 @@ */ static LIST_HEAD(core_pmus); static LIST_HEAD(other_pmus); -static bool read_sysfs_core_pmus; -static bool read_sysfs_all_pmus; +enum perf_tool_pmu_type { + PERF_TOOL_PMU_TYPE_PE_CORE, + PERF_TOOL_PMU_TYPE_PE_OTHER, + PERF_TOOL_PMU_TYPE_TOOL, + PERF_TOOL_PMU_TYPE_HWMON, + +#define PERF_TOOL_PMU_TYPE_PE_CORE_MASK (1 << PERF_TOOL_PMU_TYPE_PE_CORE) +#define PERF_TOOL_PMU_TYPE_PE_OTHER_MASK (1 << PERF_TOOL_PMU_TYPE_PE_OTHER) +#define PERF_TOOL_PMU_TYPE_TOOL_MASK (1 << PERF_TOOL_PMU_TYPE_TOOL) +#define PERF_TOOL_PMU_TYPE_HWMON_MASK (1 << PERF_TOOL_PMU_TYPE_HWMON) + +#define PERF_TOOL_PMU_TYPE_ALL_MASK (PERF_TOOL_PMU_TYPE_PE_CORE_MASK | \ + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK | \ + PERF_TOOL_PMU_TYPE_TOOL_MASK | \ + PERF_TOOL_PMU_TYPE_HWMON_MASK) +}; +static unsigned int read_pmu_types; -static void pmu_read_sysfs(bool core_only); +static void pmu_read_sysfs(unsigned int to_read_pmus); size_t pmu_name_len_no_suffix(const char *str) { @@ -102,8 +117,7 @@ void perf_pmus__destroy(void) perf_pmu__delete(pmu); } - read_sysfs_core_pmus = false; - read_sysfs_all_pmus = false; + read_pmu_types = 0; } static struct perf_pmu *pmu_find(const char *name) @@ -129,6 +143,7 @@ struct perf_pmu *perf_pmus__find(const char *name) struct perf_pmu *pmu; int dirfd; bool core_pmu; + unsigned int to_read_pmus = 0; /* * Once PMU is loaded it stays in the list, @@ -139,11 +154,11 @@ struct perf_pmu *perf_pmus__find(const char *name) if (pmu) return pmu; - if (read_sysfs_all_pmus) + if (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK) return NULL; core_pmu = is_pmu_core(name); - if (core_pmu && read_sysfs_core_pmus) + if (core_pmu && (read_pmu_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK)) return NULL; dirfd = perf_pmu__event_source_devices_fd(); @@ -151,15 +166,27 @@ struct perf_pmu *perf_pmus__find(const char *name) /*eager_load=*/false); close(dirfd); - if (!pmu) { - /* - * Looking up an inidividual PMU failed. This may mean name is - * an alias, so read the PMUs from sysfs and try to find again. - */ - pmu_read_sysfs(core_pmu); + if (pmu) + return pmu; + + /* Looking up an individual perf event PMU failed, check if a tool PMU should be read. */ + if (!strncmp(name, "hwmon_", 6)) + to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK; + else if (!strcmp(name, "tool")) + to_read_pmus |= PERF_TOOL_PMU_TYPE_TOOL_MASK; + + if (to_read_pmus) { + pmu_read_sysfs(to_read_pmus); pmu = pmu_find(name); + if (pmu) + return pmu; } - return pmu; + /* Read all necessary PMUs from sysfs and see if the PMU is found. */ + to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK; + if (!core_pmu) + to_read_pmus |= PERF_TOOL_PMU_TYPE_PE_OTHER_MASK; + pmu_read_sysfs(to_read_pmus); + return pmu_find(name); } static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) @@ -176,11 +203,11 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) if (pmu) return pmu; - if (read_sysfs_all_pmus) + if (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK) return NULL; core_pmu = is_pmu_core(name); - if (core_pmu && read_sysfs_core_pmus) + if (core_pmu && (read_pmu_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK)) return NULL; return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name, @@ -197,52 +224,57 @@ static int pmus_cmp(void *priv __maybe_unused, } /* Add all pmus in sysfs to pmu list: */ -static void pmu_read_sysfs(bool core_only) +static void pmu_read_sysfs(unsigned int to_read_types) { - int fd; - DIR *dir; - struct dirent *dent; struct perf_pmu *tool_pmu; - if (read_sysfs_all_pmus || (core_only && read_sysfs_core_pmus)) + if ((read_pmu_types & to_read_types) == to_read_types) { + /* All requested PMU types have been read. */ return; + } - fd = perf_pmu__event_source_devices_fd(); - if (fd < 0) - return; + if (to_read_types & (PERF_TOOL_PMU_TYPE_PE_CORE_MASK | PERF_TOOL_PMU_TYPE_PE_OTHER_MASK)) { + int fd = perf_pmu__event_source_devices_fd(); + struct io_dir dir; + struct io_dirent64 *dent; + bool core_only = (to_read_types & PERF_TOOL_PMU_TYPE_PE_OTHER_MASK) == 0; - dir = fdopendir(fd); - if (!dir) { - close(fd); - return; - } + if (fd < 0) + goto skip_pe_pmus; - while ((dent = readdir(dir))) { - if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) - continue; - if (core_only && !is_pmu_core(dent->d_name)) - continue; - /* add to static LIST_HEAD(core_pmus) or LIST_HEAD(other_pmus): */ - perf_pmu__find2(fd, dent->d_name); - } + io_dir__init(&dir, fd); + + while ((dent = io_dir__readdir(&dir)) != NULL) { + if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) + continue; + if (core_only && !is_pmu_core(dent->d_name)) + continue; + /* add to static LIST_HEAD(core_pmus) or LIST_HEAD(other_pmus): */ + perf_pmu__find2(fd, dent->d_name); + } - closedir(dir); - if (list_empty(&core_pmus)) { + close(fd); + } +skip_pe_pmus: + if ((to_read_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK) && list_empty(&core_pmus)) { if (!perf_pmu__create_placeholder_core_pmu(&core_pmus)) pr_err("Failure to set up any core PMUs\n"); } list_sort(NULL, &core_pmus, pmus_cmp); - if (!core_only) { - tool_pmu = perf_pmus__tool_pmu(); - list_add_tail(&tool_pmu->list, &other_pmus); - perf_pmus__read_hwmon_pmus(&other_pmus); + + if ((to_read_types & PERF_TOOL_PMU_TYPE_TOOL_MASK) != 0 && + (read_pmu_types & PERF_TOOL_PMU_TYPE_TOOL_MASK) == 0) { + tool_pmu = tool_pmu__new(); + if (tool_pmu) + list_add_tail(&tool_pmu->list, &other_pmus); } + if ((to_read_types & PERF_TOOL_PMU_TYPE_HWMON_MASK) != 0 && + (read_pmu_types & PERF_TOOL_PMU_TYPE_HWMON_MASK) == 0) + perf_pmus__read_hwmon_pmus(&other_pmus); + list_sort(NULL, &other_pmus, pmus_cmp); - if (!list_empty(&core_pmus)) { - read_sysfs_core_pmus = true; - if (!core_only) - read_sysfs_all_pmus = true; - } + + read_pmu_types |= to_read_types; } static struct perf_pmu *__perf_pmus__find_by_type(unsigned int type) @@ -263,12 +295,21 @@ static struct perf_pmu *__perf_pmus__find_by_type(unsigned int type) struct perf_pmu *perf_pmus__find_by_type(unsigned int type) { + unsigned int to_read_pmus; struct perf_pmu *pmu = __perf_pmus__find_by_type(type); - if (pmu || read_sysfs_all_pmus) + if (pmu || (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK)) return pmu; - pmu_read_sysfs(/*core_only=*/false); + if (type >= PERF_PMU_TYPE_PE_START && type <= PERF_PMU_TYPE_PE_END) { + to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK | + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK; + } else if (type >= PERF_PMU_TYPE_HWMON_START && type <= PERF_PMU_TYPE_HWMON_END) { + to_read_pmus = PERF_TOOL_PMU_TYPE_HWMON_MASK; + } else { + to_read_pmus = PERF_TOOL_PMU_TYPE_TOOL_MASK; + } + pmu_read_sysfs(to_read_pmus); pmu = __perf_pmus__find_by_type(type); return pmu; } @@ -282,7 +323,7 @@ struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu) bool use_core_pmus = !pmu || pmu->is_core; if (!pmu) { - pmu_read_sysfs(/*core_only=*/false); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_ALL_MASK); pmu = list_prepare_entry(pmu, &core_pmus, list); } if (use_core_pmus) { @@ -300,7 +341,7 @@ struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu) struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu) { if (!pmu) { - pmu_read_sysfs(/*core_only=*/true); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_PE_CORE_MASK); return list_first_entry_or_null(&core_pmus, typeof(*pmu), list); } list_for_each_entry_continue(pmu, &core_pmus, list) @@ -316,7 +357,7 @@ static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu) const char *last_pmu_name = (pmu && pmu->name) ? pmu->name : ""; if (!pmu) { - pmu_read_sysfs(/*core_only=*/false); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_ALL_MASK); pmu = list_prepare_entry(pmu, &core_pmus, list); } else last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: ""); @@ -674,47 +715,28 @@ bool perf_pmus__supports_extended_type(void) return perf_pmus__do_support_extended_type; } -char *perf_pmus__default_pmu_name(void) -{ - int fd; - DIR *dir; - struct dirent *dent; - char *result = NULL; - - if (!list_empty(&core_pmus)) - return strdup(list_first_entry(&core_pmus, struct perf_pmu, list)->name); - - fd = perf_pmu__event_source_devices_fd(); - if (fd < 0) - return strdup("cpu"); - - dir = fdopendir(fd); - if (!dir) { - close(fd); - return strdup("cpu"); - } - - while ((dent = readdir(dir))) { - if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) - continue; - if (is_pmu_core(dent->d_name)) { - result = strdup(dent->d_name); - break; - } - } - - closedir(dir); - return result ?: strdup("cpu"); -} - struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) { struct perf_pmu *pmu = evsel->pmu; + bool legacy_core_type; - if (!pmu) { - pmu = perf_pmus__find_by_type(evsel->core.attr.type); - ((struct evsel *)evsel)->pmu = pmu; + if (pmu) + return pmu; + + pmu = perf_pmus__find_by_type(evsel->core.attr.type); + legacy_core_type = + evsel->core.attr.type == PERF_TYPE_HARDWARE || + evsel->core.attr.type == PERF_TYPE_HW_CACHE; + if (!pmu && legacy_core_type) { + if (perf_pmus__supports_extended_type()) { + u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT; + + pmu = perf_pmus__find_by_type(type); + } else { + pmu = perf_pmus__find_core_pmu(); + } } + ((struct evsel *)evsel)->pmu = pmu; return pmu; } diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h index a0cb0eb2ff97..8def20e615ad 100644 --- a/tools/perf/util/pmus.h +++ b/tools/perf/util/pmus.h @@ -27,7 +27,6 @@ void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, voi bool perf_pmus__have_event(const char *pname, const char *name); int perf_pmus__num_core_pmus(void); bool perf_pmus__supports_extended_type(void); -char *perf_pmus__default_pmu_name(void); struct perf_pmu *perf_pmus__add_test_pmu(int test_sysfs_dirfd, const char *name); struct perf_pmu *perf_pmus__add_test_hwmon_pmu(int hwmon_dir, diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1e769b68da37..3cc7c40f5097 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -973,6 +973,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) pr_debug("Matched function: %s [%lx]\n", dwarf_diename(sp_die), (unsigned long)dwarf_dieoffset(sp_die)); pf->fname = fname; + pf->abstrace_dieoffset = dwarf_dieoffset(sp_die); if (pp->line) { /* Function relative line */ dwarf_decl_line(sp_die, &pf->lno); pf->lno += pp->line; @@ -1179,6 +1180,8 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data) struct local_vars_finder *vf = data; struct probe_finder *pf = vf->pf; int tag; + Dwarf_Attribute attr; + Dwarf_Die var_die; tag = dwarf_tag(die_mem); if (tag == DW_TAG_formal_parameter || @@ -1196,10 +1199,22 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data) } } - if (dwarf_haspc(die_mem, vf->pf->addr)) + if (dwarf_haspc(die_mem, vf->pf->addr)) { + /* + * when DW_AT_entry_pc contains instruction address, + * also check if the DW_AT_abstract_origin of die_mem + * points to correct die. + */ + if (dwarf_attr(die_mem, DW_AT_abstract_origin, &attr)) { + dwarf_formref_die(&attr, &var_die); + if (pf->abstrace_dieoffset != dwarf_dieoffset(&var_die)) + goto out; + } return DIE_FIND_CB_CONTINUE; - else - return DIE_FIND_CB_SIBLING; + } + +out: + return DIE_FIND_CB_SIBLING; } static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf, diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index dcf6cc1e1cbe..ecd6d937c592 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -63,6 +63,7 @@ struct probe_finder { const char *fname; /* Real file name */ Dwarf_Die cu_die; /* Current CU */ Dwarf_Die sp_die; + Dwarf_Off abstrace_dieoffset; struct intlist *lcache; /* Line cache for lazy match */ /* For variable searching */ diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c index a1d1e4ef6257..141ffa129c69 100644 --- a/tools/perf/util/pstack.c +++ b/tools/perf/util/pstack.c @@ -63,20 +63,6 @@ void pstack__push(struct pstack *pstack, void *key) pstack->entries[pstack->top++] = key; } -void *pstack__pop(struct pstack *pstack) -{ - void *ret; - - if (pstack->top == 0) { - pr_err("%s: underflow!