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
|
.text
.align 16, 0x90
.globl __gmpn_div_qr_2n_pi1
.def __gmpn_div_qr_2n_pi1
.scl 2
.type 32
.endef
__gmpn_div_qr_2n_pi1:
push %rdi
push %rsi
mov %rcx, %rdi
mov %rdx, %rsi
mov %r8, %rdx
mov %r9, %rcx
mov 56(%rsp), %r8
mov 64(%rsp), %r9
mov 72(%rsp), %r10
mov %rdx, %r11
push %r15
push %r14
push %r13
push %r12
push %rbx
mov -16(%r11, %rcx, 8), %r12
mov -8(%r11, %rcx, 8), %rbx
mov %r12, %r14
mov %rbx, %r13
sub %r9, %r14
sbb %r8, %r13
cmovnc %r14, %r12
cmovnc %r13, %rbx
sbb %rax, %rax
inc %rax
push %rax
lea -2(%rcx), %rcx
mov %r8, %r15
neg %r15
jmp Lnext
.align 16, 0x90
Lloop:
mov %r10, %rax
mul %rbx
mov %r12, %r14
add %rax, %r14
adc %rbx, %rdx
mov %rdx, %r13
imul %r15, %rdx
mov %r9, %rax
lea (%rdx, %r12), %rbx
mul %r13
mov (%r11, %rcx, 8), %r12
sub %r9, %r12
sbb %r8, %rbx
sub %rax, %r12
sbb %rdx, %rbx
xor %eax, %eax
xor %edx, %edx
cmp %r14, %rbx
cmovnc %r9, %rax
cmovnc %r8, %rdx
adc $0, %r13
nop
add %rax, %r12
adc %rdx, %rbx
cmp %r8, %rbx
jae Lfix
Lbck:
mov %r13, (%rdi, %rcx, 8)
Lnext:
sub $1, %rcx
jnc Lloop
Lend:
mov %rbx, 8(%rsi)
mov %r12, (%rsi)
pop %rax
pop %rbx
pop %r12
pop %r13
pop %r14
pop %r15
pop %rsi
pop %rdi
ret
Lfix:
seta %dl
cmp %r9, %r12
setae %al
orb %dl, %al
je Lbck
inc %r13
sub %r9, %r12
sbb %r8, %rbx
jmp Lbck
|
