dp_mul.c
4.39 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
/* 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_mul(union ieee754dp x, union ieee754dp y)
{
int re;
int rs;
u64 rm;
unsigned lxm;
unsigned hxm;
unsigned lym;
unsigned hym;
u64 lrm;
u64 hrm;
u64 t;
u64 at;
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_ZERO):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
ieee754_setcx(IEEE754_INVALID_OPERATION);
return ieee754dp_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 ieee754dp_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 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;
break;
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
break;
}
/* rm = xm * ym, re = xe+ye basically */
assert(xm & DP_HIDDEN_BIT);
assert(ym & DP_HIDDEN_BIT);
re = xe + ye;
rs = xs ^ ys;
/* shunt to top of word */
xm <<= 64 - (DP_FBITS + 1);
ym <<= 64 - (DP_FBITS + 1);
/*
* Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
*/
/* 32 * 32 => 64 */
#define DPXMULT(x, y) ((u64)(x) * (u64)y)
lxm = xm;
hxm = xm >> 32;
lym = ym;
hym = ym >> 32;
lrm = DPXMULT(lxm, lym);
hrm = DPXMULT(hxm, hym);
t = DPXMULT(lxm, hym);
at = lrm + (t << 32);
hrm += at < lrm;
lrm = at;
hrm = hrm + (t >> 32);
t = DPXMULT(hxm, lym);
at = lrm + (t << 32);
hrm += at < lrm;
lrm = at;
hrm = hrm + (t >> 32);
rm = hrm | (lrm != 0);
/*
* Sticky shift down to normal rounding precision.
*/
if ((s64) rm < 0) {
rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
((rm << (DP_FBITS + 1 + 3)) != 0);
re++;
} else {
rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
}
assert(rm & (DP_HIDDEN_BIT << 3));
return ieee754dp_format(rs, re, rm);
}