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
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
|
.text
.align 5, 0x90
.globl ___gmpn_sqr_basecase
___gmpn_sqr_basecase:
cmp $2, %rdx
jae Lgt1
mov (%rsi), %rdx
.byte 0xc4,226,251,0xf6,210
mov %rax, (%rdi)
mov %rdx, 8(%rdi)
ret
Lgt1: jne Lgt2
mov (%rsi), %rdx
mov 8(%rsi), %rcx
.byte 0xc4,98,179,0xf6,209
.byte 0xc4,98,251,0xf6,194
mov %rcx, %rdx
.byte 0xc4,226,163,0xf6,210
add %r9, %r9
adc %r10, %r10
adc $0, %rdx
add %r9, %r8
adc %r11, %r10
adc $0, %rdx
mov %rax, (%rdi)
mov %r8, 8(%rdi)
mov %r10, 16(%rdi)
mov %rdx, 24(%rdi)
ret
Lgt2: cmp $4, %rdx
jae Lgt3
mov (%rsi), %r8
mov 8(%rsi), %rdx
mov %rdx, %r9
.byte 0xc4,194,163,0xf6,192
mov 16(%rsi), %rdx
.byte 0xc4,194,171,0xf6,200
mov %r11, %r8
add %rax, %r10
adc $0, %rcx
.byte 0xc4,194,235,0xf6,193
add %rcx, %rdx
mov %rdx, 24(%rdi)
adc $0, %rax
mov %rax, 32(%rdi)
xor %ecx, %ecx
mov (%rsi), %rdx
.byte 0xc4,98,251,0xf6,218
mov %rax, (%rdi)
add %r8, %r8
adc %r10, %r10
setc %cl
mov 8(%rsi), %rdx
.byte 0xc4,226,251,0xf6,210
add %r11, %r8
adc %rax, %r10
mov %r8, 8(%rdi)
mov %r10, 16(%rdi)
mov 24(%rdi), %r8
mov 32(%rdi), %r10
lea (%rdx,%rcx), %r11
adc %r8, %r8
adc %r10, %r10
setc %cl
mov 16(%rsi), %rdx
.byte 0xc4,226,251,0xf6,210
add %r11, %r8
adc %rax, %r10
mov %r8, 24(%rdi)
mov %r10, 32(%rdi)
adc %rcx, %rdx
mov %rdx, 40(%rdi)
ret
Lgt3:
Ldo_mul_2:
push %rbx
push %rbp
push %r12
push %r13
push %r14
mov $0, %r12d
sub %rdx, %r12
push %r12
mov (%rsi), %r8
mov 8(%rsi), %rdx
lea 2(%r12), %rcx
sar $2, %rcx
inc %r12
mov %rdx, %r9
test $1, %r12b
jnz Lmx1
Lmx0: .byte 0xc4,66,227,0xf6,216
mov 16(%rsi), %rdx
mov %rbx, 8(%rdi)
xor %rbx, %rbx
.byte 0xc4,194,171,0xf6,232
test $2, %r12b
jz Lm00
Lm10: lea -8(%rdi), %rdi
lea -8(%rsi), %rsi
jmp Lmlo2
Lm00: lea 8(%rsi), %rsi
lea 8(%rdi), %rdi
jmp Lmlo0
Lmx1: .byte 0xc4,194,171,0xf6,232
mov 16(%rsi), %rdx
mov %r10, 8(%rdi)
xor %r10, %r10
.byte 0xc4,66,227,0xf6,216
test $2, %r12b
jz Lmlo3
Lm01: lea 16(%rdi), %rdi
lea 16(%rsi), %rsi
jmp Lmlo1
.align 5, 0x90
Lmtop:.byte 0xc4,66,251,0xf6,209
add %rax, %rbx
mov (%rsi), %rdx
.byte 0xc4,66,251,0xf6,216
