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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
|
dnl SPARC 64-bit submull/submulu -- Helper for mpn_submul_1 and mpn_mul_1.
dnl Copyright (C) 1998, 2000 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of the GNU Lesser General Public License as published
dnl by the Free Software Foundation; either version 2.1 of the License, or (at
dnl your option) any later version.
dnl The GNU MP Library is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
dnl License for more details.
dnl You should have received a copy of the GNU Lesser General Public License
dnl along with the GNU MP Library; see the file COPYING.LIB. If not, write to
dnl the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
dnl MA 02111-1307, USA.
ifdef(`LOWPART',
`submull:',
`submulu:')
save %sp,-256,%sp
sethi %hi(0xffff0000),%o0
andn %i3,%o0,%o0
st %o0,[%fp-17]
ld [%fp-17],%f11
fxtod %f10,%f6
srl %i3,16,%o0
st %o0,[%fp-17]
ld [%fp-17],%f11
fxtod %f10,%f8
mov 0,%g3 C cy = 0
ld [%i1+4],%f11
subcc %i2,1,%i2
dnl be,pn %icc,E(end1)
add %i1,4,%i1 C s1_ptr++
fxtod %f10,%f2
ld [%i1-4],%f11
add %i1,4,%i1 C s1_ptr++
fmuld %f2,%f8,%f16
fmuld %f2,%f6,%f4
fdtox %f16,%f14
std %f14,[%fp-25]
fdtox %f4,%f12
subcc %i2,1,%i2
be,pn %icc,E(end2)
std %f12,[%fp-17]
fxtod %f10,%f2
ld [%i1+4],%f11
add %i1,4,%i1 C s1_ptr++
fmuld %f2,%f8,%f16
fmuld %f2,%f6,%f4
fdtox %f16,%f14
std %f14,[%fp-41]
fdtox %f4,%f12
subcc %i2,1,%i2
dnl be,pn %icc,E(end3)
std %f12,[%fp-33]
fxtod %f10,%f2
ld [%i1-4],%f11
add %i1,4,%i1 C s1_ptr++
ld [%i0+DLO],%g5
ldx [%fp-25],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-17],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-25]
fdtox %f4,%f12
add %i0,4,%i0 C res_ptr++
subcc %i2,1,%i2
be,pn %icc,E(end4)
std %f12,[%fp-17]
b,a E(loop)
nop C nop is cheap to nullify
ALIGN(16)
C BEGIN LOOP
E(loop):
fxtod %f10,%f2
ld [%i1+4],%f11
add %i1,4,%i1 C s1_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0+DHI],%g5
srlx %g4,32,%g3
ldx [%fp-41],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-33],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4+DLO]
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-41]
fdtox %f4,%f12
std %f12,[%fp-33]
sub %i2,2,%i2
add %i0,4,%i0 C res_ptr++
fxtod %f10,%f2
ld [%i1-4],%f11
add %i1,4,%i1 C s1_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0+DLO],%g5
srlx %g4,32,%g3
ldx [%fp-25],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-17],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4+DHI]
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-25]
fdtox %f4,%f12
std %f12,[%fp-17]
brnz,pt %i2,E(loop)
add %i0,4,%i0 C res_ptr++
C END LOOP
E(loope):
E(end4):
fxtod %f10,%f2
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0+DHI],%g5
srlx %g4,32,%g3
ldx [%fp-41],%g2 C p16
fmuld %f2,%f8,%f16
ldx [%fp-33],%g1 C p0
fmuld %f2,%f6,%f4
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4+DLO]
fdtox %f16,%f14
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
std %f14,[%fp-41]
fdtox %f4,%f12
std %f12,[%fp-33]
add %i0,4,%i0 C res_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ld [%i0+DLO],%g5
srlx %g4,32,%g3
ldx [%fp-25],%g2 C p16
ldx [%fp-17],%g1 C p0
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4+DHI]
b,a E(yyy)
E(end2):
fxtod %f10,%f2
fmuld %f2,%f8,%f16
fmuld %f2,%f6,%f4
fdtox %f16,%f14
std %f14,[%fp-41]
fdtox %f4,%f12
std %f12,[%fp-33]
ld [%i0+DLO],%g5
ldx [%fp-25],%g2 C p16
ldx [%fp-17],%g1 C p0
sllx %g2,16,%g2 C align p16
E(yyy): add %g2,%g1,%g1 C add p16 to p0 (ADD1)
add %i0,4,%i0 C res_ptr++
add %g3,%g1,%g4 C p += cy
subxcc %g5,%g4,%l2 C add *res_ptr to p0 (ADD2)
ifdef(`LOWPART',
` ld [%i0+DHI],%g5')
srlx %g4,32,%g3
ldx [%fp-41],%g2 C p16
ldx [%fp-33],%g1 C p0
sllx %g2,16,%g2 C align p16
st %l2,[%i0-4+DLO]
add %g2,%g1,%g1 C add p16 to p0 (ADD1)
add %i0,4,%i0 C res_ptr++
add %g3,%g1,%g4 C p += cy
ifdef(`LOWPART',
` subxcc %g5,%g4,%l2') C add *res_ptr to p0 (ADD2)
ifdef(`LOWPART',
` st %l2,[%i0-4+DHI]
srlx %g4,32,%g4')
addx %g4,0,%g4
ret
restore %g0,%g4,%o0 C sideeffect: put cy in retreg
ifdef(`LOWPART',
`EPILOGUE(submull)',
`EPILOGUE(submulu)')
|
