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
|
.text
.align 16, 0x90
.globl __gmpn_rsh1add_nc
.def __gmpn_rsh1add_nc
.scl 2
.type 32
.endef
__gmpn_rsh1add_nc:
push %rdi
push %rsi
mov %rcx, %rdi
mov %rdx, %rsi
mov %r8, %rdx
mov %r9, %rcx
mov 56(%rsp), %r8
push %rbx
xor %eax, %eax
neg %r8
mov (%rsi), %rbx
adc (%rdx), %rbx
jmp Lent
.align 16, 0x90
.globl __gmpn_rsh1add_n
.def __gmpn_rsh1add_n
.scl 2
.type 32
.endef
__gmpn_rsh1add_n:
push %rdi
push %rsi
mov %rcx, %rdi
mov %rdx, %rsi
mov %r8, %rdx
mov %r9, %rcx
push %rbx
xor %eax, %eax
mov (%rsi), %rbx
add (%rdx), %rbx
Lent:
rcr %rbx
adc %eax, %eax
mov %ecx, %r11d
and $3, %r11d
cmp $1, %r11d
je Ldo
Ln1: cmp $2, %r11d
jne Ln2
add %rbx, %rbx
mov 8(%rsi), %r10
adc 8(%rdx), %r10
lea 8(%rsi), %rsi
lea 8(%rdx), %rdx
lea 8(%rdi), %rdi
rcr %r10
rcr %rbx
mov %rbx, -8(%rdi)
jmp Lcj1
Ln2: cmp $3, %r11d
jne Ln3
add %rbx, %rbx
mov 8(%rsi), %r9
mov 16(%rsi), %r10
adc 8(%rdx), %r9
adc 16(%rdx), %r10
lea 16(%rsi), %rsi
lea 16(%rdx), %rdx
lea 16(%rdi), %rdi
rcr %r10
rcr %r9
rcr %rbx
mov %rbx, -16(%rdi)
jmp Lcj2
Ln3: dec %rcx
add %rbx, %rbx
mov 8(%rsi), %r8
mov 16(%rsi), %r9
adc 8(%rdx), %r8
adc 16(%rdx), %r9
mov 24(%rsi), %r10
adc 24(%rdx), %r10
lea 24(%rsi), %rsi
lea 24(%rdx), %rdx
lea 24(%rdi), %rdi
rcr %r10
rcr %r9
rcr %r8
rcr %rbx
mov %rbx, -24(%rdi)
mov %r8, -16(%rdi)
Lcj2: mov %r9, -8(%rdi)
Lcj1: mov %r10, %rbx
Ldo:
shr $2, %rcx
je Lend
.align 16, 0x90
Ltop: add %rbx, %rbx
mov 8(%rsi), %r8
mov 16(%rsi), %r9
adc 8(%rdx), %r8
adc 16(%rdx), %r9
mov 24(%rsi), %r10
mov 32(%rsi), %r11
adc 24(%rdx), %r10
adc 32(%rdx), %r11
lea 32(%rsi), %rsi
lea 32(%rdx), %rdx
rcr %r11
rcr %r10
rcr %r9
rcr %r8
rcr %rbx
mov %rbx, (%rdi)
mov %r8, 8(%rdi)
mov %r9, 16(%rdi)
mov %r10, 24(%rdi)
mov %r11, %rbx
lea 32(%rdi), %rdi
dec %rcx
jne Ltop
Lend: mov %rbx, (%rdi)
pop %rbx
pop %rsi
pop %rdi
ret
|