adc $0, %r10
add %rax, %rbx
Lmlo1:adc $0, %r11
add %rbp, %rbx
mov %rbx, (%rdi)
adc $0, %r11
.byte 0xc4,194,251,0xf6,217
add %rax, %r10
mov 8(%rsi), %rdx
adc $0, %rbx
.byte 0xc4,194,251,0xf6,232
add %rax, %r10
adc $0, %rbp
Lmlo0:add %r11, %r10
mov %r10, 8(%rdi)
adc $0, %rbp
.byte 0xc4,66,251,0xf6,209
add %rax, %rbx
mov 16(%rsi), %rdx
.byte 0xc4,66,251,0xf6,216
adc $0, %r10
add %rax, %rbx
adc $0, %r11
Lmlo3:add %rbp, %rbx
mov %rbx, 16(%rdi)
adc $0, %r11
.byte 0xc4,194,251,0xf6,217
add %rax, %r10
mov 24(%rsi), %rdx
adc $0, %rbx
.byte 0xc4,194,251,0xf6,232
add %rax, %r10
adc $0, %rbp
Lmlo2:add %r11, %r10
lea 32(%rsi), %rsi
mov %r10, 24(%rdi)
adc $0, %rbp
inc %rcx
lea 32(%rdi), %rdi
jnz Lmtop
Lmend:.byte 0xc4,194,235,0xf6,193
add %rdx, %rbx
adc $0, %rax
add %rbp, %rbx
mov %rbx, (%rdi)
adc $0, %rax
mov %rax, 8(%rdi)
lea 16(%rsi), %rsi
lea -16(%rdi), %rdi
Ldo_addmul_2:
Louter:
lea (%rsi,%r12,8), %rsi
lea 48(%rdi,%r12,8), %rdi
mov -8(%rsi), %r8
add $2, %r12
cmp $-2, %r12
jge Lcorner
mov (%rsi), %r9
lea 1(%r12), %rcx
sar $2, %rcx
mov %r9, %rdx
test $1, %r12b
jnz Lbx1
Lbx0: mov (%rdi), %r13
mov 8(%rdi), %r14
.byte 0xc4,66,251,0xf6,216
add %rax, %r13
adc $0, %r11
mov %r13, (%rdi)
xor %rbx, %rbx
test $2, %r12b
jnz Lb10
Lb00: mov 8(%rsi), %rdx
lea 16(%rdi), %rdi
lea 16(%rsi), %rsi
jmp Llo0
Lb10: mov 8(%rsi), %rdx
mov 16(%rdi), %r13
lea 32(%rsi), %rsi
inc %rcx
.byte 0xc4,194,251,0xf6,232
jz Lex
jmp Llo2
Lbx1: mov (%rdi), %r14
mov 8(%rdi), %r13
.byte 0xc4,194,251,0xf6,232
mov 8(%rsi), %rdx
add %rax, %r14
adc $0, %rbp
xor %r10, %r10
mov %r14, (%rdi)
.byte 0xc4,66,251,0xf6,216
test $2, %r12b
jz Lb11
Lb01: mov 16(%rdi), %r14
lea 24(%rdi), %rdi
lea 24(%rsi), %rsi
jmp Llo1
Lb11: lea 8(%rdi), %rdi
lea 8(%rsi), %rsi
jmp Llo3
.align 5, 0x90
Ltop: .byte 0xc4,194,251,0xf6,232
add %r10, %r14
adc $0, %rbx
Llo2: add %rax, %r14
adc $0, %rbp
.byte 0xc4,66,251,0xf6,209
add %rax, %r13
adc $0, %r10
lea 32(%rdi), %rdi
add %r11, %r14
mov -16(%rsi), %rdx
mov %r14, -24(%rdi)
adc $0, %rbp
add %rbx, %r13
mov -8(%rdi), %r14
.byte 0xc4,66,251,0xf6,216
adc $0, %r10
Llo1: add %rax, %r13
