[mirror_ubuntu-zesty-kernel.git] / arch / mips / math-emu / sp_mul.c

/* IEEE754 floating point arithmetic
 * single precision
 */
/*
 * 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 "ieee754sp.h"

union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y)
{
	int re;
	int rs;
	unsigned rm;
	unsigned short lxm;
	unsigned short hxm;
	unsigned short lym;
	unsigned short hym;
	unsigned lrm;
	unsigned hrm;
	unsigned t;
	unsigned at;

	COMPXSP;
	COMPYSP;

	EXPLODEXSP;
	EXPLODEYSP;

	ieee754_clearcx();

	FLUSHXSP;
	FLUSHYSP;

	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);

	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):
		ieee754_setcx(IEEE754_INVALID_OPERATION);
		return ieee754sp_indef();

	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 basically */
	assert(xm & SP_HIDDEN_BIT);
	assert(ym & SP_HIDDEN_BIT);

	re = xe + ye;
	rs = xs ^ ys;

	/* shunt to top of word */
	xm <<= 32 - (SP_FBITS + 1);
	ym <<= 32 - (SP_FBITS + 1);

	/*
	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
	 */
	lxm = xm & 0xffff;
	hxm = xm >> 16;
	lym = ym & 0xffff;
	hym = ym >> 16;

	lrm = lxm * lym;	/* 16 * 16 => 32 */
	hrm = hxm * hym;	/* 16 * 16 => 32 */

	t = lxm * hym; /* 16 * 16 => 32 */
	at = lrm + (t << 16);
	hrm += at < lrm;
	lrm = at;
	hrm = hrm + (t >> 16);

	t = hxm * lym; /* 16 * 16 => 32 */
	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_FBITS + 1 + 3))) |
		    ((rm << (SP_FBITS + 1 + 3)) != 0);
		re++;
	} else {
		rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) |
		     ((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
	}
	assert(rm & (SP_HIDDEN_BIT << 3));

	return ieee754sp_format(rs, re, rm);
}
Commit	Line	Data
1da177e4 LT	1	/* IEEE754 floating point arithmetic
	2	* single precision
	3	*/
	4	/*
	5	* MIPS floating point support
	6	* Copyright (C) 1994-2000 Algorithmics Ltd.
1da177e4	7	*
1da177e4 LT	8	* This program is free software; you can distribute it and/or modify it
	9	* under the terms of the GNU General Public License (Version 2) as
	10	* published by the Free Software Foundation.
	11	*
	12	* This program is distributed in the hope it will be useful, but WITHOUT
	13	* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
	14	* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
	15	* for more details.
	16	*
	17	* You should have received a copy of the GNU General Public License along
	18	* with this program; if not, write to the Free Software Foundation, Inc.,
3f7cac41	19	* 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
1da177e4 LT	20	*/
1da177e4 LT	21
1da177e4 LT	22	#include "ieee754sp.h"
1da177e4 LT	23
2209bcb1	24	union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y)
1da177e4	25	{
3f7cac41 RB	26	int re;
	27	int rs;
	28	unsigned rm;
	29	unsigned short lxm;
	30	unsigned short hxm;
	31	unsigned short lym;
	32	unsigned short hym;
	33	unsigned lrm;
	34	unsigned hrm;
	35	unsigned t;
	36	unsigned at;
	37
1da177e4 LT	38	COMPXSP;
	39	COMPYSP;
	40
	41	EXPLODEXSP;
	42	EXPLODEYSP;
	43
9e8bad1f	44	ieee754_clearcx();
1da177e4 LT	45
	46	FLUSHXSP;
	47	FLUSHYSP;
	48
	49	switch (CLPAIR(xc, yc)) {
1da177e4	50	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
1da177e4 LT	51	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
	52	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
	53	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
	54	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
d5afa7e9 MR	55	return ieee754sp_nanxcpt(y);
	56
	57	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
	58	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
1da177e4 LT	59	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
	60	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
	61	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
	62	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
d5afa7e9	63	return ieee754sp_nanxcpt(x);
1da177e4 LT	64
	65	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
	66	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
	67	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
	68	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
	69	return y;
	70
	71	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
	72	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
	73	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
	74	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
	75	case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
	76	return x;
	77
	78
3f7cac41 RB	79	/*
	80	* Infinity handling
	81	*/
1da177e4 LT	82	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
1da177e4 LT	83	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
9e8bad1f	84	ieee754_setcx(IEEE754_INVALID_OPERATION);
90efba36	85	return ieee754sp_indef();
1da177e4 LT	86
	87	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
	88	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
	89	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
	90	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
	91	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
	92	return ieee754sp_inf(xs ^ ys);
	93
	94	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
	95	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
	96	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
	97	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
	98	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
	99	return ieee754sp_zero(xs ^ ys);
	100
	101
	102	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
	103	SPDNORMX;
	104
	105	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
	106	SPDNORMY;
	107	break;
	108
	109	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
	110	SPDNORMX;
	111	break;
	112
	113	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
	114	break;
	115	}
25985edc	116	/* rm = xm * ym, re = xe+ye basically */
1da177e4 LT	117	assert(xm & SP_HIDDEN_BIT);
	118	assert(ym & SP_HIDDEN_BIT);
	119
3f7cac41 RB	120	re = xe + ye;
	121	rs = xs ^ ys;
	122
	123	/* shunt to top of word */
	124	xm <<= 32 - (SP_FBITS + 1);
	125	ym <<= 32 - (SP_FBITS + 1);
	126
	127	/*
	128	* Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
	129	*/
	130	lxm = xm & 0xffff;
	131	hxm = xm >> 16;
	132	lym = ym & 0xffff;
	133	hym = ym >> 16;
	134
	135	lrm = lxm * lym; /* 16 * 16 => 32 */
	136	hrm = hxm * hym; /* 16 * 16 => 32 */
	137
	138	t = lxm * hym; /* 16 * 16 => 32 */
	139	at = lrm + (t << 16);
	140	hrm += at < lrm;
	141	lrm = at;
	142	hrm = hrm + (t >> 16);
	143
	144	t = hxm * lym; /* 16 * 16 => 32 */
	145	at = lrm + (t << 16);
	146	hrm += at < lrm;
	147	lrm = at;
	148	hrm = hrm + (t >> 16);
	149
	150	rm = hrm \| (lrm != 0);
	151
	152	/*
	153	* Sticky shift down to normal rounding precision.
	154	*/
	155	if ((int) rm < 0) {
	156	rm = (rm >> (32 - (SP_FBITS + 1 + 3))) \|
	157	((rm << (SP_FBITS + 1 + 3)) != 0);
	158	re++;
	159	} else {
	160	rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) \|
	161	((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
1da177e4	162	}
3f7cac41 RB	163	assert(rm & (SP_HIDDEN_BIT << 3));
	164
	165	return ieee754sp_format(rs, re, rm);
1da177e4	166	}