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
|
.text
.align 16, 0x90
.globl __gmpn_divexact_1
.def __gmpn_divexact_1
.scl 2
.type 32
.endef
__gmpn_divexact_1:
push %rdi
push %rsi
mov %rcx, %rdi
mov %rdx, %rsi
mov %r8, %rdx
mov %r9, %rcx
push %rbx
mov %rcx, %rax
xor %ecx, %ecx
mov %rdx, %r8
bt $0, %eax
jnc Levn
Lodd: mov %rax, %rbx
shr %eax
and $127, %eax
lea __gmp_binvert_limb_table(%rip), %rdx
movzbl (%rdx,%rax), %eax
mov %rbx, %r11
lea (%rax,%rax), %edx
imul %eax, %eax
imul %ebx, %eax
sub %eax, %edx
lea (%rdx,%rdx), %eax
imul %edx, %edx
imul %ebx, %edx
sub %edx, %eax
lea (%rax,%rax), %r10
imul %rax, %rax
imul %rbx, %rax
sub %rax, %r10
lea (%rsi,%r8,8), %rsi
lea -8(%rdi,%r8,8), %rdi
neg %r8
mov (%rsi,%r8,8), %rax
inc %r8
jz Lone
mov (%rsi,%r8,8), %rdx
shrd %cl, %rdx, %rax
xor %ebx, %ebx
jmp Lent
Levn: bsf %rax, %rcx
shr %cl, %rax
jmp Lodd
.align 8, 0x90
Ltop:
mul %r11
mov -8(%rsi,%r8,8), %rax
mov (%rsi,%r8,8), %r9
shrd %cl, %r9, %rax
nop
sub %rbx, %rax
setc %bl
sub %rdx, %rax
adc $0, %rbx
Lent: imul %r10, %rax
mov %rax, (%rdi,%r8,8)
inc %r8
jnz Ltop
mul %r11
mov -8(%rsi), %rax
shr %cl, %rax
sub %rbx, %rax
sub %rdx, %rax
imul %r10, %rax
mov %rax, (%rdi)
pop %rbx
pop %rsi
pop %rdi
ret
Lone: shr %cl, %rax
imul %r10, %rax
mov %rax, (%rdi)
pop %rbx
pop %rsi
pop %rdi
ret
|
