linux/arch/mips/math-emu/sp_mul.c
Linus Torvalds 1da177e4c3 Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!
2005-04-16 15:20:36 -07:00

172 lines
4.7 KiB
C

/* IEEE754 floating point arithmetic
* single precision
*/
/*
* MIPS floating point support
* Copyright (C) 1994-2000 Algorithmics Ltd.
* http://www.algor.co.uk
*
* ########################################################################
*
* 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.,
* 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
*
* ########################################################################
*/
#include "ieee754sp.h"
ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y)
{
COMPXSP;
COMPYSP;
EXPLODEXSP;
EXPLODEYSP;
CLEARCX;
FLUSHXSP;
FLUSHYSP;
switch (CLPAIR(xc, yc)) {
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
case CLPAIR(IEEE754_CLASS_SNAN, 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):
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):
SETCX(IEEE754_INVALID_OPERATION);
return ieee754sp_nanxcpt(ieee754sp_indef(), "mul", x, y);
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_ZERO):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
SETCX(IEEE754_INVALID_OPERATION);
return ieee754sp_xcpt(ieee754sp_indef(), "mul", x, y);
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
return ieee754sp_inf(xs ^ ys);
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_DNORM, 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;
break;
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
break;
}
/* rm = xm * ym, re = xe+ye basicly */
assert(xm & SP_HIDDEN_BIT);
assert(ym & SP_HIDDEN_BIT);
{
int re = xe + ye;
int rs = xs ^ ys;
unsigned rm;
/* shunt to top of word */
xm <<= 32 - (SP_MBITS + 1);
ym <<= 32 - (SP_MBITS + 1);
/* multiply 32bits xm,ym to give high 32bits rm with stickness
*/
{
unsigned short lxm = xm & 0xffff;
unsigned short hxm = xm >> 16;
unsigned short lym = ym & 0xffff;
unsigned short hym = ym >> 16;
unsigned lrm;
unsigned hrm;
lrm = lxm * lym; /* 16 * 16 => 32 */
hrm = hxm * hym; /* 16 * 16 => 32 */
{
unsigned t = lxm * hym; /* 16 * 16 => 32 */
{
unsigned at = lrm + (t << 16);
hrm += at < lrm;
lrm = at;
}
hrm = hrm + (t >> 16);
}
{
unsigned t = hxm * lym; /* 16 * 16 => 32 */
{
unsigned at = lrm + (t << 16);
hrm += at < lrm;
lrm = at;
}
hrm = hrm + (t >> 16);
}
rm = hrm | (lrm != 0);
}
/*
* sticky shift down to normal rounding precision
*/
if ((int) rm < 0) {
rm = (rm >> (32 - (SP_MBITS + 1 + 3))) |
((rm << (SP_MBITS + 1 + 3)) != 0);
re++;
} else {
rm = (rm >> (32 - (SP_MBITS + 1 + 3 + 1))) |
((rm << (SP_MBITS + 1 + 3 + 1)) != 0);
}
assert(rm & (SP_HIDDEN_BIT << 3));
SPNORMRET2(rs, re, rm, "mul", x, y);
}
}