mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-05 07:16:56 +07:00
d5afa7e905
Revert the changes made by commit fdffbafb [Lots of FPU bug fixes from Kjeld Borch Egevang.] to `ieee754sp_nanxcpt' and `ieee754dp_nanxcpt' sNaN quieting handlers and their callers so that sNaN processing is done within the handlers againg. Pass the sNaN causing an IEEE 754 invalid operation exception down to the relevant handler. Pass the sNaN in `fs' where two sNaNs are supplied to a binary operation. Set the Invalid Operation FCSR exception bits in the quieting handlers rather than at their call sites throughout. Make the handlers exclusive for sNaN processing. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/9688/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
186 lines
4.6 KiB
C
186 lines
4.6 KiB
C
/* IEEE754 floating point arithmetic
|
|
* double precision: common utilities
|
|
*/
|
|
/*
|
|
* MIPS floating point support
|
|
* Copyright (C) 1994-2000 Algorithmics Ltd.
|
|
*
|
|
* This program is free software; you can distribute it and/or modify it
|
|
* under the terms of the GNU General Public License (Version 2) as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
* for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along
|
|
* with this program; if not, write to the Free Software Foundation, Inc.,
|
|
* 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
*/
|
|
|
|
#include "ieee754dp.h"
|
|
|
|
union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y)
|
|
{
|
|
int s;
|
|
|
|
COMPXDP;
|
|
COMPYDP;
|
|
|
|
EXPLODEXDP;
|
|
EXPLODEYDP;
|
|
|
|
ieee754_clearcx();
|
|
|
|
FLUSHXDP;
|
|
FLUSHYDP;
|
|
|
|
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);
|
|
|
|
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 y;
|
|
|
|
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 x;
|
|
|
|
|
|
/*
|
|
* Infinity handling
|
|
*/
|
|
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
|
|
if (xs != ys)
|
|
return x;
|
|
ieee754_setcx(IEEE754_INVALID_OPERATION);
|
|
return ieee754dp_indef();
|
|
|
|
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
|
|
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
|
|
return ieee754dp_inf(ys ^ 1);
|
|
|
|
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
|
|
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
|
|
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
|
|
return x;
|
|
|
|
/*
|
|
* Zero handling
|
|
*/
|
|
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
|
|
if (xs != ys)
|
|
return x;
|
|
else
|
|
return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
|
|
|
|
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
|
|
return x;
|
|
|
|
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
|
|
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
|
|
/* quick fix up */
|
|
DPSIGN(y) ^= 1;
|
|
return y;
|
|
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
|
|
DPDNORMX;
|
|
/* FALL THROUGH */
|
|
|
|
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
|
|
/* normalize ym,ye */
|
|
DPDNORMY;
|
|
break;
|
|
|
|
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
|
|
/* normalize xm,xe */
|
|
DPDNORMX;
|
|
break;
|
|
|
|
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
|
|
break;
|
|
}
|
|
/* flip sign of y and handle as add */
|
|
ys ^= 1;
|
|
|
|
assert(xm & DP_HIDDEN_BIT);
|
|
assert(ym & DP_HIDDEN_BIT);
|
|
|
|
|
|
/* provide guard,round and stick bit dpace */
|
|
xm <<= 3;
|
|
ym <<= 3;
|
|
|
|
if (xe > ye) {
|
|
/*
|
|
* Have to shift y fraction right to align
|
|
*/
|
|
s = xe - ye;
|
|
ym = XDPSRS(ym, s);
|
|
ye += s;
|
|
} else if (ye > xe) {
|
|
/*
|
|
* Have to shift x fraction right to align
|
|
*/
|
|
s = ye - xe;
|
|
xm = XDPSRS(xm, s);
|
|
xe += s;
|
|
}
|
|
assert(xe == ye);
|
|
assert(xe <= DP_EMAX);
|
|
|
|
if (xs == ys) {
|
|
/* generate 28 bit result of adding two 27 bit numbers
|
|
*/
|
|
xm = xm + ym;
|
|
|
|
if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */
|
|
xm = XDPSRS1(xm); /* shift preserving sticky */
|
|
xe++;
|
|
}
|
|
} else {
|
|
if (xm >= ym) {
|
|
xm = xm - ym;
|
|
} else {
|
|
xm = ym - xm;
|
|
xs = ys;
|
|
}
|
|
if (xm == 0) {
|
|
if (ieee754_csr.rm == FPU_CSR_RD)
|
|
return ieee754dp_zero(1); /* round negative inf. => sign = -1 */
|
|
else
|
|
return ieee754dp_zero(0); /* other round modes => sign = 1 */
|
|
}
|
|
|
|
/* normalize to rounding precision
|
|
*/
|
|
while ((xm >> (DP_FBITS + 3)) == 0) {
|
|
xm <<= 1;
|
|
xe--;
|
|
}
|
|
}
|
|
|
|
return ieee754dp_format(xs, xe, xm);
|
|
}
|