mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 13:22:55 +07:00
aabf5cf02e
Fix the value returned by <MAX|MIN>.<D|S>, if both inputs are negative normal fp numbers. The previous logic did not take into account that if both inputs have the same sign, there should be separate treatment of the cases when both inputs are negative and when both inputs are positive. A relevant example: MAX.S fd,fs,ft: If fs contains -5.0, and ft contains -7.0, fd is going to contain -5.0 (without this patch, it used to contain -7.0). Fixes:a79f5f9ba5("MIPS: math-emu: Add support for the MIPS R6 MAX{, A} FPU instruction") Fixes:4e9561b20e("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/16882/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
250 lines
6.6 KiB
C
250 lines
6.6 KiB
C
/*
|
|
* IEEE754 floating point arithmetic
|
|
* double precision: MIN{,A}.f
|
|
* MIN : Scalar Floating-Point Minimum
|
|
* MINA: Scalar Floating-Point argument with Minimum Absolute Value
|
|
*
|
|
* MIN.D : FPR[fd] = minNum(FPR[fs],FPR[ft])
|
|
* MINA.D: 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 "ieee754dp.h"
|
|
|
|
union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
|
|
{
|
|
COMPXDP;
|
|
COMPYDP;
|
|
|
|
EXPLODEXDP;
|
|
EXPLODEYDP;
|
|
|
|
FLUSHXDP;
|
|
FLUSHYDP;
|
|
|
|
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 ieee754dp_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 ieee754dp_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 ? x : y;
|
|
|
|
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 ? y : x;
|
|
|
|
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
|
|
return ieee754dp_zero(xs | ys);
|
|
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
|
|
DPDNORMX;
|
|
|
|
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
|
|
DPDNORMY;
|
|
break;
|
|
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
|
|
DPDNORMX;
|
|
}
|
|
|
|
/* Finally get to do some computation */
|
|
|
|
assert(xm & DP_HIDDEN_BIT);
|
|
assert(ym & DP_HIDDEN_BIT);
|
|
|
|
/* Compare signs */
|
|
if (xs > ys)
|
|
return x;
|
|
else if (xs < ys)
|
|
return y;
|
|
|
|
/* Signs of inputs are the same, let's compare exponents */
|
|
if (xs == 0) {
|
|
/* Inputs are both positive */
|
|
if (xe > ye)
|
|
return y;
|
|
else if (xe < ye)
|
|
return x;
|
|
} else {
|
|
/* Inputs are both negative */
|
|
if (xe > ye)
|
|
return x;
|
|
else if (xe < ye)
|
|
return y;
|
|
}
|
|
|
|
/* 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 x;
|
|
return y;
|
|
}
|
|
/* Inputs are both negative, with equal signs and exponents */
|
|
if (xm <= ym)
|
|
return y;
|
|
return x;
|
|
}
|
|
|
|
union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
|
|
{
|
|
COMPXDP;
|
|
COMPYDP;
|
|
|
|
EXPLODEXDP;
|
|
EXPLODEYDP;
|
|
|
|
FLUSHXDP;
|
|
FLUSHYDP;
|
|
|
|
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 ieee754dp_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 ieee754dp_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):
|
|
return ieee754dp_zero(xs | ys);
|
|
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
|
|
DPDNORMX;
|
|
|
|
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
|
|
DPDNORMY;
|
|
break;
|
|
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
|
|
DPDNORMX;
|
|
}
|
|
|
|
/* Finally get to do some computation */
|
|
|
|
assert(xm & DP_HIDDEN_BIT);
|
|
assert(ym & DP_HIDDEN_BIT);
|
|
|
|
/* Compare exponent */
|
|
if (xe > ye)
|
|
return y;
|
|
else if (xe < ye)
|
|
return x;
|
|
|
|
/* Compare mantissa */
|
|
if (xm <= ym)
|
|
return x;
|
|
return y;
|
|
}
|