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
261
262
263
264
265
266
267
268
269
270
271
272
|
dnl AMD64 mpn_mod_1s_4p
dnl Contributed to the GNU project by Torbjorn Granlund.
dnl Copyright 2009-2012, 2014 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 AMD K8,K9 3
C AMD K10 3
C Intel P4 15.5
C Intel core2 5
C Intel corei 4
C Intel atom 23
C VIA nano 4.75
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
ASM_START()
TEXT
ALIGN(16)
PROLOGUE(mpn_mod_1s_4p)
FUNC_ENTRY(4)
push %r15
push %r14
push %r13
push %r12
push %rbp
push %rbx
mov %rdx, %r15
mov %rcx, %r14
mov 16(%rcx), %r11 C B1modb
mov 24(%rcx), %rbx C B2modb
mov 32(%rcx), %rbp C B3modb
mov 40(%rcx), %r13 C B4modb
mov 48(%rcx), %r12 C B5modb
xor R32(%r8), R32(%r8)
mov R32(%rsi), R32(%rdx)
and $3, R32(%rdx)
je L(b0)
cmp $2, R32(%rdx)
jc L(b1)
je L(b2)
L(b3): lea -24(%rdi,%rsi,8), %rdi
mov 8(%rdi), %rax
mul %r11
mov (%rdi), %r9
add %rax, %r9
adc %rdx, %r8
mov 16(%rdi), %rax
mul %rbx
jmp L(m0)
ALIGN(8)
L(b0): lea -32(%rdi,%rsi,8), %rdi
mov 8(%rdi), %rax
mul %r11
mov (%rdi), %r9
add %rax, %r9
adc %rdx, %r8
mov 16(%rdi), %rax
mul %rbx
add %rax, %r9
adc %rdx, %r8
mov 24(%rdi), %rax
mul %rbp
jmp L(m0)
ALIGN(8)
L(b1): lea -8(%rdi,%rsi,8), %rdi
mov (%rdi), %r9
jmp L(m1)
ALIGN(8)
L(b2): lea -16(%rdi,%rsi,8), %rdi
mov 8(%rdi), %r8
mov (%rdi), %r9
jmp L(m1)
ALIGN(16)
L(top): mov -24(%rdi), %rax
mov -32(%rdi), %r10
mul %r11 C up[1] * B1modb
add %rax, %r10
mov -16(%rdi), %rax
mov $0, R32(%rcx)
adc %rdx, %rcx
mul %rbx C up[2] * B2modb
add %rax, %r10
mov -8(%rdi), %rax
adc %rdx, %rcx
sub $32, %rdi
mul %rbp C up[3] * B3modb
add %rax, %r10
mov %r13, %rax
adc %rdx, %rcx
mul %r9 C rl * B4modb
add %rax, %r10
mov %r12, %rax
adc %rdx, %rcx
mul %r8 C rh * B5modb
mov %r10, %r9
mov %rcx, %r8
L(m0): add %rax, %r9
adc %rdx, %r8
L(m1): sub $4, %rsi
ja L(top)
L(end): mov 8(%r14), R32(%rsi)
mov %r8, %rax
mul %r11
mov %rax, %r8
add %r9, %r8
adc $0, %rdx
xor R32(%rcx), R32(%rcx)
sub R32(%rsi), R32(%rcx)
mov %r8, %rdi
shr R8(%rcx), %rdi
mov R32(%rsi), R32(%rcx)
sal R8(%rcx), %rdx
or %rdx, %rdi
mov %rdi, %rax
mulq (%r14)
mov %r15, %rbx
mov %rax, %r9
sal R8(%rcx), %r8
inc %rdi
add %r8, %r9
adc %rdi, %rdx
imul %rbx, %rdx
sub %rdx, %r8
lea (%r8,%rbx), %rax
cmp %r8, %r9
cmovc %rax, %r8
mov %r8, %rax
sub %rbx, %rax
cmovc %r8, %rax
shr R8(%rcx), %rax
pop %rbx
pop %rbp
pop %r12
pop %r13
pop %r14
pop %r15
FUNC_EXIT()
ret
EPILOGUE()
ALIGN(16)
PROLOGUE(mpn_mod_1s_4p_cps)
FUNC_ENTRY(2)
push %rbp
bsr %rsi, %rcx
push %rbx
mov %rdi, %rbx
push %r12
xor $63, R32(%rcx)
mov %rsi, %r12
mov R32(%rcx), R32(%rbp) C preserve cnt over call
sal R8(%rcx), %r12 C b << cnt
IFSTD(` mov %r12, %rdi ') C pass parameter
IFDOS(` mov %r12, %rcx ') C pass parameter
IFDOS(` sub $32, %rsp ')
ASSERT(nz, `test $15, %rsp')
CALL( mpn_invert_limb)
IFDOS(` add $32, %rsp ')
mov %r12, %r8
mov %rax, %r11
mov %rax, (%rbx) C store bi
mov %rbp, 8(%rbx) C store cnt
neg %r8
mov R32(%rbp), R32(%rcx)
mov $1, R32(%rsi)
ifdef(`SHLD_SLOW',`
shl R8(%rcx), %rsi
neg R32(%rcx)
mov %rax, %rbp
shr R8(%rcx), %rax
or %rax, %rsi
mov %rbp, %rax
neg R32(%rcx)
',`
shld R8(%rcx), %rax, %rsi C FIXME: Slow on Atom and Nano
')
imul %r8, %rsi
mul %rsi
add %rsi, %rdx
shr R8(%rcx), %rsi
mov %rsi, 16(%rbx) C store B1modb
not %rdx
imul %r12, %rdx
lea (%rdx,%r12), %rsi
cmp %rdx, %rax
cmovnc %rdx, %rsi
mov %r11, %rax
mul %rsi
add %rsi, %rdx
shr R8(%rcx), %rsi
mov %rsi, 24(%rbx) C store B2modb
not %rdx
imul %r12, %rdx
lea (%rdx,%r12), %rsi
cmp %rdx, %rax
cmovnc %rdx, %rsi
mov %r11, %rax
mul %rsi
add %rsi, %rdx
shr R8(%rcx), %rsi
mov %rsi, 32(%rbx) C store B3modb
not %rdx
imul %r12, %rdx
lea (%rdx,%r12), %rsi
cmp %rdx, %rax
cmovnc %rdx, %rsi
mov %r11, %rax
mul %rsi
add %rsi, %rdx
shr R8(%rcx), %rsi
mov %rsi, 40(%rbx) C store B4modb
not %rdx
imul %r12, %rdx
add %rdx, %r12
cmp %rdx, %rax
cmovnc %rdx, %r12
shr R8(%rcx), %r12
mov %r12, 48(%rbx) C store B5modb
pop %r12
pop %rbx
pop %rbp
FUNC_EXIT()
ret
EPILOGUE()
|
