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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
|
.text
.align 5, 0x90
.globl ___gmpn_mullo_basecase
___gmpn_mullo_basecase:
mov %rdx, %r8
mov (%rsi), %rdx
cmp $4, %rcx
jb Lsmall
push %rbx
push %rbp
push %r12
push %r13
mov (%r8), %r9
mov 8(%r8), %rbx
lea 2(%rcx), %rbp
shr $2, %rbp
neg %rcx
add $2, %rcx
push %rsi
test $1, %cl
jnz Lm2x1
Lm2x0:.byte 0xc4,66,171,0xf6,233
xor %r12d, %r12d
test $2, %cl
jz Lm2b2
Lm2b0:lea -8(%rdi), %rdi
lea -8(%rsi), %rsi
jmp Lm2e0
Lm2b2:lea -24(%rdi), %rdi
lea 8(%rsi), %rsi
jmp Lm2e2
Lm2x1:.byte 0xc4,66,155,0xf6,217
xor %r10d, %r10d
test $2, %cl
jnz Lm2b3
Lm2b1:jmp Lm2e1
Lm2b3:lea -16(%rdi), %rdi
lea -16(%rsi), %rsi
jmp Lm2e3
.align 4, 0x90
Lm2tp:.byte 0xc4,98,251,0xf6,211
add %rax, %r12
mov (%rsi), %rdx
.byte 0xc4,66,251,0xf6,217
adc $0, %r10
add %rax, %r12
adc $0, %r11
add %r13, %r12
Lm2e1:mov %r12, (%rdi)
adc $0, %r11
.byte 0xc4,98,251,0xf6,227
add %rax, %r10
mov 8(%rsi), %rdx
adc $0, %r12
.byte 0xc4,66,251,0xf6,233
add %rax, %r10
adc $0, %r13
add %r11, %r10
Lm2e0:mov %r10, 8(%rdi)
adc $0, %r13
.byte 0xc4,98,251,0xf6,211
add %rax, %r12
mov 16(%rsi), %rdx
.byte 0xc4,66,251,0xf6,217
adc $0, %r10
add %rax, %r12
adc $0, %r11
add %r13, %r12
Lm2e3:mov %r12, 16(%rdi)
adc $0, %r11
.byte 0xc4,98,251,0xf6,227
add %rax, %r10
mov 24(%rsi), %rdx
adc $0, %r12
.byte 0xc4,66,251,0xf6,233
add %rax, %r10
adc $0, %r13
add %r11, %r10
lea 32(%rsi), %rsi
Lm2e2:mov %r10, 24(%rdi)
adc $0, %r13
dec %rbp
lea 32(%rdi), %rdi
jnz Lm2tp
Lm2ed:.byte 0xc4,98,251,0xf6,211
add %rax, %r12
mov (%rsi), %rdx
.byte 0xc4,66,251,0xf6,217
add %r12, %rax
add %r13, %rax
mov %rax, (%rdi)
mov (%rsp), %rsi
lea 16(%r8), %r8
lea 8(%rdi,%rcx,8), %rdi
add $2, %rcx
jge Lcor1
push %r14
push %r15
Louter:
mov (%r8), %r9
mov 8(%r8), %rbx
lea (%rcx), %rbp
sar $2, %rbp
mov (%rsi), %rdx
test $1, %cl
jnz Lbx1
Lbx0: mov (%rdi), %r15
mov 8(%rdi), %r14
.byte 0xc4,66,251,0xf6,233
add %rax, %r15
adc $0, %r13
.byte 0xc4,98,251,0xf6,211
add %rax, %r14
adc $0, %r10
mov 8(%rsi), %rdx
mov %r15, (%rdi)
.byte 0xc4,66,251,0xf6,217
test $2, %cl
jz Lb2
Lb0: lea 8(%rdi), %rdi
lea 8(%rsi), %rsi
jmp Llo0
Lb2: mov 16(%rdi), %r15
lea 24(%rdi), %rdi
lea 24(%rsi), %rsi
jmp Llo2
Lbx1: mov (%rdi), %r14
mov 8(%rdi), %r15
.byte 0xc4,66,251,0xf6,217
add %rax, %r14
.byte 0xc4,98,251,0xf6,227
adc $0, %r11
mov %r14, (%rdi)
add %rax, %r15
adc $0, %r12
mov 8(%rsi), %rdx
test $2, %cl
jnz Lb3
Lb1: lea 16(%rsi), %rsi
lea 16(%rdi), %rdi
jmp Llo1
Lb3: mov 16(%rdi), %r14
lea 32(%rsi), %rsi
