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
|
.text
.align 16, 0x90
.globl __gmpn_mul_2
.type __gmpn_mul_2,@function
__gmpn_mul_2:
push %rbx
push %rbp
mov (%rcx), %r8
mov 8(%rcx), %r9
mov (%rsi), %rax
mov %rdx, %r11
neg %r11
lea -8(%rsi,%rdx,8), %rsi
lea -8(%rdi,%rdx,8), %rdi
and $3, %edx
jz .Lm2p0
cmp $2, %edx
jc .Lm2p1
jz .Lm2p2
.Lm2p3:
mul %r8
xor %r10d, %r10d
mov %rax, %rcx
mov %rdx, %rbp
mov 8(%rsi,%r11,8), %rax
add $-1, %r11
mul %r9
add %rax, %rbp
jmp .Lm23
.Lm2p0:
mul %r8
xor %ebp, %ebp
mov %rax, %rbx
mov %rdx, %rcx
jmp .Lm20
.Lm2p1:
mul %r8
xor %r10d, %r10d
xor %ebx, %ebx
xor %ecx, %ecx
add $1, %r11
jmp .Lm2top
.Lm2p2:
mul %r8
xor %ebx, %ebx
xor %ecx, %ecx
mov %rax, %rbp
mov %rdx, %r10
mov 8(%rsi,%r11,8), %rax
add $-2, %r11
jmp .Lm22
.align 32, 0x90
.Lm2top:
add %rax, %r10
adc %rdx, %rbx
mov 0(%rsi,%r11,8), %rax
adc $0, %ecx
mov $0, %ebp
mul %r9
add %rax, %rbx
mov %r10, 0(%rdi,%r11,8)
adc %rdx, %rcx
mov 8(%rsi,%r11,8), %rax
mul %r8
add %rax, %rbx
adc %rdx, %rcx
adc $0, %ebp
.Lm20: mov 8(%rsi,%r11,8), %rax
mul %r9
add %rax, %rcx
adc %rdx, %rbp
mov 16(%rsi,%r11,8), %rax
mov $0, %r10d
mul %r8
add %rax, %rcx
mov 16(%rsi,%r11,8), %rax
adc %rdx, %rbp
adc $0, %r10d
mul %r9
add %rax, %rbp
mov %rbx, 8(%rdi,%r11,8)
.Lm23: adc %rdx, %r10
mov 24(%rsi,%r11,8), %rax
mul %r8
mov $0, %ebx
add %rax, %rbp
adc %rdx, %r10
mov %rcx, 16(%rdi,%r11,8)
mov 24(%rsi,%r11,8), %rax
mov $0, %ecx
adc $0, %ebx
.Lm22: mul %r9
add %rax, %r10
mov %rbp, 24(%rdi,%r11,8)
adc %rdx, %rbx
mov 32(%rsi,%r11,8), %rax
mul %r8
add $4, %r11
js .Lm2top
add %rax, %r10
adc %rdx, %rbx
adc $0, %ecx
mov (%rsi), %rax
mul %r9
mov %r10, (%rdi)
add %rax, %rbx
adc %rdx, %rcx
mov %rbx, 8(%rdi)
mov %rcx, %rax
pop %rbp
pop %rbx
ret
.size __gmpn_mul_2,.-__gmpn_mul_2
|
