OpenCloudOS-Kernel/arch/mips/math-emu/sp_fmax.c

250 lines
6.6 KiB
C
Raw Normal View History

/*
* 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);
/*
* Quiet NaN handling
*/
/*
* The case of both inputs quiet NaNs
*/
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
return x;
/*
* The cases of exactly one input quiet NaN (numbers
* are here preferred as returned values 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_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):
MIPS: math-emu: <MAX|MAXA|MIN|MINA>.<D|S>: Fix cases of both inputs zero Fix the value returned by <MAX|MAXA|MIN|MINA>.<D|S>, if both inputs are zeros. The right behavior in such cases is stated in instruction reference manual and is as follows: fs ft MAX MIN MAXA MINA --------------------------------------------- 0 0 0 0 0 0 0 -0 0 -0 0 -0 -0 0 0 -0 0 -0 -0 -0 -0 -0 -0 -0 Prior to this patch, some of the above cases were yielding correct results. However, for the sake of code consistency, all such cases are rewritten in this patch. A relevant example: MAX.S fd,fs,ft: If fs contains +0.0, and ft contains -0.0, fd is going to contain +0.0 (without this patch, it used to contain -0.0). Fixes: a79f5f9ba508 ("MIPS: math-emu: Add support for the MIPS R6 MAX{, A} FPU instruction") Fixes: 4e9561b20e2f ("MIPS: math-emu: Add support for the MIPS R6 MIN{, A} FPU instruction") Signed-off-by: Miodrag Dinic <miodrag.dinic@imgtec.com> Signed-off-by: Goran Ferenc <goran.ferenc@imgtec.com> Signed-off-by: Aleksandar Markovic <aleksandar.markovic@imgtec.com> Reviewed-by: James Hogan <james.hogan@imgtec.com> Cc: Bo Hu <bohu@google.com> Cc: Douglas Leung <douglas.leung@imgtec.com> Cc: Jin Qian <jinqian@google.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Petar Jovanovic <petar.jovanovic@imgtec.com> Cc: Raghu Gandham <raghu.gandham@imgtec.com> Cc: <stable@vger.kernel.org> # 4.3+ Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16881/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2017-07-28 00:08:49 +08:00
return ieee754sp_zero(xs & ys);
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;
/* Signs of inputs are equal, let's compare exponents */
if (xs == 0) {
/* Inputs are both positive */
if (xe > ye)
return x;
else if (xe < ye)
return y;
} else {
/* Inputs are both negative */
if (xe > ye)
return y;
else if (xe < ye)
return x;
}
/* Signs and exponents of inputs are equal, let's compare mantissas */
if (xs == 0) {
/* Inputs are both positive, with equal signs and exponents */
if (xm <= ym)
return y;
return x;
}
/* Inputs are both negative, with equal signs and exponents */
if (xm <= ym)
return x;
return y;
}
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);
/*
* Quiet NaN handling
*/
/*
* The case of both inputs quiet NaNs
*/
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
return x;
/*
* The cases of exactly one input quiet NaN (numbers
* are here preferred as returned values 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_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):
MIPS: math-emu: <MAX|MAXA|MIN|MINA>.<D|S>: Fix cases of both inputs zero Fix the value returned by <MAX|MAXA|MIN|MINA>.<D|S>, if both inputs are zeros. The right behavior in such cases is stated in instruction reference manual and is as follows: fs ft MAX MIN MAXA MINA --------------------------------------------- 0 0 0 0 0 0 0 -0 0 -0 0 -0 -0 0 0 -0 0 -0 -0 -0 -0 -0 -0 -0 Prior to this patch, some of the above cases were yielding correct results. However, for the sake of code consistency, all such cases are rewritten in this patch. A relevant example: MAX.S fd,fs,ft: If fs contains +0.0, and ft contains -0.0, fd is going to contain +0.0 (without this patch, it used to contain -0.0). Fixes: a79f5f9ba508 ("MIPS: math-emu: Add support for the MIPS R6 MAX{, A} FPU instruction") Fixes: 4e9561b20e2f ("MIPS: math-emu: Add support for the MIPS R6 MIN{, A} FPU instruction") Signed-off-by: Miodrag Dinic <miodrag.dinic@imgtec.com> Signed-off-by: Goran Ferenc <goran.ferenc@imgtec.com> Signed-off-by: Aleksandar Markovic <aleksandar.markovic@imgtec.com> Reviewed-by: James Hogan <james.hogan@imgtec.com> Cc: Bo Hu <bohu@google.com> Cc: Douglas Leung <douglas.leung@imgtec.com> Cc: Jin Qian <jinqian@google.com> Cc: Paul Burton <paul.burton@imgtec.com> Cc: Petar Jovanovic <petar.jovanovic@imgtec.com> Cc: Raghu Gandham <raghu.gandham@imgtec.com> Cc: <stable@vger.kernel.org> # 4.3+ Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16881/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2017-07-28 00:08:49 +08:00
return ieee754sp_zero(xs & ys);
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;
}