\n", __func__); - return NULL; - } - - ret = pstack->entries[--pstack->top]; - pstack->entries[pstack->top] = NULL; - return ret; -} - void *pstack__peek(struct pstack *pstack) { if (pstack->top == 0) diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h index 8729b8be061d..712051b8130f 100644 --- a/tools/perf/util/pstack.h +++ b/tools/perf/util/pstack.h @@ -10,7 +10,6 @@ void pstack__delete(struct pstack *pstack); bool pstack__empty(const struct pstack *pstack); void pstack__remove(struct pstack *pstack, void *key); void pstack__push(struct pstack *pstack, void *key); -void *pstack__pop(struct pstack *pstack); void *pstack__peek(struct pstack *pstack); #endif /* _PERF_PSTACK_ */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index b4bc57859f73..f3c05da25b4a 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -9,10 +9,12 @@ #include <event-parse.h> #endif #include <perf/mmap.h> +#include "callchain.h" #include "evlist.h" #include "evsel.h" #include "event.h" #include "print_binary.h" +#include "record.h" #include "strbuf.h" #include "thread_map.h" #include "trace-event.h" @@ -20,13 +22,6 @@ #include "util/sample.h" #include <internal/lib.h> -#define _PyUnicode_FromString(arg) \ - PyUnicode_FromString(arg) -#define _PyUnicode_FromFormat(...) \ - PyUnicode_FromFormat(__VA_ARGS__) -#define _PyLong_FromLong(arg) \ - PyLong_FromLong(arg) - PyMODINIT_FUNC PyInit_perf(void); #define member_def(type, member, ptype, help) \ @@ -47,7 +42,7 @@ struct pyrf_event { }; #define sample_members \ - sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \ + sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"), \ sample_member_def(sample_pid, pid, T_INT, "event pid"), \ sample_member_def(sample_tid, tid, T_INT, "event tid"), \ sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \ @@ -270,6 +265,12 @@ static PyMemberDef pyrf_sample_event__members[] = { { .name = NULL, }, }; +static void pyrf_sample_event__delete(struct pyrf_event *pevent) +{ + perf_sample__exit(&pevent->sample); + Py_TYPE(pevent)->tp_free((PyObject*)pevent); +} + static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent) { PyObject *ret; @@ -336,23 +337,14 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) { const char *str = _PyUnicode_AsString(PyObject_Str(attr_name)); struct evsel *evsel = pevent->evsel; + struct tep_event *tp_format = evsel__tp_format(evsel); struct tep_format_field *field; - if (!evsel->tp_format) { - struct tep_event *tp_format; - - tp_format = trace_event__tp_format_id(evsel->core.attr.config); - if (IS_ERR_OR_NULL(tp_format)) - return NULL; - - evsel->tp_format = tp_format; - } - - field = tep_find_any_field(evsel->tp_format, str); - if (!field) + if (IS_ERR_OR_NULL(tp_format)) return NULL; - return tracepoint_field(pevent, field); + field = tep_find_any_field(tp_format, str); + return field ? tracepoint_field(pevent, field) : NULL; } #endif /* HAVE_LIBTRACEEVENT */ @@ -428,6 +420,9 @@ static int pyrf_event__setup_types(void) pyrf_sample_event__type.tp_new = pyrf_context_switch_event__type.tp_new = pyrf_throttle_event__type.tp_new = PyType_GenericNew; + + pyrf_sample_event__type.tp_dealloc = (destructor)pyrf_sample_event__delete, + err = PyType_Ready(&pyrf_mmap_event__type); if (err < 0) goto out; @@ -481,6 +476,11 @@ static PyObject *pyrf_event__new(const union perf_event *event) event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)) return NULL; + // FIXME this better be dynamic or we need to parse everything + // before calling perf_mmap__consume(), including tracepoint fields. + if (sizeof(pevent->event) < event->header.size) + return NULL; + ptype = pyrf_event__type[event->header.type]; pevent = PyObject_New(struct pyrf_event, ptype); if (pevent != NULL) @@ -802,6 +802,28 @@ static PyMethodDef pyrf_evsel__methods[] = { { .ml_name = NULL, } }; +#define evsel_member_def(member, ptype, help) \ + { #member, ptype, \ + offsetof(struct pyrf_evsel, evsel.member), \ + 0, help } + +#define evsel_attr_member_def(member, ptype, help) \ + { #member, ptype, \ + offsetof(struct pyrf_evsel, evsel.core.attr.member), \ + 0, help } + +static PyMemberDef pyrf_evsel__members[] = { + evsel_member_def(tracking, T_BOOL, "tracking event."), + evsel_attr_member_def(type, T_UINT, "attribute type."), + evsel_attr_member_def(size, T_UINT, "attribute size."), + evsel_attr_member_def(config, T_ULONGLONG, "attribute config."), + evsel_attr_member_def(sample_period, T_ULONGLONG, "attribute sample_period."), + evsel_attr_member_def(sample_type, T_ULONGLONG, "attribute sample_type."), + evsel_attr_member_def(read_format, T_ULONGLONG, "attribute read_format."), + evsel_attr_member_def(wakeup_events, T_UINT, "attribute wakeup_events."), + { .name = NULL, }, +}; + static const char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); static PyTypeObject pyrf_evsel__type = { @@ -811,6 +833,7 @@ static PyTypeObject pyrf_evsel__type = { .tp_dealloc = (destructor)pyrf_evsel__delete, .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, .tp_doc = pyrf_evsel__doc, + .tp_members = pyrf_evsel__members, .tp_methods = pyrf_evsel__methods, .tp_init = (initproc)pyrf_evsel__init, .tp_str = pyrf_evsel__str, @@ -851,6 +874,16 @@ static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) Py_TYPE(pevlist)->tp_free((PyObject*)pevlist); } +static PyObject *pyrf_evlist__all_cpus(struct pyrf_evlist *pevlist) +{ + struct pyrf_cpu_map *pcpu_map = PyObject_New(struct pyrf_cpu_map, &pyrf_cpu_map__type); + + if (pcpu_map) + pcpu_map->cpus = perf_cpu_map__get(pevlist->evlist.core.all_cpus); + + return (PyObject *)pcpu_map; +} + static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { @@ -984,20 +1017,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, evsel = evlist__event2evsel(evlist, event); if (!evsel) { + Py_DECREF(pyevent); Py_INCREF(Py_None); return Py_None; } pevent->evsel = evsel; - err = evsel__parse_sample(evsel, event, &pevent->sample); - - /* Consume the even only after we parsed it out. */ perf_mmap__consume(&md->core); - if (err) + err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample); + if (err) { + Py_DECREF(pyevent); return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); + } + return pyevent; } end: @@ -1019,8 +1054,53 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, return Py_None; } +static PyObject *pyrf_evlist__config(struct pyrf_evlist *pevlist) +{ + struct record_opts opts = { + .sample_time = true, + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, + .target = { + .uses_mmap = true, + .default_per_cpu = true, + }, + .nr_threads_synthesize = 1, + .ctl_fd = -1, + .ctl_fd_ack = -1, + .no_buffering = true, + .no_inherit = true, + }; + struct evlist *evlist = &pevlist->evlist; + + evlist__config(evlist, &opts, &callchain_param); + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__disable(struct pyrf_evlist *pevlist) +{ + evlist__disable(&pevlist->evlist); + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__enable(struct pyrf_evlist *pevlist) +{ + evlist__enable(&pevlist->evlist); + Py_INCREF(Py_None); + return Py_None; +} + static PyMethodDef pyrf_evlist__methods[] = { { + .ml_name = "all_cpus", + .ml_meth = (PyCFunction)pyrf_evlist__all_cpus, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("CPU map union of all evsel CPU maps.") + }, + { .ml_name = "mmap", .ml_meth = (PyCFunction)pyrf_evlist__mmap, .ml_flags = METH_VARARGS | METH_KEYWORDS, @@ -1056,6 +1136,24 @@ static PyMethodDef pyrf_evlist__methods[] = { .ml_flags = METH_VARARGS | METH_KEYWORDS, .ml_doc = PyDoc_STR("reads an event.") }, + { + .ml_name = "config", + .ml_meth = (PyCFunction)pyrf_evlist__config, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Apply default record options to the evlist.") + }, + { + .ml_name = "disable", + .ml_meth = (PyCFunction)pyrf_evlist__disable, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Disable the evsels in the evlist.") + }, + { + .ml_name = "enable", + .ml_meth = (PyCFunction)pyrf_evlist__enable, + .ml_flags = METH_NOARGS, + .ml_doc = PyDoc_STR("Enable the evsels in the evlist.") + }, { .ml_name = NULL, } }; @@ -1254,6 +1352,8 @@ static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel) evsel__init(&pevsel->evsel, &evsel->core.attr, evsel->core.idx); evsel__clone(&pevsel->evsel, evsel); + if (evsel__is_group_leader(evsel)) + evsel__set_leader(&pevsel->evsel, &pevsel->evsel); return (PyObject *)pevsel; } @@ -1281,12 +1381,18 @@ static PyObject *pyrf__parse_events(PyObject *self, PyObject *args) struct evlist evlist = {}; struct parse_events_error err; PyObject *result; + PyObject *pcpus = NULL, *pthreads = NULL; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; - if (!PyArg_ParseTuple(args, "s", &input)) + if (!PyArg_ParseTuple(args, "s|OO", &input, &pcpus, &pthreads)) return NULL; + threads = pthreads ? ((struct pyrf_thread_map *)pthreads)->threads : NULL; + cpus = pcpus ? ((struct