.byte 0xc4,66,251,0xf6,233
inc %rbp
jz Lcj3
jmp Llo3
.align 4, 0x90
Ltop: .byte 0xc4,66,251,0xf6,233
add %r10, %r15
adc $0, %r12
Llo3: add %rax, %r15
adc $0, %r13
.byte 0xc4,98,251,0xf6,211
add %rax, %r14
adc $0, %r10
lea 32(%rdi), %rdi
add %r11, %r15
mov -16(%rsi), %rdx
mov %r15, -24(%rdi)
adc $0, %r13
add %r12, %r14
mov -8(%rdi), %r15
.byte 0xc4,66,251,0xf6,217
adc $0, %r10
Llo2: add %rax, %r14
.byte 0xc4,98,251,0xf6,227
adc $0, %r11
add %r13, %r14
mov %r14, -16(%rdi)
adc $0, %r11
add %rax, %r15
adc $0, %r12
add %r10, %r15
mov -8(%rsi), %rdx
adc $0, %r12
Llo1: .byte 0xc4,66,251,0xf6,233
add %rax, %r15
adc $0, %r13
mov (%rdi), %r14
.byte 0xc4,98,251,0xf6,211
add %rax, %r14
adc $0, %r10
add %r11, %r15
mov %r15, -8(%rdi)
adc $0, %r13
mov (%rsi), %rdx
add %r12, %r14
.byte 0xc4,66,251,0xf6,217
adc $0, %r10
Llo0: add %rax, %r14
adc $0, %r11
.byte 0xc4,98,251,0xf6,227
add %r13, %r14
mov 8(%rdi), %r15
mov %r14, (%rdi)
mov 16(%rdi), %r14
adc $0, %r11
add %rax, %r15
adc $0, %r12
mov 8(%rsi), %rdx
lea 32(%rsi), %rsi
inc %rbp
jnz Ltop
Lend: .byte 0xc4,66,251,0xf6,233
add %r10, %r15
adc $0, %r12
Lcj3: add %rax, %r15
adc $0, %r13
.byte 0xc4,98,251,0xf6,211
add %rax, %r14
add %r11, %r15
mov -16(%rsi), %rdx
mov %r15, 8(%rdi)
adc $0, %r13
add %r12, %r14
.byte 0xc4,66,251,0xf6,217
add %r14, %rax
add %r13, %rax
mov %rax, 16(%rdi)
mov 16(%rsp), %rsi
lea 16(%r8), %r8
lea 24(%rdi,%rcx,8), %rdi
add $2, %rcx
jl Louter
pop %r15
pop %r14
jnz Lcor0
Lcor1:mov (%r8), %r9
mov 8(%r8), %rbx
mov (%rsi), %rdx
.byte 0xc4,194,155,0xf6,233
add (%rdi), %r12
adc %rax, %rbp
mov 8(%rsi), %r10
imul %r9, %r10
imul %rbx, %rdx
mov %r12, (%rdi)
add %r10, %rdx
add %rbp, %rdx
mov %rdx, 8(%rdi)
pop %rax
pop %r13
pop %r12
pop %rbp
pop %rbx
ret
Lcor0:mov (%r8), %r11
imul (%rsi), %r11
add %rax, %r11
mov %r11, (%rdi)
pop %rax
pop %r13
pop %r12
pop %rbp
pop %rbx
ret
.align 4, 0x90
Lsmall:
cmp $2, %rcx
jae Lgt1
Ln1: imul (%r8), %rdx
mov %rdx, (%rdi)
ret
Lgt1: ja Lgt2
Ln2: mov (%r8), %r9
.byte 0xc4,194,251,0xf6,209
mov %rax, (%rdi)
mov 8(%rsi), %rax
imul %r9, %rax
add %rax, %rdx
mov 8(%r8), %r9
mov (%rsi), %rcx
imul %r9, %rcx
add %rcx, %rdx
mov %rdx, 8(%rdi)
ret
Lgt2:
Ln3: mov (%r8), %r9
.byte 0xc4,66,251,0xf6,209
mov %rax, (%rdi)
mov 8(%rsi), %rdx
.byte 0xc4,194,251,0xf6,209
imul 16(%rsi), %r9
add %rax, %r10
adc %rdx, %r9
mov 8(%r8), %r11
mov (%rsi), %rdx
.byte 0xc4,194,251,0xf6,211
add %rax, %r10
adc %rdx, %r9
imul 8(%rsi), %r11
add %r11, %r9
mov %r10, 8(%rdi)
mov 16(%r8), %r10
mov (%rsi), %rax
imul %rax, %r10
add %r10, %r9
mov %r9, 16(%rdi)
ret
|
