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
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
|
.text
.align 16, 0x90
.globl __gmpn_div_qr_1n_pi1
.type __gmpn_div_qr_1n_pi1,@function
__gmpn_div_qr_1n_pi1:
dec %rdx
jnz .Lfirst
lea 1(%rcx), %r10
mov %rcx, %rax
mul %r9
mov (%rsi), %r11
add %r11, %rax
adc %r10, %rdx
mov %rdx, %r10
imul %r8, %rdx
sub %rdx, %r11
cmp %r11, %rax
lea (%r11, %r8), %rax
cmovnc %r11, %rax
sbb $0, %r10
cmp %r8, %rax
jc .Lsingle_div_done
sub %r8, %rax
add $1, %r10
.Lsingle_div_done:
mov %r10, (%rdi)
ret
.Lfirst:
push %r15
push %r14
push %r13
push %r12
push %rbx
push %rbp
mov %r8, %rbp
imul %r9, %rbp
neg %rbp
mov %rbp, %rbx
sub %r8, %rbx
push %r8
mov %rdx, %r8
mov %r9, %rax
mul %rcx
mov %rax, %r13
add %rcx, %rdx
mov %rdx, %r10
mov %rbp, %rax
mul %rcx
mov -8(%rsi, %r8, 8), %r11
mov (%rsi, %r8, 8), %rcx
mov %r10, (%rdi, %r8, 8)
add %rax, %r11
adc %rdx, %rcx
sbb %r12, %r12
dec %r8
mov %rcx, %rax
jz .Lfinal
mov $0, %r14d
.align 16, 0x90
.Lloop:
cmovc %r9, %r14
mov %r12, %r15
neg %r15
mul %r9
add %rdx, %r14
adc $0, %r15
add %r13, %r14
mov %rax, %r13
mov %rbp, %rax
lea (%rbx, %r11), %r10
adc $0, %r15
mul %rcx
and %rbp, %r12
add %r12, %r11
cmovnc %r11, %r10
adc %rcx, %r14
mov -8(%rsi, %r8, 8), %r11
adc %r15, 8(%rdi, %r8, 8)
jc .Lq_incr
.Lq_incr_done:
add %rax, %r11
mov %r10, %rax
adc %rdx, %rax
mov %r14, (%rdi, %r8, 8)
mov $0, %r14d
sbb %r12, %r12
dec %r8
mov %rax, %rcx
jnz .Lloop
.Lfinal:
pop %r8
mov %r12, %r14
and %r8, %r12
sub %r12, %rax
neg %r14
mov %rax, %rcx
sub %r8, %rax
cmovc %rcx, %rax
sbb $-1, %r14
lea 1(%rax), %r10
mul %r9
add %r11, %rax
adc %r10, %rdx
mov %rdx, %r10
imul %r8, %rdx
sub %rdx, %r11
cmp %r11, %rax
lea (%r11, %r8), %rax
cmovnc %r11, %rax
sbb $0, %r10
cmp %r8, %rax
jc .Ldiv_done
sub %r8, %rax
add $1, %r10
.Ldiv_done:
add %r10, %r13
mov %r13, (%rdi)
adc %r14, 8(%rdi)
jnc .Ldone
.Lfinal_q_incr:
addq $1, 16(%rdi)
lea 8(%rdi), %rdi
jc .Lfinal_q_incr
.Ldone:
pop %rbp
pop %rbx
pop %r12
pop %r13
pop %r14
pop %r15
ret
.Lq_incr:
lea 16(%rdi, %r8, 8), %rcx
.Lq_incr_loop:
addq $1, (%rcx)
jnc .Lq_incr_done
lea 8(%rcx), %rcx
jmp .Lq_incr_loop
.size __gmpn_div_qr_1n_pi1,.-__gmpn_div_qr_1n_pi1
|
