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
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
|
dnl x86-32 mpn_mod_1s_4p, requiring cmov.
dnl Contributed to the GNU project by Torbjorn Granlund.
dnl Copyright 2009, 2010 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of either:
dnl
dnl * the GNU Lesser General Public License as published by the Free
dnl Software Foundation; either version 3 of the License, or (at your
dnl option) any later version.
dnl
dnl or
dnl
dnl * the GNU General Public License as published by the Free Software
dnl Foundation; either version 2 of the License, or (at your option) any
dnl later version.
dnl
dnl or both in parallel, as here.
dnl
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 General Public License
dnl for more details.
dnl
dnl You should have received copies of the GNU General Public License and the
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
dnl see https://www.gnu.org/licenses/.
include(`../config.m4')
C cycles/limb
C P5 ?
C P6 model 0-8,10-12 ?
C P6 model 9 (Banias) ?
C P6 model 13 (Dothan) 6
C P4 model 0 (Willamette) ?
C P4 model 1 (?) ?
C P4 model 2 (Northwood) 15.5
C P4 model 3 (Prescott) ?
C P4 model 4 (Nocona) ?
C AMD K6 ?
C AMD K7 4.75
C AMD K8 ?
ASM_START()
TEXT
ALIGN(16)
PROLOGUE(mpn_mod_1s_4p)
push %ebp
push %edi
push %esi
push %ebx
sub $28, %esp
mov 60(%esp), %edi C cps[]
mov 8(%edi), %eax
mov 12(%edi), %edx
mov 16(%edi), %ecx
mov 20(%edi), %esi
mov 24(%edi), %edi
mov %eax, 4(%esp)
mov %edx, 8(%esp)
mov %ecx, 12(%esp)
mov %esi, 16(%esp)
mov %edi, 20(%esp)
mov 52(%esp), %eax C n
xor %edi, %edi
mov 48(%esp), %esi C up
lea -12(%esi,%eax,4), %esi
and $3, %eax
je L(b0)
cmp $2, %eax
jc L(b1)
je L(b2)
L(b3): mov 4(%esi), %eax
mull 4(%esp)
mov (%esi), %ebp
add %eax, %ebp
adc %edx, %edi
mov 8(%esi), %eax
mull 8(%esp)
lea -12(%esi), %esi
jmp L(m0)
L(b0): mov (%esi), %eax
mull 4(%esp)
mov -4(%esi), %ebp
add %eax, %ebp
adc %edx, %edi
mov 4(%esi), %eax
mull 8(%esp)
add %eax, %ebp
adc %edx, %edi
mov 8(%esi), %eax
mull 12(%esp)
lea -16(%esi), %esi
jmp L(m0)
L(b1): mov 8(%esi), %ebp
lea -4(%esi), %esi
jmp L(m1)
L(b2): mov 8(%esi), %edi
mov 4(%esi), %ebp
lea -8(%esi), %esi
jmp L(m1)
ALIGN(16)
L(top): mov (%esi), %eax
mull 4(%esp)
mov -4(%esi), %ebx
xor %ecx, %ecx
add %eax, %ebx
adc %edx, %ecx
mov 4(%esi), %eax
mull 8(%esp)
add %eax, %ebx
adc %edx, %ecx
mov 8(%esi), %eax
mull 12(%esp)
add %eax, %ebx
adc %edx, %ecx
lea -16(%esi), %esi
mov 16(%esp), %eax
mul %ebp
add %eax, %ebx
adc %edx, %ecx
mov 20(%esp), %eax
mul %edi
mov %ebx, %ebp
mov %ecx, %edi
L(m0): add %eax, %ebp
adc %edx, %edi
L(m1): subl $4, 52(%esp)
ja L(top)
L(end): mov 4(%esp), %eax
mul %edi
mov 60(%esp), %edi
add %eax, %ebp
adc $0, %edx
mov 4(%edi), %ecx
mov %edx, %esi
mov %ebp, %eax
sal %cl, %esi
mov %ecx, %ebx
neg %ecx
shr %cl, %eax
or %esi, %eax
lea 1(%eax), %esi
mull (%edi)
mov %ebx, %ecx
mov %eax, %ebx
mov %ebp, %eax
mov 56(%esp), %ebp
sal %cl, %eax
add %eax, %ebx
adc %esi, %edx
imul %ebp, %edx
sub %edx, %eax
lea (%eax,%ebp), %edx
cmp %eax, %ebx
cmovc( %edx, %eax)
mov %eax, %edx
sub %ebp, %eax
cmovc( %edx, %eax)
add $28, %esp
pop %ebx
pop %esi
pop %edi
pop %ebp
shr %cl, %eax
ret
EPILOGUE()
ALIGN(16)
PROLOGUE(mpn_mod_1s_4p_cps)
C CAUTION: This is the same code as in pentium4/sse2/mod_1_4.asm
push %ebp
push %edi
push %esi
push %ebx
mov 20(%esp), %ebp C FIXME: avoid bp for 0-idx
mov 24(%esp), %ebx
bsr %ebx, %ecx
xor $31, %ecx
sal %cl, %ebx C b << cnt
mov %ebx, %edx
not %edx
mov $-1, %eax
div %ebx
xor %edi, %edi
sub %ebx, %edi
mov $1, %esi
mov %eax, (%ebp) C store bi
mov %ecx, 4(%ebp) C store cnt
shld %cl, %eax, %esi
imul %edi, %esi
mov %eax, %edi
mul %esi
add %esi, %edx
shr %cl, %esi
mov %esi, 8(%ebp) C store B1modb
not %edx
imul %ebx, %edx
lea (%edx,%ebx), %esi
cmp %edx, %eax
cmovnc( %edx, %esi)
mov %edi, %eax
mul %esi
add %esi, %edx
shr %cl, %esi
mov %esi, 12(%ebp) C store B2modb
not %edx
imul %ebx, %edx
lea (%edx,%ebx), %esi
cmp %edx, %eax
cmovnc( %edx, %esi)
mov %edi, %eax
mul %esi
add %esi, %edx
shr %cl, %esi
mov %esi, 16(%ebp) C store B3modb
not %edx
imul %ebx, %edx
lea (%edx,%ebx), %esi
cmp %edx, %eax
cmovnc( %edx, %esi)
mov %edi, %eax
mul %esi
add %esi, %edx
shr %cl, %esi
mov %esi, 20(%ebp) C store B4modb
not %edx
imul %ebx, %edx
add %edx, %ebx
cmp %edx, %eax
cmovnc( %edx, %ebx)
shr %cl, %ebx
mov %ebx, 24(%ebp) C store B5modb
pop %ebx
pop %esi
pop %edi
pop %ebp
ret
EPILOGUE()
|