.byte 0xc4,194,251,0xf6,217
adc $0, %r11
add %rbp, %r13
mov %r13, -16(%rdi)
adc $0, %r11
add %rax, %r14
adc $0, %rbx
add %r10, %r14
mov -8(%rsi), %rdx
adc $0, %rbx
Llo0: .byte 0xc4,194,251,0xf6,232
add %rax, %r14
adc $0, %rbp
mov (%rdi), %r13
.byte 0xc4,66,251,0xf6,209
add %rax, %r13
adc $0, %r10
add %r11, %r14
mov %r14, -8(%rdi)
adc $0, %rbp
mov (%rsi), %rdx
add %rbx, %r13
.byte 0xc4,66,251,0xf6,216
adc $0, %r10
Llo3: add %rax, %r13
adc $0, %r11
.byte 0xc4,194,251,0xf6,217
add %rbp, %r13
mov 8(%rdi), %r14
mov %r13, (%rdi)
mov 16(%rdi), %r13
adc $0, %r11
add %rax, %r14
adc $0, %rbx
mov 8(%rsi), %rdx
lea 32(%rsi), %rsi
inc %rcx
jnz Ltop
Lend: .byte 0xc4,194,251,0xf6,232
add %r10, %r14
adc $0, %rbx
Lex: add %rax, %r14
adc $0, %rbp
.byte 0xc4,194,235,0xf6,193
add %r11, %r14
mov %r14, 8(%rdi)
adc $0, %rbp
add %rbx, %rdx
adc $0, %rax
add %rdx, %rbp
mov %rbp, 16(%rdi)
adc $0, %rax
mov %rax, 24(%rdi)
jmp Louter
Lcorner:
pop %r12
mov (%rsi), %rdx
jg Lsmall_corner
mov %rdx, %r9
mov (%rdi), %r13
mov %rax, %r14
.byte 0xc4,66,251,0xf6,216
add %rax, %r13
adc $0, %r11
mov %r13, (%rdi)
mov 8(%rsi), %rdx
.byte 0xc4,194,251,0xf6,232
add %rax, %r14
adc $0, %rbp
.byte 0xc4,194,235,0xf6,193
add %r11, %r14
mov %r14, 8(%rdi)
adc $0, %rbp
add %rbp, %rdx
mov %rdx, 16(%rdi)
adc $0, %rax
mov %rax, 24(%rdi)
lea 32(%rdi), %rdi
lea 16(%rsi), %rsi
jmp Lcom
Lsmall_corner:
.byte 0xc4,194,139,0xf6,232
add %rax, %r14
adc $0, %rbp
mov %r14, (%rdi)
mov %rbp, 8(%rdi)
lea 16(%rdi), %rdi
lea 8(%rsi), %rsi
Lcom:
Lsqr_diag_addlsh1:
lea 8(%rsi,%r12,8), %rsi
lea (%rdi,%r12,8), %rdi
lea (%rdi,%r12,8), %rdi
inc %r12
mov -8(%rsi), %rdx
xor %ebx, %ebx
.byte 0xc4,98,251,0xf6,210
mov %rax, 8(%rdi)
mov 16(%rdi), %r8
mov 24(%rdi), %r9
jmp Ldm
.align 4, 0x90
Ldtop:mov 32(%rdi), %r8
mov 40(%rdi), %r9
lea 16(%rdi), %rdi
lea (%rdx,%rbx), %r10
Ldm: adc %r8, %r8
adc %r9, %r9
setc %bl
mov (%rsi), %rdx
lea 8(%rsi), %rsi
.byte 0xc4,226,251,0xf6,210
add %r10, %r8
adc %rax, %r9
mov %r8, 16(%rdi)
mov %r9, 24(%rdi)
inc %r12
jnz Ldtop
Ldend:adc %rbx, %rdx
mov %rdx, 32(%rdi)
pop %r14
pop %r13
pop %r12
pop %rbp
pop %rbx
ret
|