pyrf_cpu_map *)pcpus)->cpus : NULL; + parse_events_error__init(&err); - evlist__init(&evlist, NULL, NULL); + evlist__init(&evlist, cpus, threads); if (parse_events(&evlist, input, &err)) { parse_events_error__print(&err, input); PyErr_SetFromErrno(PyExc_OSError); diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h deleted file mode 100644 index d927a0d25052..000000000000 --- a/tools/perf/util/rb_resort.h +++ /dev/null @@ -1,146 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _PERF_RESORT_RB_H_ -#define _PERF_RESORT_RB_H_ -/* - * Template for creating a class to resort an existing rb_tree according to - * a new sort criteria, that must be present in the entries of the source - * rb_tree. - * - * (c) 2016 Arnaldo Carvalho de Melo <acme@redhat.com> - * - * Quick example, resorting threads by its shortname: - * - * First define the prefix (threads) to be used for the functions and data - * structures created, and provide an expression for the sorting, then the - * fields to be present in each of the entries in the new, sorted, rb_tree. - * - * The body of the init function should collect the fields, maybe - * pre-calculating them from multiple entries in the original 'entry' from - * the rb_tree used as a source for the entries to be sorted: - -DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname, - b->thread->shortname) < 0, - struct thread *thread; -) -{ - entry->thread = rb_entry(nd, struct thread, rb_node); -} - - * After this it is just a matter of instantiating it and iterating it, - * for a few data structures with existing rb_trees, such as 'struct machine', - * helpers are available to get the rb_root and the nr_entries: - - DECLARE_RESORT_RB_MACHINE_THREADS(threads, machine_ptr); - - * This will instantiate the new rb_tree and a cursor for it, that can be used as: - - struct rb_node *nd; - - resort_rb__for_each_entry(nd, threads) { - struct thread *t = threads_entry; - printf("%s: %d\n", t->shortname, t->tid); - } - - * Then delete it: - - resort_rb__delete(threads); - - * The name of the data structures and functions will have a _sorted suffix - * right before the method names, i.e. will look like: - * - * struct threads_sorted_entry {} - * threads_sorted__insert() - */ - -#define DEFINE_RESORT_RB(__name, __comp, ...) \ -struct __name##_sorted_entry { \ - struct rb_node rb_node; \ - __VA_ARGS__ \ -}; \ -static void __name##_sorted__init_entry(struct rb_node *nd, \ - struct __name##_sorted_entry *entry); \ - \ -static int __name##_sorted__cmp(struct rb_node *nda, struct rb_node *ndb) \ -{ \ - struct __name##_sorted_entry *a, *b; \ - a = rb_entry(nda, struct __name##_sorted_entry, rb_node); \ - b = rb_entry(ndb, struct __name##_sorted_entry, rb_node); \ - return __comp; \ -} \ - \ -struct __name##_sorted { \ - struct rb_root entries; \ - struct __name##_sorted_entry nd[0]; \ -}; \ - \ -static void __name##_sorted__insert(struct __name##_sorted *sorted, \ - struct rb_node *sorted_nd) \ -{ \ - struct rb_node **p = &sorted->entries.rb_node, *parent = NULL; \ - while (*p != NULL) { \ - parent = *p; \ - if (__name##_sorted__cmp(sorted_nd, parent)) \ - p = &(*p)->rb_left; \ - else \ - p = &(*p)->rb_right; \ - } \ - rb_link_node(sorted_nd, parent, p); \ - rb_insert_color(sorted_nd, &sorted->entries); \ -} \ - \ -static void __name##_sorted__sort(struct __name##_sorted *sorted, \ - struct rb_root *entries) \ -{ \ - struct rb_node *nd; \ - unsigned int i = 0; \ - for (nd = rb_first(entries); nd; nd = rb_next(nd)) { \ - struct __name##_sorted_entry *snd = &sorted->nd[i++]; \ - __name##_sorted__init_entry(nd, snd); \ - __name##_sorted__insert(sorted, &snd->rb_node); \ - } \ -} \ - \ -static struct __name##_sorted *__name##_sorted__new(struct rb_root *entries, \ - int nr_entries) \ -{ \ - struct __name##_sorted *sorted; \ - sorted = malloc(sizeof(*sorted) + sizeof(sorted->nd[0]) * nr_entries); \ - if (sorted) { \ - sorted->entries = RB_ROOT; \ - __name##_sorted__sort(sorted, entries); \ - } \ - return sorted; \ -} \ - \ -static void __name##_sorted__delete(struct __name##_sorted *sorted) \ -{ \ - free(sorted); \ -} \ - \ -static void __name##_sorted__init_entry(struct rb_node *nd, \ - struct __name##_sorted_entry *entry) - -#define DECLARE_RESORT_RB(__name) \ -struct __name##_sorted_entry *__name##_entry; \ -struct __name##_sorted *__name = __name##_sorted__new - -#define resort_rb__for_each_entry(__nd, __name) \ - for (__nd = rb_first(&__name->entries); \ - __name##_entry = rb_entry(__nd, struct __name##_sorted_entry, \ - rb_node), __nd; \ - __nd = rb_next(__nd)) - -#define resort_rb__delete(__name) \ - __name##_sorted__delete(__name), __name = NULL - -/* - * Helpers for other classes that contains both an rbtree and the - * number of entries in it: - */ - -/* For 'struct intlist' */ -#define DECLARE_RESORT_RB_INTLIST(__name, __ilist) \ - DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries.rb_root, \ - __ilist->rblist.nr_entries) - -#endif /* _PERF_RESORT_RB_H_ */ diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 30638653ad2d..0ce52f0280b8 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -513,6 +513,7 @@ static bool s390_cpumsf_make_event(size_t pos, .period = 1 }; union perf_event event; + int ret; memset(&event, 0, sizeof(event)); if (basic->CL == 1) /* Native LPAR mode */ @@ -536,8 +537,9 @@ static bool s390_cpumsf_make_event(size_t pos, pr_debug4("%s pos:%#zx ip:%#" PRIx64 " P:%d CL:%d pid:%d.%d cpumode:%d cpu:%d\n", __func__, pos, sample.ip, basic->P, basic->CL, sample.pid, sample.tid, sample.cpumode, sample.cpu); - if (perf_session__deliver_synth_event(sfq->sf->session, &event, - &sample)) { + ret = perf_session__deliver_synth_event(sfq->sf->session, &event, &sample); + perf_sample__exit(&sample); + if (ret) { pr_err("s390 Auxiliary Trace: failed to deliver event\n"); return false; } diff --git a/tools/perf/util/sample.c b/tools/perf/util/sample.c new file mode 100644 index 000000000000..605fee971f55 --- /dev/null +++ b/tools/perf/util/sample.c @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include "sample.h" +#include "debug.h" +#include <linux/zalloc.h> +#include <stdlib.h> +#include <string.h> + +void perf_sample__init(struct perf_sample *sample, bool all) +{ + if (all) { + memset(sample, 0, sizeof(*sample)); + } else { + sample->user_regs = NULL; + sample->intr_regs = NULL; + } +} + +void perf_sample__exit(struct perf_sample *sample) +{ + free(sample->user_regs); + free(sample->intr_regs); +} + +struct regs_dump *perf_sample__user_regs(struct perf_sample *sample) +{ + if (!sample->user_regs) { + sample->user_regs = zalloc(sizeof(*sample->user_regs)); + if (!sample->user_regs) + pr_err("Failure to allocate sample user_regs"); + } + return sample->user_regs; +} + + +struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample) +{ + if (!sample->intr_regs) { + sample->intr_regs = zalloc(sizeof(*sample->intr_regs)); + if (!sample->intr_regs) + pr_err("Failure to allocate sample intr_regs"); + } + return sample->intr_regs; +} diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h index 70b2c3135555..0e96240052e9 100644 --- a/tools/perf/util/sample.h +++ b/tools/perf/util/sample.h @@ -67,7 +67,7 @@ struct aux_sample { }; struct simd_flags { - u64 arch:1, /* architecture (isa) */ + u8 arch:1, /* architecture (isa) */ pred:2; /* predication */ }; @@ -114,14 +114,19 @@ struct perf_sample { struct ip_callchain *callchain; struct branch_stack *branch_stack; u64 *branch_stack_cntr; - struct regs_dump user_regs; - struct regs_dump intr_regs; + struct regs_dump *user_regs; + struct regs_dump *intr_regs; struct stack_dump user_stack; struct sample_read read; struct aux_sample aux_sample; struct simd_flags simd_flags; }; +void perf_sample__init(struct perf_sample *sample, bool all); +void perf_sample__exit(struct perf_sample *sample); +struct regs_dump *perf_sample__user_regs(struct perf_sample *sample); +struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample); + /* * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get * 8-byte alignment. diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index b1b5e94537e4..520729e78965 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -745,19 +745,30 @@ static int set_regs_in_dict(PyObject *dict, const char *arch = perf_env__arch(evsel__env(evsel)); int size = (__sw_hweight64(attr->sample_regs_intr) * MAX_REG_SIZE) + 1; - char *bf = malloc(size); - if (!bf) - return -1; + char *bf = NULL; - regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size); + if (sample->intr_regs) { + bf = malloc(size); + if (!bf) + return -1; - pydict_set_item_string_decref(dict, "iregs", - _PyUnicode_FromString(bf)); + regs_map(sample->intr_regs, attr->sample_regs_intr, arch, bf, size); - regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, size); + pydict_set_item_string_decref(dict, "iregs", + _PyUnicode_FromString(bf)); + } - pydict_set_item_string_decref(dict, "uregs", - _PyUnicode_FromString(bf)); + if (sample->user_regs) { + if (!bf) { + bf = malloc(size); + if (!bf) + return -1; + } + regs_map(sample->user_regs, attr->sample_regs_user, arch, bf, size); + + pydict_set_item_string_decref(dict, "uregs", + _PyUnicode_FromString(bf)); + } free(bf); return 0; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c06e3020a976..60fb9997ea0d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -950,7 +950,12 @@ static void regs__printf(const char *type, struct regs_dump *regs, const char *a static void regs_user__printf(struct perf_sample *sample, const char *arch) { - struct regs_dump *user_regs = &sample->user_regs; + struct regs_dump *user_regs; + + if (!sample->user_regs) + return; + + user_regs = perf_sample__user_regs(sample); if (user_regs->regs) regs__printf("user", user_regs, arch); @@ -958,7 +963,12 @@ static void regs_user__printf(struct perf_sample *sample, const char *arch) static void regs_intr__printf(struct perf_sample *sample, const char *arch) { - struct regs_dump *intr_regs = &sample->intr_regs; + struct regs_dump *intr_regs; + + if (!sample->intr_regs) + return; + + intr_regs = perf_sample__intr_regs(sample); if (intr_regs->regs) regs__printf("intr", intr_regs, arch); @@ -1351,25 +1361,30 @@ static int perf_session__deliver_event(struct perf_session *session, const char *file_path) { struct perf_sample sample; - int ret = evlist__parse_sample(session->evlist, event, &sample); + int ret; + perf_sample__init(&sample, /*all=*/false); + ret = evlist__parse_sample(session->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); - return ret; + goto out; } ret = auxtrace__process_event(session, event, &sample, tool); if (ret < 0) - return ret; - if (ret > 0) - return 0; + goto out; + if (ret > 0) { + ret = 0; + goto out; + } ret = machines__deliver_event(&session->machines, session->evlist, event, &sample, tool, file_offset, file_path); if (dump_trace && sample.aux_sample.size) auxtrace__dump_auxtrace_sample(session, &sample); - +out: + perf_sample__exit(&sample); return ret; } @@ -1380,10 +1395,11 @@ static s64 perf_session__process_user_event(struct perf_session *session, { struct ordered_events *oe = &session->ordered_events; const struct perf_tool *tool = session->tool; - struct perf_sample sample = { .time = 0, }; + struct perf_sample sample; int fd = perf_data__fd(session->data); int err; + perf_sample__init(&sample, /*all=*/true); if (event->header.type != PERF_RECORD_COMPRESSED || perf_tool__compressed_is_stub(tool)) dump_event(session->evlist, event, file_offset, &sample, file_path); @@ -1395,15 +1411,17 @@ static s64 perf_session__process_user_event(struct perf_session *session, perf_session__set_id_hdr_size(session); perf_session__set_comm_exec(session); } - return err; + break; case PERF_RECORD_EVENT_UPDATE: - return tool->event_update(tool, event, &session->evlist); + err = tool->event_update(tool, event, &session->evlist); + break; case PERF_RECORD_HEADER_EVENT_TYPE: /* * Deprecated, but we need to handle it for sake * of old data files create in pipe mode. */ - return 0; + err = 0; + break; case PERF_RECORD_HEADER_TRACING_DATA: /* * Setup for reading amidst mmap, but only when we @@ -1412,15 +1430,20 @@ static s64 perf_session__process_user_event(struct perf_session *session, */ if (!perf_data__is_pipe(session->data)) lseek(fd, file_offset, SEEK_SET); - return tool->tracing_data(session, event); + err = tool->tracing_data(session, event); + break; case PERF_RECORD_HEADER_BUILD_ID: - return tool->build_id(session, event); + err = tool->build_id(session, event); + break; case PERF_RECORD_FINISHED_ROUND: - return tool->finished_round(tool, event, oe); + err = tool->finished_round(tool, event, oe); + break; case PERF_RECORD_ID_INDEX: - return tool->id_index(session, event); + err = tool->id_index(session, event); + break; case PERF_RECORD_AUXTRACE_INFO: - return tool->auxtrace_info(session, event); + err = tool->auxtrace_info(session, event); + break; case PERF_RECORD_AUXTRACE: /* * Setup for reading amidst mmap, but only when we @@ -1429,35 +1452,48 @@ static s64 perf_session__process_user_event(struct perf_session *session, */ if (!perf_data__is_pipe(session->data)) lseek(fd, file_offset + event->header.size, SEEK_SET); - return tool->auxtrace(session, event); + err = tool->auxtrace(session, event); + break; case PERF_RECORD_AUXTRACE_ERROR: perf_session__auxtrace_error_inc(session, event); - return tool->auxtrace_error(session, event); + err = tool->auxtrace_error(session, event); + break; case PERF_RECORD_THREAD_MAP: - return tool->thread_map(session, event); + err = tool->thread_map(session, event); + break; case PERF_RECORD_CPU_MAP: - return tool->cpu_map(session, event); + err = tool->cpu_map(session, event); + break; case PERF_RECORD_STAT_CONFIG: - return tool->stat_config(session, event); + err = tool->stat_config(session, event); + break; case PERF_RECORD_STAT: - return tool->stat(session, event); + err = tool->stat(session, event); + break; case PERF_RECORD_STAT_ROUND: - return tool->stat_round(session, event); + err = tool->stat_round(session, event); + break; case PERF_RECORD_TIME_CONV: session->time_conv = event->time_conv; - return tool->time_conv(session, event); + err = tool->time_conv(session, event); + break; case PERF_RECORD_HEADER_FEATURE: - return tool->feature(session, event); + err = tool->feature(session, event); + break; case PERF_RECORD_COMPRESSED: err = tool->compressed(session, event, file_offset, file_path); if (err) dump_event(session->evlist, event, file_offset, &sample, file_path); - return err; + break; case PERF_RECORD_FINISHED_INIT: - return tool->finished_init(session, event); + err = tool->finished_init(session, event); + break; default: - return -EINVAL; + err = -EINVAL; + break; } + perf_sample__exit(&sample); + return err; } int perf_session__deliver_synth_event(struct perf_session *session, @@ -2403,6 +2439,18 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg) return false; } +bool perf_session__has_switch_events(struct perf_session *session) +{ + struct evsel *evsel; + + evlist__for_each_entry(session->evlist, evsel) { + if (evsel->core.attr.context_switch) + return true; + } + + return false; +} + int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr) { char *bracket; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index bcf1bcf06959..db1c120a9e67 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -141,6 +141,7 @@ int perf_session__resolve_callchain(struct perf_session *session, struct symbol **parent); bool perf_session__has_traces(struct perf_session *session, const char *msg); +bool perf_session__has_switch_events(struct perf_session *session); void perf_event__attr_swap(struct perf_event_attr *attr); diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 649550e9b7aa..dd289d15acfd 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -3,6 +3,7 @@ from subprocess import Popen, PIPE from re import sub cc = getenv("CC") +assert cc, "Environment variable CC not set" # Check if CC has options, as is the case in yocto, where it uses CC="cc --sysroot..." cc_tokens = cc.split() @@ -12,8 +13,13 @@ if len(cc_tokens) > 1: else: cc_options = "" +# ignore optional stderr could be None as it is set to PIPE to avoid that. +# mypy: disable-error-code="union-attr" cc_is_clang = b"clang version" in Popen([cc, "-v"], stderr=PIPE).stderr.readline() -src_feature_tests = getenv('srctree') + '/tools/build/feature' + +srctree = getenv('srctree') +assert srctree, "Environment variable srctree, for the Linux sources, not set" +src_feature_tests = f'{srctree}/tools/build/feature' def clang_has_option(option): cc_output = Popen([cc, cc_options + option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() @@ -71,7 +77,7 @@ else: # The python headers have mixed code with declarations (decls after asserts, for instance) cflags += [ "-Wno-declaration-after-statement" ] -src_perf = getenv('srctree') + '/tools/perf' +src_perf = f'{srctree}/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') build_tmp = getenv('PYTHON_EXTBUILD_TMP') diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 3dd33721823f..c51049087e4e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -892,6 +892,38 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; +/* --sort parallelism */ + +static int64_t +sort__parallelism_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->parallelism - left->parallelism; +} + +static int hist_entry__parallelism_filter(struct hist_entry *he, int type, const void *arg) +{ + const unsigned long *parallelism_filter = arg; + + if (type != HIST_FILTER__PARALLELISM) + return -1; + + return test_bit(he->parallelism, parallelism_filter); +} + +static int hist_entry__parallelism_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%*d", width, he->parallelism); +} + +struct sort_entry sort_parallelism = { + .se_header = "Parallelism", + .se_cmp = sort__parallelism_cmp, + .se_filter = hist_entry__parallelism_filter, + .se_snprintf = hist_entry__parallelism_snprintf, + .se_width_idx = HISTC_PARALLELISM, +}; + /* --sort cgroup_id */ static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev) @@ -2371,44 +2403,19 @@ sort__typeoff_sort(struct hist_entry *left, struct hist_entry *right) return left->mem_type_off - right->mem_type_off; } -static void fill_member_name(char *buf, size_t sz, struct annotated_member *m, - int offset, bool first) -{ - struct annotated_member *child; - - if (list_empty(&m->children)) - return; - - list_for_each_entry(child, &m->children, node) { - if (child->offset <= offset && offset < child->offset + child->size) { - int len = 0; - - /* It can have anonymous struct/union members */ - if (child->var_name) { - len = scnprintf(buf, sz, "%s%s", - first ? "" : ".", child->var_name); - first = false; - } - - fill_member_name(buf + len, sz - len, child, offset, first); - return; - } - } -} - static int hist_entry__typeoff_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width __maybe_unused) { struct annotated_data_type *he_type = he->mem_type; char buf[4096]; - buf[0] = '\0'; - if (list_empty(&he_type->self.children)) - snprintf(buf, sizeof(buf), "no field"); - else - fill_member_name(buf, sizeof(buf), &he_type->self, - he->mem_type_off, true); - buf[4095] = '\0'; + if (he_type == &unknown_type || he_type == &stackop_type || + he_type == &canary_type) + return repsep_snprintf(bf, size, "%s", he_type->self.type_name); + + if (!annotated_data_type__get_member_name(he_type, buf, sizeof(buf), + he->mem_type_off)) + scnprintf(buf, sizeof(buf), "no field"); return repsep_snprintf(bf, size, "%s +%#x (%s)", he_type->self.type_name, he->mem_type_off, buf); @@ -2534,6 +2541,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_ANNOTATE_DATA_TYPE_OFFSET, "typeoff", sort_type_offset), DIM(SORT_SYM_OFFSET, "symoff", sort_sym_offset), DIM(SORT_ANNOTATE_DATA_TYPE_CACHELINE, "typecln", sort_type_cacheline), + DIM(SORT_PARALLELISM, "parallelism", sort_parallelism), }; #undef DIM @@ -2589,17 +2597,20 @@ struct hpp_dimension { const char *name; struct perf_hpp_fmt *fmt; int taken; + int was_taken; }; #define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], } static struct hpp_dimension hpp_sort_dimensions[] = { DIM(PERF_HPP__OVERHEAD, "overhead"), + DIM(PERF_HPP__LATENCY, "latency"), DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"), DIM(PERF_HPP__OVERHEAD_US, "overhead_us"), DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"), DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"), DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"), + DIM(PERF_HPP__LATENCY_ACC, "latency_children"), DIM(PERF_HPP__SAMPLES, "sample"), DIM(PERF_HPP__PERIOD, "period"), DIM(PERF_HPP__WEIGHT1, "weight1"), @@ -2735,6 +2746,7 @@ MK_SORT_ENTRY_CHK(thread) MK_SORT_ENTRY_CHK(comm) MK_SORT_ENTRY_CHK(dso) MK_SORT_ENTRY_CHK(sym) +MK_SORT_ENTRY_CHK(parallelism) static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) @@ -3477,6 +3489,7 @@ static int __hpp_dimension__add(struct hpp_dimension *hd, return -1; hd->taken = 1; + hd->was_taken = 1; perf_hpp_list__register_sort_field(list, fmt); return 0; } @@ -3511,10 +3524,15 @@ static int __hpp_dimension__add_output(struct perf_hpp_list *list, return 0; } -int hpp_dimension__add_output(unsigned col) +int hpp_dimension__add_output(unsigned col, bool implicit) { + struct hpp_dimension *hd; + BUG_ON(col >= PERF_HPP__MAX_INDEX); - return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]); + hd = &hpp_sort_dimensions[col]; + if (implicit && !hd->was_taken) + return 0; + return __hpp_dimension__add_output(&perf_hpp_list, hd); } int sort_dimension__add(struct perf_hpp_list *list, const char *tok, @@ -3639,6 +3657,34 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, return -ESRCH; } +/* This should match with sort_dimension__add() above */ +static bool is_hpp_sort_key(const char *key) +{ + unsigned i; + + for (i = 0; i < ARRAY_SIZE(arch_specific_sort_keys); i++) { + if (!strcmp(arch_specific_sort_keys[i], key) && + !arch_support_sort_key(key)) { + return false; + } + } + + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; + + if (sd->name && !strncasecmp(key, sd->name, strlen(key))) + return false; + } + + for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) { + struct hpp_dimension *hd = &hpp_sort_dimensions[i]; + + if (!strncasecmp(key, hd->name, strlen(key))) + return true; + } + return false; +} + static int setup_sort_list(struct perf_hpp_list *list, char *str, struct evlist *evlist) { @@ -3646,7 +3692,9 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, int ret = 0; int level = 0; int next_level = 1; + int prev_level = 0; bool in_group = false; + bool prev_was_hpp = false; do { tok = str; @@ -3667,6 +3715,19 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, } if (*tok) { + if (is_hpp_sort_key(tok)) { + /* keep output (hpp) sort keys in the same level */ + if (prev_was_hpp) { + bool next_same = (level == next_level); + + level = prev_level; + next_level = next_same ? level : level+1; + } + prev_was_hpp = true; + } else { + prev_was_hpp = false; + } + ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok))) @@ -3678,6 +3739,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ui__error("Unknown --sort key: `%s'", tok); break; } + prev_level = level; } level = next_level; @@ -3773,10 +3835,24 @@ static char *setup_overhead(char *keys) if (sort__mode == SORT_MODE__DIFF) return keys; - keys = prefix_if_not_in("overhead", keys); - - if (symbol_conf.cumulate_callchain) - keys = prefix_if_not_in("overhead_children", keys); + if (symbol_conf.prefer_latency) { + keys = prefix_if_not_in("overhead", keys); + keys = prefix_if_not_in("latency", keys); + if (symbol_conf.cumulate_callchain) { + keys = prefix_if_not_in("overhead_children", keys); + keys = prefix_if_not_in("latency_children", keys); + } + } else if (!keys || (!strstr(keys, "overhead") && + !strstr(keys, "latency"))) { + if (symbol_conf.enable_latency) + keys = prefix_if_not_in("latency", keys); + keys = prefix_if_not_in("overhead", keys); + if (symbol_conf.cumulate_callchain) { + if (symbol_conf.enable_latency) + keys = prefix_if_not_in("latency_children", keys); + keys = prefix_if_not_in("overhead_children", keys); + } + } return keys; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index a8572574e168..180d36a2bea3 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -72,6 +72,7 @@ enum sort_type { SORT_ANNOTATE_DATA_TYPE_OFFSET, SORT_SYM_OFFSET, SORT_ANNOTATE_DATA_TYPE_CACHELINE, + SORT_PARALLELISM, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, @@ -140,7 +141,7 @@ int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, i bool is_strict_order(const char *order); -int hpp_dimension__add_output(unsigned col); +int hpp_dimension__add_output(unsigned col, bool implicit); void reset_dimensions(void); int sort_dimension__add(struct perf_hpp_list *list, const char *tok, struct evlist *evlist, diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index ba79f73e1cf5..e852ac0d9847 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -929,12 +929,16 @@ static void printout(struct perf_stat_config *config, struct outstate *os, } } -static void uniquify_event_name(struct evsel *counter) +static void evsel__uniquify_counter(struct evsel *counter) { const char *name, *pmu_name; char *new_name, *config; int ret; + /* No uniquification necessary. */ + if (!counter->needs_uniquify) + return; + /* The evsel was already uniquified. */ if (counter->uniquified_name) return; @@ -942,19 +946,6 @@ static void uniquify_event_name(struct evsel *counter) /* Avoid checking to uniquify twice. */ counter->uniquified_name = true; - /* The evsel has a "name=" config term or is from libpfm. */ - if (counter->use_config_name || counter->is_libpfm_event) - return; - - /* Legacy no PMU event, don't uniquify. */ - if (!counter->pmu || - (counter->pmu->type < PERF_TYPE_MAX && counter->pmu->type != PERF_TYPE_RAW)) - return; - - /* A sysfs or json event replacing a legacy event, don't uniquify. */ - if (counter->pmu->is_core && counter->alternate_hw_config != PERF_COUNT_HW_MAX) - return; - name = evsel__name(counter); pmu_name = counter->pmu->name; /* Already prefixed by the PMU name. */ @@ -993,17 +984,6 @@ static void uniquify_event_name(struct evsel *counter) } } -static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config) -{ - return evsel__is_hybrid(evsel) && !config->hybrid_merge; -} - -static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter) -{ - if (config->aggr_mode == AGGR_NONE || hybrid_uniquify(counter, config)) - uniquify_event_name(counter); -} - /** * should_skip_zero_count() - Check if the event should print 0 values. * @config: The perf stat configuration (including aggregation mode). @@ -1089,7 +1069,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config, if (counter->merged_stat) return; - uniquify_counter(config, counter); + evsel__uniquify_counter(counter); val = aggr->counts.val; ena = aggr->counts.ena; @@ -1670,7 +1650,8 @@ static void print_cgroup_counter(struct perf_stat_config *config, struct evlist print_metric_end(config, os); } -static void disable_uniquify(struct evlist *evlist) +/* Should uniquify be disabled for the evlist? */ +static bool evlist__disable_uniquify(const struct evlist *evlist) { struct evsel *counter; struct perf_pmu *last_pmu = NULL; @@ -1679,20 +1660,84 @@ static void disable_uniquify(struct evlist *evlist) evlist__for_each_entry(evlist, counter) { /* If PMUs vary then uniquify can be useful. */ if (!first && counter->pmu != last_pmu) - return; + return false; first = false; if (counter->pmu) { /* Allow uniquify for uncore PMUs. */ if (!counter->pmu->is_core) - return; + return false; /* Keep hybrid event names uniquified for clarity. */ if (perf_pmus__num_core_pmus() > 1) - return; + return false; + } + } + return true; +} + +static void evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_config *config) +{ + struct evsel *evsel; + + if (counter->merged_stat) { + /* Counter won't be shown. */ + return; + } + + if (counter->use_config_name || counter->is_libpfm_event) { + /* Original name will be used. */ + return; + } + + if (!config->hybrid_merge && evsel__is_hybrid(counter)) { + /* Unique hybrid counters necessary. */ + counter->needs_uniquify = true; + return; + } + + if (counter->core.attr.type < PERF_TYPE_MAX && counter->core.attr.type != PERF_TYPE_RAW) { + /* Legacy event, don't uniquify. */ + return; + } + + if (counter->pmu && counter->pmu->is_core && + counter->alternate_hw_config != PERF_COUNT_HW_MAX) { + /* A sysfs or json event replacing a legacy event, don't uniquify. */ + return; + } + + if (config->aggr_mode == AGGR_NONE) { + /* Always unique with no aggregation. */ + counter->needs_uniquify = true; + return; + } + + /* + * Do other non-merged events in the evlist have the same name? If so + * uniquify is necessary. + */ + evlist__for_each_entry(counter->evlist, evsel) { + if (evsel == counter || evsel->merged_stat) + continue; + + if (evsel__name_is(counter, evsel__name(evsel))) { + counter->needs_uniquify = true; + return; } } - evlist__for_each_entry_continue(evlist, counter) { - counter->uniquified_name = true; +} + +static void evlist__set_needs_uniquify(struct evlist *evlist, const struct perf_stat_config *config) +{ + struct evsel *counter; + + if (evlist__disable_uniquify(evlist)) { + evlist__for_each_entry(evlist, counter) + counter->uniquified_name = true; + return; } + + evlist__for_each_entry(evlist, counter) + evsel__set_needs_uniquify(counter, config); } void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, @@ -1706,7 +1751,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf .first = true, }; - disable_uniquify(evlist); + evlist__set_needs_uniquify(evlist, config); if (config->iostat_run) evlist->selected = evlist__first(evlist); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index fa8b2a1048ff..d83bda5824d2 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -151,6 +151,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type { struct evsel *cur; int evsel_ctx = evsel_context(evsel); + struct perf_pmu *evsel_pmu = evsel__find_pmu(evsel); evlist__for_each_entry(evsel->evlist, cur) { struct perf_stat_aggr *aggr; @@ -177,7 +178,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type * Except the SW CLOCK events, * ignore if not the PMU we're looking for. */ - if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu)) + if ((type != STAT_NSECS) && (evsel_pmu != evsel__find_pmu(cur))) continue; aggr = &cur->stats->aggr[aggr_idx]; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 7c2ccdcc3fdb..1f7abd8754c7 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -535,7 +535,10 @@ static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias) return 0; } -/* events should have the same name, scale, unit, cgroup but on different PMUs */ +/* + * Events should have the same name, scale, unit, cgroup but on different core + * PMUs or on different but matching uncore PMUs. + */ static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b) { if (strcmp(evsel__name(evsel_a), evsel__name(evsel_b))) @@ -553,7 +556,13 @@ static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b) if (evsel__is_clock(evsel_a) != evsel__is_clock(evsel_b)) return false; - return evsel_a->pmu != evsel_b->pmu; + if (evsel_a->pmu == evsel_b->pmu || evsel_a->pmu == NULL || evsel_b->pmu == NULL) + return