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
|
.text
.align 4, 0x90
.globl ___gmpn_mod_1_1p
___gmpn_mod_1_1p:
push %rbp
push %rbx
mov %rdx, %rbx
mov %rcx, %r8
mov -8(%rdi, %rsi, 8), %rax
cmp $3, %rsi
jnc Lfirst
mov -16(%rdi, %rsi, 8), %rbp
jmp Lreduce_two
Lfirst:
mov 24(%r8), %r11
mul %r11
mov -24(%rdi, %rsi, 8), %rbp
add %rax, %rbp
mov -16(%rdi, %rsi, 8), %rax
adc %rdx, %rax
sbb %rcx, %rcx
sub $4, %rsi
jc Lreduce_three
mov %r11, %r10
sub %rbx, %r10
.align 4, 0x90
Ltop: and %r11, %rcx
lea (%r10, %rbp), %r9
mul %r11
add %rbp, %rcx
mov (%rdi, %rsi, 8), %rbp
cmovc %r9, %rcx
add %rax, %rbp
mov %rcx, %rax
adc %rdx, %rax
sbb %rcx, %rcx
sub $1, %rsi
jnc Ltop
Lreduce_three:
and %rbx, %rcx
sub %rcx, %rax
Lreduce_two:
mov 8(%r8), %ecx
test %ecx, %ecx
jz Lnormalized
mulq 16(%r8)
xor %r9, %r9
add %rax, %rbp
adc %rdx, %r9
mov %r9, %rax
shld %cl, %rbp, %rax
shl %cl, %rbp
jmp Ludiv
Lnormalized:
mov %rax, %r9
sub %rbx, %r9
cmovnc %r9, %rax
Ludiv:
lea 1(%rax), %r9
mulq (%r8)
add %rbp, %rax
adc %r9, %rdx
imul %rbx, %rdx
sub %rdx, %rbp
cmp %rbp, %rax
lea (%rbx, %rbp), %rax
cmovnc %rbp, %rax
cmp %rbx, %rax
jnc Lfix
Lok: shr %cl, %rax
pop %rbx
pop %rbp
ret
Lfix: sub %rbx, %rax
jmp Lok
.align 4, 0x90
.globl ___gmpn_mod_1_1p_cps
___gmpn_mod_1_1p_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
neg %r12
mov %r12, %r8
mov %rax, (%rbx)
mov %rbp, 8(%rbx)
imul %rax, %r12
mov %r12, 24(%rbx)
mov %ebp, %ecx
test %ecx, %ecx
jz Lz
mov $1, %edx
shld %cl, %rax, %rdx
imul %rdx, %r8
shr %cl, %r8
mov %r8, 16(%rbx)
Lz:
pop %r12
pop %rbx
pop %rbp
ret
|
