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
|
.text
.align 16, 0x90
.globl __gmpn_mod_1s_2p
.type __gmpn_mod_1s_2p,@function
__gmpn_mod_1s_2p:
push %r14
test $1, %sil
mov %rdx, %r14
push %r13
mov %rcx, %r13
push %r12
push %rbp
push %rbx
mov 16(%rcx), %r10
mov 24(%rcx), %rbx
mov 32(%rcx), %rbp
je .Lb0
dec %rsi
je .Lone
mov -8(%rdi,%rsi,8), %rax
mul %r10
mov %rax, %r9
mov %rdx, %r8
mov (%rdi,%rsi,8), %rax
add -16(%rdi,%rsi,8), %r9
adc $0, %r8
mul %rbx
add %rax, %r9
adc %rdx, %r8
jmp .L11
.Lb0: mov -8(%rdi,%rsi,8), %r8
mov -16(%rdi,%rsi,8), %r9
.L11: sub $4, %rsi
jb .Led2
lea 40(%rdi,%rsi,8), %rdi
mov -40(%rdi), %r11
mov -32(%rdi), %rax
jmp .Lm0
.align 16, 0x90
.Ltop: mov -24(%rdi), %r9
add %rax, %r11
mov -16(%rdi), %rax
adc %rdx, %r12
mul %r10
add %rax, %r9
mov %r11, %rax
mov %rdx, %r8
adc $0, %r8
mul %rbx
add %rax, %r9
mov %r12, %rax
adc %rdx, %r8
mul %rbp
sub $2, %rsi
jb .Led1
mov -40(%rdi), %r11
add %rax, %r9
mov -32(%rdi), %rax
adc %rdx, %r8
.Lm0: mul %r10
add %rax, %r11
mov %r9, %rax
mov %rdx, %r12
adc $0, %r12
mul %rbx
add %rax, %r11
lea -32(%rdi), %rdi
mov %r8, %rax
adc %rdx, %r12
mul %rbp
sub $2, %rsi
jae .Ltop
.Led0: mov %r11, %r9
mov %r12, %r8
.Led1: add %rax, %r9
adc %rdx, %r8
.Led2: mov 8(%r13), %edi
mov %r8, %rax
mov %r9, %r8
mul %r10
add %rax, %r8
adc $0, %rdx
.L1: xor %ecx, %ecx
mov %r8, %r9
sub %edi, %ecx
shr %cl, %r9
mov %edi, %ecx
sal %cl, %rdx
or %rdx, %r9
sal %cl, %r8
mov %r9, %rax
mulq (%r13)
mov %rax, %rsi
inc %r9
add %r8, %rsi
adc %r9, %rdx
imul %r14, %rdx
sub %rdx, %r8
lea (%r8,%r14), %rax
cmp %r8, %rsi
cmovc %rax, %r8
mov %r8, %rax
sub %r14, %rax
cmovc %r8, %rax
mov %edi, %ecx
shr %cl, %rax
pop %rbx
pop %rbp
pop %r12
pop %r13
pop %r14
ret
.Lone:
mov (%rdi), %r8
mov 8(%rcx), %edi
xor %rdx, %rdx
jmp .L1
.size __gmpn_mod_1s_2p,.-__gmpn_mod_1s_2p
.align 16, 0x90
.globl __gmpn_mod_1s_2p_cps
.type __gmpn_mod_1s_2p_cps,@function
__gmpn_mod_1s_2p_cps:
push %rbp
bsr %rsi, %rcx
push %rbx
mov %rdi, %rbx
push %r12
xor $63, %ecx
mov %rsi, %r12
mov %ecx, %ebp
sal %cl, %r12
mov %r12, %rdi
call __gmpn_invert_limb@PLT
mov %r12, %r8
mov %rax, %r11
mov %rax, (%rbx)
mov %rbp, 8(%rbx)
neg %r8
mov %ebp, %ecx
mov $1, %esi
shld %cl, %rax, %rsi
imul %r8, %rsi
mul %rsi
add %rsi, %rdx
shr %cl, %rsi
mov %rsi, 16(%rbx)
not %rdx
imul %r12, %rdx
lea (%rdx,%r12), %rsi
cmp %rdx, %rax
cmovnc %rdx, %rsi
mov %r11, %rax
mul %rsi
add %rsi, %rdx
shr %cl, %rsi
mov %rsi, 24(%rbx)
not %rdx
imul %r12, %rdx
add %rdx, %r12
cmp %rdx, %rax
cmovnc %rdx, %r12
shr %cl, %r12
mov %r12, 32(%rbx)
pop %r12
pop %rbx
pop %rbp
ret
.size __gmpn_mod_1s_2p_cps,.-__gmpn_mod_1s_2p_cps
|
