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
|
.text
.align 16, 0x90
.globl __gmpn_mul_1c
.def __gmpn_mul_1c
.scl 2
.type 32
.endef
__gmpn_mul_1c:
push %rsi
push %rdi
mov %rdx, %rsi
push %rbx
mov 64(%rsp), %r10
jmp Lcommon
.globl __gmpn_mul_1
.def __gmpn_mul_1
.scl 2
.type 32
.endef
__gmpn_mul_1:
push %rsi
push %rdi
mov %rdx, %rsi
push %rbx
xor %r10, %r10
Lcommon:
mov (%rsi), %rax
mov %r8, %rbx
mul %r9
add %r10, %rax
adc $0, %rdx
and $3, %ebx
jz Lb0
cmp $2, %ebx
jz Lb2
jg Lb3
Lb1: dec %r8
jne Lgt1
mov %rax, (%rcx)
jmp Lret
Lgt1: lea 8(%rsi,%r8,8), %rsi
lea -8(%rcx,%r8,8), %rcx
neg %r8
xor %r10, %r10
xor %ebx, %ebx
mov %rax, %rdi
mov (%rsi,%r8,8), %rax
mov %rdx, %r11
jmp LL1
Lb0: lea (%rsi,%r8,8), %rsi
lea -16(%rcx,%r8,8), %rcx
neg %r8
xor %r10, %r10
mov %rax, %r11
mov %rdx, %rbx
jmp LL0
Lb3: lea -8(%rsi,%r8,8), %rsi
lea -24(%rcx,%r8,8), %rcx
neg %r8
mov %rax, %rbx
mov %rdx, %r10
jmp LL3
Lb2: lea -16(%rsi,%r8,8), %rsi
lea -32(%rcx,%r8,8), %rcx
neg %r8
xor %r11, %r11
xor %ebx, %ebx
mov %rax, %r10
mov 24(%rsi,%r8,8), %rax
mov %rdx, %rdi
jmp LL2
.align 16, 0x90
Ltop: mov %r10, (%rcx,%r8,8)
add %rax, %rdi
mov (%rsi,%r8,8), %rax
adc %rdx, %r11
mov $0, %r10d
LL1: mul %r9
mov %rdi, 8(%rcx,%r8,8)
add %rax, %r11
adc %rdx, %rbx
LL0: mov 8(%rsi,%r8,8), %rax
mul %r9
mov %r11, 16(%rcx,%r8,8)
add %rax, %rbx
adc %rdx, %r10
LL3: mov 16(%rsi,%r8,8), %rax
mul %r9
mov %rbx, 24(%rcx,%r8,8)
mov $0, %r11d
mov %r11, %rbx
add %rax, %r10
mov 24(%rsi,%r8,8), %rax
mov %r11, %rdi
adc %rdx, %rdi
LL2: mul %r9
add $4, %r8
js Ltop
mov %r10, (%rcx,%r8,8)
add %rax, %rdi
adc %r11, %rdx
mov %rdi, 8(%rcx,%r8,8)
add %r11, %rdx
Lret: mov %rdx, %rax
pop %rbx
pop %rdi
pop %rsi
ret
|