false; + + if (evsel_a->pmu->is_core) + return evsel_b->pmu->is_core; + + return perf_pmu__name_no_suffix_match(evsel_a->pmu, evsel_b->pmu->name); } static void evsel__merge_aliases(struct evsel *evsel) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66fd1249660a..fbf6d0f73af9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -7,6 +7,7 @@ #include <unistd.h> #include <inttypes.h> +#include "compress.h" #include "dso.h" #include "map.h" #include "maps.h" @@ -1173,33 +1174,6 @@ out: #endif -static int dso__swap_init(struct dso *dso, unsigned char eidata) -{ - static unsigned int const endian = 1; - - dso__set_needs_swap(dso, DSO_SWAP__NO); - - switch (eidata) { - case ELFDATA2LSB: - /* We are big endian, DSO is little endian. */ - if (*(unsigned char const *)&endian != 1) - dso__set_needs_swap(dso, DSO_SWAP__YES); - break; - - case ELFDATA2MSB: - /* We are little endian, DSO is big endian. */ - if (*(unsigned char const *)&endian != 0) - dso__set_needs_swap(dso, DSO_SWAP__YES); - break; - - default: - pr_err("unrecognized DSO data encoding %d\n", eidata); - return -EINVAL; - } - - return 0; -} - bool symsrc__possibly_runtime(struct symsrc *ss) { return ss->dynsym || ss->opdsec; @@ -1228,6 +1202,81 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) ehdr.e_type == ET_DYN; } +static Elf *read_gnu_debugdata(struct dso *dso, Elf *elf, const char *name, int *fd_ret) +{ + Elf *elf_embedded; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Scn *scn; + Elf_Data *scn_data; + FILE *wrapped; + size_t shndx; + char temp_filename[] = "/tmp/perf.gnu_debugdata.elf.XXXXXX"; + int ret, temp_fd; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_debug("%s: cannot read %s ELF file.\n", __func__, name); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + return NULL; + } + + scn = elf_section_by_name(elf, &ehdr, &shdr, ".gnu_debugdata", &shndx); + if (!scn) { + *dso__load_errno(dso) = -ENOENT; + return NULL; + } + + if (shdr.sh_type == SHT_NOBITS) { + pr_debug("%s: .gnu_debugdata of ELF file %s has no data.\n", __func__, name); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + return NULL; + } + + scn_data = elf_rawdata(scn, NULL); + if (!scn_data) { + pr_debug("%s: error reading .gnu_debugdata of %s: %s\n", __func__, + name, elf_errmsg(-1)); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + return NULL; + } + + wrapped = fmemopen(scn_data->d_buf, scn_data->d_size, "r"); + if (!wrapped) { + pr_debug("%s: fmemopen: %s\n", __func__, strerror(errno)); + *dso__load_errno(dso) = -errno; + return NULL; + } + + temp_fd = mkstemp(temp_filename); + if (temp_fd < 0) { + pr_debug("%s: mkstemp: %s\n", __func__, strerror(errno)); + *dso__load_errno(dso) = -errno; + fclose(wrapped); + return NULL; + } + unlink(temp_filename); + + ret = lzma_decompress_stream_to_file(wrapped, temp_fd); + fclose(wrapped); + if (ret < 0) { + *dso__load_errno(dso) = -errno; + close(temp_fd); + return NULL; + } + + elf_embedded = elf_begin(temp_fd, PERF_ELF_C_READ_MMAP, NULL); + if (!elf_embedded) { + pr_debug("%s: error reading .gnu_debugdata of %s: %s\n", __func__, + name, elf_errmsg(-1)); + *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; + close(temp_fd); + return NULL; + } + pr_debug("%s: using .gnu_debugdata of %s\n", __func__, name); + *fd_ret = temp_fd; + return elf_embedded; +} + int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, enum dso_binary_type type) { @@ -1256,6 +1305,19 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, goto out_close; } + if (type == DSO_BINARY_TYPE__GNU_DEBUGDATA) { + int new_fd; + Elf *embedded = read_gnu_debugdata(dso, elf, name, &new_fd); + + if (!embedded) + goto out_close; + + elf_end(elf); + close(fd); + fd = new_fd; + elf = embedded; + } + if (gelf_getehdr(elf, &ehdr) == NULL) { *dso__load_errno(dso) = DSO_LOAD_ERRNO__INVALID_ELF; pr_debug("%s: cannot get elf header.\n", __func__); @@ -1854,10 +1916,23 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, kmodule, 1); if (err < 0) return err; - err += nr; + nr += err; } - return err; + /* + * The .gnu_debugdata is a special situation: it contains a symbol + * table, but the runtime file may also contain dynsym entries which are + * not present there. We need to load both. + */ + if (syms_ss->type == DSO_BINARY_TYPE__GNU_DEBUGDATA && runtime_ss->dynsym) { + err = dso__load_sym_internal(dso, map, runtime_ss, runtime_ss, + kmodule, 1); + if (err < 0) + return err; + nr += err; + } + + return nr; } static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 49b08adc6ee3..11540219481b 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -18,6 +18,7 @@ #include "annotate.h" #include "build-id.h" #include "cap.h" +#include "cpumap.h" #include "dso.h" #include "util.h" // lsdir() #include "debug.h" @@ -84,6 +85,7 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__FEDORA_DEBUGINFO, DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__GNU_DEBUGDATA, DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, DSO_BINARY_TYPE__GUEST_KMODULE_COMP, @@ -1716,6 +1718,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + case DSO_BINARY_TYPE__GNU_DEBUGDATA: return !kmod && dso__kernel(dso) == DSO_SPACE__USER; case DSO_BINARY_TYPE__KALLSYMS: @@ -2471,6 +2474,36 @@ int symbol__annotation_init(void) return 0; } +static int setup_parallelism_bitmap(void) +{ + struct perf_cpu_map *map; + struct perf_cpu cpu; + int i, err = -1; + + if (symbol_conf.parallelism_list_str == NULL) + return 0; + + map = perf_cpu_map__new(symbol_conf.parallelism_list_str); + if (map == NULL) { + pr_err("failed to parse parallelism filter list\n"); + return -1; + } + + bitmap_fill(symbol_conf.parallelism_filter, MAX_NR_CPUS + 1); + perf_cpu_map__for_each_cpu(cpu, i, map) { + if (cpu.cpu <= 0 || cpu.cpu > MAX_NR_CPUS) { + pr_err("Requested parallelism level %d is invalid.\n", cpu.cpu); + goto out_delete_map; + } + __clear_bit(cpu.cpu, symbol_conf.parallelism_filter); + } + + err = 0; +out_delete_map: + perf_cpu_map__put(map); + return err; +} + int symbol__init(struct perf_env *env) { const char *symfs; @@ -2490,6 +2523,9 @@ int symbol__init(struct perf_env *env) return -1; } + if (setup_parallelism_bitmap()) + return -1; + if (setup_list(&symbol_conf.dso_list, symbol_conf.dso_list_str, "dso") < 0) return -1; diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index a9c51acc722f..cd9aa82c7d5a 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -3,6 +3,8 @@ #define __PERF_SYMBOL_CONF 1 #include <stdbool.h> +#include <linux/bitmap.h> +#include "perf.h" struct strlist; struct intlist; @@ -47,7 +49,9 @@ struct symbol_conf { keep_exited_threads, annotate_data_member, annotate_data_sample, - skip_empty; + skip_empty, + enable_latency, + prefer_latency; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -62,6 +66,7 @@ struct symbol_conf { *pid_list_str, *tid_list_str, *sym_list_str, + *parallelism_list_str, *col_width_list_str, *bt_stop_list_str; const char *addr2line_path; @@ -82,6 +87,7 @@ struct symbol_conf { int pad_output_len_dso; int group_sort_idx; int addr_range; + DECLARE_BITMAP(parallelism_filter, MAX_NR_CPUS + 1); }; extern struct symbol_conf symbol_conf; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 6923b0d5efed..2fc4d0537840 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -38,6 +38,7 @@ #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <api/fs/fs.h> #include <api/io.h> +#include <api/io_dir.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> @@ -767,10 +768,10 @@ static int __event__synthesize_thread(union perf_event *comm_event, bool needs_mmap, bool mmap_data) { char filename[PATH_MAX]; - struct dirent **dirent; + struct io_dir iod; + struct io_dirent64 *dent; pid_t tgid, ppid; int rc = 0; - int i, n; /* special case: only send one comm event using passed in pid */ if (!full) { @@ -802,16 +803,19 @@ static int __event__synthesize_thread(union perf_event *comm_event, snprintf(filename, sizeof(filename), "%s/proc/%d/task", machine->root_dir, pid); - n = scandir(filename, &dirent, filter_task, NULL); - if (n < 0) - return n; + io_dir__init(&iod, open(filename, O_CLOEXEC | O_DIRECTORY | O_RDONLY)); + if (iod.dirfd < 0) + return -1; - for (i = 0; i < n; i++) { + while ((dent = io_dir__readdir(&iod)) != NULL) { char *end; pid_t _pid; bool kernel_thread = false; - _pid = strtol(dirent[i]->d_name, &end, 10); + if (!isdigit(dent->d_name[0])) + continue; + + _pid = strtol(dent->d_name, &end, 10); if (*end) continue; @@ -845,9 +849,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, } } - for (i = 0; i < n; i++) - zfree(&dirent[i]); - free(dirent); + close(iod.dirfd); return rc; } @@ -1508,9 +1510,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, } if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { + if (sample->user_regs && sample->user_regs->abi) { result += sizeof(u64); - sz = hweight64(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs->mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -1536,9 +1538,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, result += sizeof(u64); if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { + if (sample->intr_regs && sample->intr_regs->abi) { result += sizeof(u64); - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs->mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -1707,10 +1709,10 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo } if (type & PERF_SAMPLE_REGS_USER) { - if (sample->user_regs.abi) { - *array++ = sample->user_regs.abi; - sz = hweight64(sample->user_regs.mask) * sizeof(u64); - memcpy(array, sample->user_regs.regs, sz); + if (sample->user_regs && sample->user_regs->abi) { + *array++ = sample->user_regs->abi; + sz = hweight64(sample->user_regs->mask) * sizeof(u64); + memcpy(array, sample->user_regs->regs, sz); array = (void *)array + sz; } else { *array++ = 0; @@ -1743,10 +1745,10 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo } if (type & PERF_SAMPLE_REGS_INTR) { - if (sample->intr_regs.abi) { - *array++ = sample->intr_regs.abi; - sz = hweight64(sample->intr_regs.mask) * sizeof(u64); - memcpy(array, sample->intr_regs.regs, sz); + if (sample->intr_regs && sample->intr_regs->abi) { + *array++ = sample->intr_regs->abi; + sz = hweight64(sample->intr_regs->mask) * sizeof(u64); + memcpy(array, sample->intr_regs->regs, sz); array = (void *)array + sz; } else { *array++ = 0; diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 928aca4cd6e9..67a8ec10e9e4 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -7,119 +7,127 @@ #include "syscalltbl.h" #include <stdlib.h> +#include <asm/bitsperlong.h> #include <linux/compiler.h> +#include <linux/kernel.h> #include <linux/zalloc.h> #include <string.h> #include "string2.h" -#include <syscall_table.h> -const int syscalltbl_native_max_id = SYSCALLTBL_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl; +#include "trace/beauty/generated/syscalltbl.c" -struct syscall { - int id; - const char *name; -}; - -static int syscallcmpname(const void *vkey, const void *ventry) -{ - const char *key = vkey; - const struct syscall *entry = ventry; - - return strcmp(key, entry->name); -} - -static int syscallcmp(const void *va, const void *vb) +static const struct syscalltbl *find_table(int e_machine) { - const struct syscall *a = va, *b = vb; + static const struct syscalltbl *last_table; + static int last_table_machine = EM_NONE; - return strcmp(a->name, b->name); -} + /* Tables only exist for EM_SPARC. */ + if (e_machine == EM_SPARCV9) + e_machine = EM_SPARC; -static int syscalltbl__init_native(struct syscalltbl *tbl) -{ - int nr_entries = 0, i, j; - struct syscall *entries; + if (last_table_machine == e_machine && last_table != NULL) + return last_table; - for (i = 0; i <= syscalltbl_native_max_id; ++i) - if (syscalltbl_native[i]) - ++nr_entries; + for (size_t i = 0; i < ARRAY_SIZE(syscalltbls); i++) { + const struct syscalltbl *entry = &syscalltbls[i]; - entries = tbl->syscalls.entries = malloc(sizeof(struct syscall) * nr_entries); - if (tbl->syscalls.entries == NULL) - return -1; + if (entry->e_machine != e_machine && entry->e_machine != EM_NONE) + continue; - for (i = 0, j = 0; i <= syscalltbl_native_max_id; ++i) { - if (syscalltbl_native[i]) { - entries[j].name = syscalltbl_native[i]; - entries[j].id = i; - ++j; - } + last_table = entry; + last_table_machine = e_machine; + return entry; } - - qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp); - tbl->syscalls.nr_entries = nr_entries; - tbl->syscalls.max_id = syscalltbl_native_max_id; - return 0; + return NULL; } -struct syscalltbl *syscalltbl__new(void) +const char *syscalltbl__name(int e_machine, int id) { - struct syscalltbl *tbl = malloc(sizeof(*tbl)); - if (tbl) { - if (syscalltbl__init_native(tbl)) { - free(tbl); - return NULL; - } + const struct syscalltbl *table = find_table(e_machine); + + if (e_machine == EM_MIPS && id > 1000) { + /* + * MIPS may encode the N32/64/O32 type in the high part of + * syscall number. Mask this off if present. See the values of + * __NR_N32_Linux, __NR_64_Linux, __NR_O32_Linux and __NR_Linux. + */ + id = id % 1000; } - return tbl; + if (table && id >= 0 && id < table->num_to_name_len) + return table->num_to_name[id]; + return NULL; } -void syscalltbl__delete(struct syscalltbl *tbl) +struct syscall_cmp_key { + const char *name; + const char *const *tbl; +}; + +static int syscallcmpname(const void *vkey, const void *ventry) { - zfree(&tbl->syscalls.entries); - free(tbl); + const struct syscall_cmp_key *key = vkey; + const uint16_t *entry = ventry; + + return strcmp(key->name, key->tbl[*entry]); } -const char *syscalltbl__name(const struct syscalltbl *tbl __maybe_unused, int id) +int syscalltbl__id(int e_machine, const char *name) { - return id <= syscalltbl_native_max_id ? syscalltbl_native[id]: NULL; + const struct syscalltbl *table = find_table(e_machine); + struct syscall_cmp_key key; + const uint16_t *id; + + if (!table) + return -1; + + key.name = name; + key.tbl = table->num_to_name; + id = bsearch(&key, table->sorted_names, table->sorted_names_len, + sizeof(table->sorted_names[0]), syscallcmpname); + + return id ? *id : -1; } -int syscalltbl__id(struct syscalltbl *tbl, const char *name) +int syscalltbl__num_idx(int e_machine) { - struct syscall *sc = bsearch(name, tbl->syscalls.entries, - tbl->syscalls.nr_entries, sizeof(*sc), - syscallcmpname); + const struct syscalltbl *table = find_table(e_machine); + + if (!table) + return 0; - return sc ? sc->id : -1; + return table->sorted_names_len; } -int syscalltbl__id_at_idx(struct syscalltbl *tbl, int idx) +int syscalltbl__id_at_idx(int e_machine, int idx) { - struct syscall *syscalls = tbl->syscalls.entries; + const struct syscalltbl *table = find_table(e_machine); - return idx < tbl->syscalls.nr_entries ? syscalls[idx].id : -1; + if (!table) + return -1; + + assert(idx >= 0 && idx < table->sorted_names_len); + return table->sorted_names[idx]; } -int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +int syscalltbl__strglobmatch_next(int e_machine, const char *syscall_glob, int *idx) { - int i; - struct syscall *syscalls = tbl->syscalls.entries; + const struct syscalltbl *table = find_table(e_machine); + + for (int i = *idx + 1; table && i < table->sorted_names_len; ++i) { + const char *name = table->num_to_name[table->sorted_names[i]]; - for (i = *idx + 1; i < tbl->syscalls.nr_entries; ++i) { - if (strglobmatch(syscalls[i].name, syscall_glob)) { + if (strglobmatch(name, syscall_glob)) { *idx = i; - return syscalls[i].id; + return table->sorted_names[i]; } } return -1; } -int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +int syscalltbl__strglobmatch_first(int e_machine, const char *syscall_glob, int *idx) { *idx = -1; - return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); + return syscalltbl__strglobmatch_next(e_machine, syscall_glob, idx); } diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index 362411a6d849..2bb628eff367 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -2,22 +2,12 @@ #ifndef __PERF_SYSCALLTBL_H #define __PERF_SYSCALLTBL_H -struct syscalltbl { - struct { - int max_id; - int nr_entries; - void *entries; - } syscalls; -}; +const char *syscalltbl__name(int e_machine, int id); +int syscalltbl__id(int e_machine, const char *name); +int syscalltbl__num_idx(int e_machine); +int syscalltbl__id_at_idx(int e_machine, int idx); -struct syscalltbl *syscalltbl__new(void); -void syscalltbl__delete(struct syscalltbl *tbl); - -const char *syscalltbl__name(const struct syscalltbl *tbl, int id); -int syscalltbl__id(struct syscalltbl *tbl, const char *name); -int syscalltbl__id_at_idx(struct syscalltbl *tbl, int idx); - -int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx); -int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx); +int syscalltbl__strglobmatch_first(int e_machine, const char *syscall_glob, int *idx); +int syscalltbl__strglobmatch_next(int e_machine, const char *syscall_glob, int *idx); #endif /* __PERF_SYSCALLTBL_H */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0ffdd52d86d7..89585f53c1d5 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#include <elf.h> #include <errno.h> +#include <fcntl.h> #include <stdlib.h> #include <stdio.h> #include <string.h> @@ -16,6 +18,7 @@ #include "symbol.h" #include "unwind.h" #include "callchain.h" +#include "dwarf-regs.h" #include <api/fs/fs.h> @@ -51,6 +54,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread__set_ppid(thread, -1); thread__set_cpu(thread, -1); thread__set_guest_cpu(thread, -1); + thread__set_e_machine(thread, EM_NONE); thread__set_lbr_stitch_enable(thread, false); INIT_LIST_HEAD(thread__namespaces_list(thread)); INIT_LIST_HEAD(thread__comm_list(thread)); @@ -423,6 +427,82 @@ void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, } } +static uint16_t read_proc_e_machine_for_pid(pid_t pid) +{ + char path[6 /* "/proc/" */ + 11 /* max length of pid */ + 5 /* "/exe\0" */]; + int fd; + uint16_t e_machine = EM_NONE; + + snprintf(path, sizeof(path), "/proc/%d/exe", pid); + fd = open(path, O_RDONLY); + if (fd >= 0) { + _Static_assert(offsetof(Elf32_Ehdr, e_machine) == 18, "Unexpected offset"); + _Static_assert(offsetof(Elf64_Ehdr, e_machine) == 18, "Unexpected offset"); + if (pread(fd, &e_machine, sizeof(e_machine), 18) != sizeof(e_machine)) + e_machine = EM_NONE; + close(fd); + } + return e_machine; +} + +static int thread__e_machine_callback(struct map *map, void *machine) +{ + struct dso *dso = map__dso(map); + + _Static_assert(0 == EM_NONE, "Unexpected EM_NONE"); + if (!dso) + return EM_NONE; + + return dso__e_machine(dso, machine); +} + +uint16_t thread__e_machine(struct thread *thread, struct machine *machine) +{ + pid_t tid, pid; + uint16_t e_machine = RC_CHK_ACCESS(thread)->e_machine; + + if (e_machine != EM_NONE) + return e_machine; + + tid = thread__tid(thread); + pid = thread__pid(thread); + if (pid != tid) { + struct thread *parent = machine__findnew_thread(machine, pid, pid); + + if (parent) { + e_machine = thread__e_machine(parent, machine); + thread__set_e_machine(thread, e_machine); + return e_machine; + } + /* Something went wrong, fallback. */ + } + /* Reading on the PID thread. First try to find from the maps. */ + e_machine = maps__for_each_map(thread__maps(thread), + thread__e_machine_callback, + machine); + if (e_machine == EM_NONE) { + /* Maps failed, perhaps we're live with map events disabled. */ + bool is_live = machine->machines == NULL; + + if (!is_live) { + /* Check if the session has a data file. */ + struct perf_session *session = container_of(machine->machines, + struct perf_session, + machines); + + is_live = !!session->data; + } + /* Read from /proc/pid/exe if live. */ + if (is_live) + e_machine = read_proc_e_machine_for_pid(pid); + } + if (e_machine != EM_NONE) + thread__set_e_machine(thread, e_machine); + else + e_machine = EM_HOST; + return e_machine; +} + struct thread *thread__main_thread(struct machine *machine, struct thread *thread) { if (thread__pid(thread) == thread__tid(thread)) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 6cbf6eb2812e..cd574a896418 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -60,7 +60,11 @@ DECLARE_RC_STRUCT(thread) { struct srccode_state srccode_state; bool filter; int filter_entry_depth; - + /** + * @e_machine: The ELF EM_* associated with the thread. EM_NONE if not + * computed. + */ + uint16_t e_machine; /* LBR call stack stitch */ bool lbr_stitch_enable; struct lbr_stitch *lbr_stitch; @@ -302,6 +306,14 @@ static inline void thread__set_filter_entry_depth(struct thread *thread, int dep RC_CHK_ACCESS(thread)->filter_entry_depth = depth; } +uint16_t thread__e_machine(struct thread *thread, struct machine *machine); + +static inline void thread__set_e_machine(struct thread *thread, uint16_t e_machine) +{ + RC_CHK_ACCESS(thread)->e_machine = e_machine; +} + + static inline bool thread__lbr_stitch_enable(const struct thread *thread) { return