forked from Minki/linux
15560a58bf
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: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/16881/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
234 lines
6.2 KiB
C
234 lines
6.2 KiB
C
/*
|
|
* IEEE754 floating point arithmetic
|
|
* single precision: MIN{,A}.f
|
|
* MIN : Scalar Floating-Point Minimum
|
|
* MINA: Scalar Floating-Point argument with Minimum Absolute Value
|
|
*
|
|
* MIN.S : FPR[fd] = minNum(FPR[fs],FPR[ft])
|
|
* MINA.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_fmin(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 ? 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 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 x;
|
|
else if (xs < ys)
|
|
return y;
|
|
|
|
/* Compare exponent */
|
|
if (xe > ye)
|
|
return y;
|
|
else if (xe < ye)
|
|
return x;
|
|
|
|
/* Compare mantissa */
|
|
if (xm <= ym)
|
|
return x;
|
|
return y;
|
|
}
|
|
|
|
union ieee754sp ieee754sp_fmina(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):
|
|
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 y;
|
|
else if (xe < ye)
|
|
return x;
|
|
|
|
/* Compare mantissa */
|
|
if (xm <= ym)
|
|
return x;
|
|
return y;
|
|
}
|