MIPS: math-emu: Add support for the MIPS R6 MAX{, A} FPU instruction

MIPS R6 introduced the following instruction:
Scalar Floating-Point Maximum and
Scalar Floating-Point argument with Maximum Absolute Value
MAX.fmt writes the maximum value of the inputs fs and ft to the
destination fd.
MAXA.fmt takes input arguments fs and ft and writes the argument with
the maximum absolute value to the destination fd.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/10961/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

1 files changed, 213 insertions, 0 deletions

diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c
new file mode 100644
index 000000000000..4d000844e48e
--- /dev/null
+++ b/arch/mips/math-emu/sp_fmax.c
@@ -0,0 +1,213 @@
+/*
+ * IEEE754 floating point arithmetic
+ * single precision: MAX{,A}.f
+ * MAX : Scalar Floating-Point Maximum
+ * MAXA: Scalar Floating-Point argument with Maximum Absolute Value
+ *
+ * MAX.S : FPR[fd] = maxNum(FPR[fs],FPR[ft])
+ * MAXA.S: FPR[fd] = maxNumMag(FPR[fs],FPR[ft])
+ *
+ * MIPS floating point support
+ * Copyright (C) 2015 Imagination Technologies, Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ *  This program is free software; you can distribute it and/or modify it
+ *  under the terms of the GNU General Public License as published by the
+ *  Free Software Foundation; version 2 of the License.
+ */
+
+#include "ieee754sp.h"
+
+union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
+{
+	COMPXSP;
+	COMPYSP;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+
+	FLUSHXSP;
+	FLUSHYSP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return xs ? y : x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return ys ? x : y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754sp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		SPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	/* Compare signs */
+	if (xs > ys)
+		return y;
+	else if (xs < ys)
+		return x;
+
+	/* Compare exponent */
+	if (xe > ye)
+		return x;
+	else if (xe < ye)
+		return y;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return y;
+	return x;
+}
+
+union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
+{
+	COMPXSP;
+	COMPYSP;
+
+	EXPLODEXSP;
+	EXPLODEYSP;
+
+	FLUSHXSP;
+	FLUSHYSP;
+
+	ieee754_clearcx();
+
+	switch (CLPAIR(xc, yc)) {
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+		return ieee754sp_nanxcpt(y);
+
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+		return ieee754sp_nanxcpt(x);
+
+	/* numbers are preferred to NaNs */
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
+		return y;
+
+	/*
+	 * Infinity and zero handling
+	 */
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
+		return x;
+
+	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
+		return y;
+
+	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
+		if (xs == ys)
+			return x;
+		return ieee754sp_zero(1);
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
+		SPDNORMX;
+
+	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
+		SPDNORMY;
+		break;
+
+	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
+		SPDNORMX;
+	}
+
+	/* Finally get to do some computation */
+
+	assert(xm & SP_HIDDEN_BIT);
+	assert(ym & SP_HIDDEN_BIT);
+
+	/* Compare exponent */
+	if (xe > ye)
+		return x;
+	else if (xe < ye)
+		return y;
+
+	/* Compare mantissa */
+	if (xm <= ym)
+		return y;
+	return x;
+}