RC_CHK_ACCESS(thread)->lbr_stitch_enable; diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c index 4fb097578479..97b327d1ce4a 100644 --- a/tools/perf/util/tool_pmu.c +++ b/tools/perf/util/tool_pmu.c @@ -62,7 +62,8 @@ int tool_pmu__num_skip_events(void) const char *tool_pmu__event_to_str(enum tool_pmu_event ev) { - if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) + if ((ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) && + !tool_pmu__skip_event(tool_pmu__event_names[ev])) return tool_pmu__event_names[ev]; return NULL; @@ -354,6 +355,7 @@ bool tool_pmu__read_event(enum tool_pmu_event ev, u64 *result) if (online) { *result = perf_cpu_map__nr(online); + perf_cpu_map__put(online); return true; } return false; @@ -489,17 +491,24 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) return 0; } -struct perf_pmu *perf_pmus__tool_pmu(void) +struct perf_pmu *tool_pmu__new(void) { - static struct perf_pmu tool = { - .name = "tool", - .type = PERF_PMU_TYPE_TOOL, - .aliases = LIST_HEAD_INIT(tool.aliases), - .caps = LIST_HEAD_INIT(tool.caps), - .format = LIST_HEAD_INIT(tool.format), - }; - if (!tool.events_table) - tool.events_table = find_core_events_table("common", "common"); - - return &tool; + struct perf_pmu *tool = zalloc(sizeof(struct perf_pmu)); + + if (!tool) + goto out; + tool->name = strdup("tool"); + if (!tool->name) { + zfree(&tool); + goto out; + } + + tool->type = PERF_PMU_TYPE_TOOL; + INIT_LIST_HEAD(&tool->aliases); + INIT_LIST_HEAD(&tool->caps); + INIT_LIST_HEAD(&tool->format); + tool->events_table = find_core_events_table("common", "common"); + +out: + return tool; } diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h index a60184859080..c6ad1dd90a56 100644 --- a/tools/perf/util/tool_pmu.h +++ b/tools/perf/util/tool_pmu.h @@ -51,6 +51,6 @@ int evsel__tool_pmu_open(struct evsel *evsel, int start_cpu_map_idx, int end_cpu_map_idx); int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread); -struct perf_pmu *perf_pmus__tool_pmu(void); +struct perf_pmu *tool_pmu__new(void); #endif /* __TOOL_PMU_H */ diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 4e81e02a4f18..72abb28b7b5a 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -309,53 +309,107 @@ static const struct { {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"}, {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_BRANCH_MISS, "br miss"}, {0, NULL} }; -static const char *sample_flags_to_name(u32 flags) +static const struct { + u32 flags; + const char *name; +} branch_events[] = { + {PERF_IP_FLAG_BRANCH_MISS, "miss"}, + {PERF_IP_FLAG_NOT_TAKEN, "not_taken"}, + {0, NULL} +}; + +static int sample_flags_to_name(u32 flags, char *str, size_t size) { int i; + const char *prefix; + int pos = 0, ret, ev_idx = 0; + u32 xf = flags & PERF_ADDITIONAL_STATE_MASK; + u32 types, events; + char xs[16] = { 0 }; + + /* Clear additional state bits */ + flags &= ~PERF_ADDITIONAL_STATE_MASK; + + if (flags & PERF_IP_FLAG_TRACE_BEGIN) + prefix = "tr strt "; + else if (flags & PERF_IP_FLAG_TRACE_END) + prefix = "tr end "; + else + prefix = ""; + + ret = snprintf(str + pos, size - pos, "%s", prefix); + if (ret < 0) + return ret; + pos += ret; + + flags &= ~(PERF_IP_FLAG_TRACE_BEGIN | PERF_IP_FLAG_TRACE_END); + + types = flags & ~PERF_IP_FLAG_BRANCH_EVENT_MASK; + for (i = 0; sample_flags[i].name; i++) { + if (sample_flags[i].flags != types) + continue; + + ret = snprintf(str + pos, size - pos, "%s", sample_flags[i].name); + if (ret < 0) + return ret; + pos += ret; + break; + } - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == flags) - return sample_flags[i].name; + events = flags & PERF_IP_FLAG_BRANCH_EVENT_MASK; + for (i = 0; branch_events[i].name; i++) { + if (!(branch_events[i].flags & events)) + continue; + + ret = snprintf(str + pos, size - pos, !ev_idx ? "/%s" : ",%s", + branch_events[i].name); + if (ret < 0) + return ret; + pos += ret; + ev_idx++; } - return NULL; + /* Add an end character '/' for events */ + if (ev_idx) { + ret = snprintf(str + pos, size - pos, "/"); + if (ret < 0) + return ret; + pos += ret; + } + + if (!xf) + return pos; + + snprintf(xs, sizeof(xs), "(%s%s%s)", + flags & PERF_IP_FLAG_IN_TX ? "x" : "", + flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", + flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); + + /* Right align the string if its length is less than the limit */ + if ((pos + strlen(xs)) < SAMPLE_FLAGS_STR_ALIGNED_SIZE) + ret = snprintf(str + pos, size - pos, "%*s", + (int)(SAMPLE_FLAGS_STR_ALIGNED_SIZE - ret), xs); + else + ret = snprintf(str + pos, size - pos, " %s", xs); + if (ret < 0) + return ret; + + return pos + ret; } int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) { - u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | - PERF_IP_FLAG_INTR_TOGGLE; const char *chars = PERF_IP_FLAG_CHARS; const size_t n = strlen(PERF_IP_FLAG_CHARS); - const char *name = NULL; size_t i, pos = 0; - char xs[16] = {0}; - - if (flags & xf) - snprintf(xs, sizeof(xs), "(%s%s%s)", - flags & PERF_IP_FLAG_IN_TX ? "x" : "", - flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", - flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); - - name = sample_flags_to_name(flags & ~xf); - if (name) - return snprintf(str, sz, "%-15s%6s", name, xs); - - if (flags & PERF_IP_FLAG_TRACE_BEGIN) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); - if (name) - return snprintf(str, sz, "tr strt %-7s%6s", name, xs); - } + int ret; - if (flags & PERF_IP_FLAG_TRACE_END) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); - if (name) - return snprintf(str, sz, "tr end %-7s%6s", name, xs); - } + ret = sample_flags_to_name(flags, str, sz); + if (ret > 0) + return ret; for (i = 0; i < n; i++, flags >>= 1) { if ((flags & 1) && pos < sz) diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index ac9fde2f980c..71e680bc3d4b 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -145,6 +145,8 @@ int common_flags(struct scripting_context *context); int common_lock_depth(struct scripting_context *context); #define SAMPLE_FLAGS_BUF_SIZE 64 +#define SAMPLE_FLAGS_STR_ALIGNED_SIZE 21 + int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz); #if defined(LIBTRACEEVENT_VERSION) && LIBTRACEEVENT_VERSION >= MAKE_LIBTRACEEVENT_VERSION(1, 5, 0) diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c index 32c39cfe209b..4c6a86e1cb54 100644 --- a/tools/perf/util/units.c +++ b/tools/perf/util/units.c @@ -64,7 +64,7 @@ unsigned long convert_unit(unsigned long value, char *unit) int unit_number__scnprintf(char *buf, size_t size, u64 n) { - char unit[4] = "BKMG"; + char unit[] = "BKMG"; int i = 0; while (((n / 1024) > 1) && (i < 3)) { diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index bde216e630d2..793d11832694 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -190,7 +190,10 @@ static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word * int offset; int ret; - ret = perf_reg_value(&start, &ui->sample->user_regs, + if (!ui->sample->user_regs) + return false; + + ret = perf_reg_value(&start, ui->sample->user_regs, perf_arch_reg_sp(arch)); if (ret) return false; @@ -273,7 +276,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, Dwarf_Word ip; int err = -EINVAL, i; - if (!data->user_regs.regs) + if (!data->user_regs || !data->user_regs->regs) return -EINVAL; ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack); @@ -286,7 +289,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (!ui->dwfl) goto out; - err = perf_reg_value(&ip, &data->user_regs, perf_arch_reg_ip(arch)); + err = perf_reg_value(&ip, data->user_regs, perf_arch_reg_ip(arch)); if (err) goto out; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 16c2b03831f3..9fb2c1343c7f 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -330,8 +330,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, int ret, fd; if (dso__data(dso)->eh_frame_hdr_offset == 0) { - fd = dso__data_get_fd(dso, ui->machine); - if (fd < 0) + if (!dso__data_get_fd(dso, ui->machine, &fd)) return -EINVAL; /* Check the .eh_frame section for unwinding info */ @@ -372,8 +371,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, * has to be pointed by symsrc_filename */ if (ofs == 0) { - fd = dso__data_get_fd(dso, machine); - if (fd >= 0) { + if (dso__data_get_fd(dso, machine, &fd) { ofs = elf_section_offset(fd, ".debug_frame"); dso__data_put_fd(dso); } @@ -485,14 +483,16 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, /* Check the .debug_frame section for unwinding info */ if (ret < 0 && !read_unwind_spec_debug_frame(dso, ui->machine, &segbase)) { - int fd = dso__data_get_fd(dso, ui->machine); - int is_exec = elf_is_exec(fd, dso__name(dso)); + int fd; u64 start = map__start(map); - unw_word_t base = is_exec ? 0 : start; + unw_word_t base = start; const char *symfile; - if (fd >= 0) + if (dso__data_get_fd(dso, ui->machine, &fd)) { + if (elf_is_exec(fd, dso__name(dso))) + base = 0; dso__data_put_fd(dso); + } symfile = dso__symsrc_filename(dso) ?: dso__name(dso); @@ -579,12 +579,12 @@ static int access_mem(unw_addr_space_t __maybe_unused as, int ret; /* Don't support write, probably not needed. */ - if (__write || !stack || !ui->sample->user_regs.regs) { + if (__write || !stack || !ui->sample->user_regs || !ui->sample->user_regs->regs) { *valp = 0; return 0; } - ret = perf_reg_value(&start, &ui->sample->user_regs, + ret = perf_reg_value(&start, perf_sample__user_regs(ui->sample), perf_arch_reg_sp(arch)); if (ret) return ret; @@ -628,7 +628,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as, return 0; } - if (!ui->sample->user_regs.regs) { + if (!ui->sample->user_regs || !ui->sample->user_regs->regs) { *valp = 0; return 0; } @@ -637,7 +637,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as, if (id < 0) return -EINVAL; - ret = perf_reg_value(&val, &ui->sample->user_regs, id); + ret = perf_reg_value(&val, perf_sample__user_regs(ui->sample), id); if (ret) { if (!ui->best_effort) pr_err("unwind: can't read reg %d\n", regnum); @@ -741,7 +741,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, unw_cursor_t c; int ret, i = 0; - ret = perf_reg_value(&val, &ui->sample->user_regs, + ret = perf_reg_value(&val, perf_sample__user_regs(ui->sample), perf_arch_reg_ip(arch)); if (ret) return ret; @@ -808,7 +808,7 @@ static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, .best_effort = best_effort }; - if (!data->user_regs.regs) + if (!data->user_regs || !data->user_regs->regs) return -EINVAL; if (max_stack <= 0) |