File: sse2_amd64.s

package info (click to toggle)
golang-github-templexxx-xor 0.1.2-5~bpo9+1
  • links: PTS, VCS
  • area: main
  • in suites: stretch-backports
  • size: 108 kB
  • sloc: asm: 834; makefile: 2
file content (574 lines) | stat: -rw-r--r-- 9,152 bytes parent folder | download | duplicates (4)
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
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
#include "textflag.h"

// addr of mem
#define DST BX
#define SRC SI
#define SRC0 TMP4
#define SRC1 TMP5

// loop args
// num of vect
#define VECT CX
#define LEN DX
// pos of matrix
#define POS R8

// tmp store
// num of vect or ...
#define TMP1 R9
// pos of matrix or ...
#define TMP2 R10
// store addr of data/parity or ...
#define TMP3 R11
#define TMP4 R12
#define TMP5 R13
#define TMP6 R14

// func bytesSrc0(dst, src0, src1 []byte)
TEXT ·xorSrc0(SB), NOSPLIT, $0
	MOVQ  len+32(FP), LEN
	CMPQ  LEN, $0
	JE    ret
	MOVQ  dst+0(FP), DST
	MOVQ  src0+24(FP), SRC0
	MOVQ  src1+48(FP), SRC1
	TESTQ $15, LEN
	JNZ   not_aligned

aligned:
	MOVQ $0, POS

loop16b:
	MOVOU (SRC0)(POS*1), X0
	XORPD (SRC1)(POS*1), X0
	MOVOU X0, (DST)(POS*1)
	ADDQ  $16, POS
	CMPQ  LEN, POS
	JNE   loop16b
	RET

loop_1b:
	MOVB  -1(SRC0)(LEN*1), TMP1
	MOVB  -1(SRC1)(LEN*1), TMP2
	XORB  TMP1, TMP2
	MOVB  TMP2, -1(DST)(LEN*1)
	SUBQ  $1, LEN
	TESTQ $7, LEN
	JNZ   loop_1b
	CMPQ  LEN, $0
	JE    ret
	TESTQ $15, LEN
	JZ    aligned

not_aligned:
	TESTQ $7, LEN
	JNE   loop_1b
	MOVQ  LEN, TMP1
	ANDQ  $15, TMP1

loop_8b:
	MOVQ -8(SRC0)(LEN*1), TMP2
	MOVQ -8(SRC1)(LEN*1), TMP3
	XORQ TMP2, TMP3
	MOVQ TMP3, -8(DST)(LEN*1)
	SUBQ $8, LEN
	SUBQ $8, TMP1
	JG   loop_8b

	CMPQ LEN, $16
	JGE  aligned
	RET

ret:
	RET

// func bytesSrc1(dst, src0, src1 []byte)
TEXT ·xorSrc1(SB), NOSPLIT, $0
	MOVQ  len+56(FP), LEN
	CMPQ  LEN, $0
	JE    ret
	MOVQ  dst+0(FP), DST
	MOVQ  src0+24(FP), SRC0
	MOVQ  src1+48(FP), SRC1
	TESTQ $15, LEN
	JNZ   not_aligned

aligned:
	MOVQ $0, POS

loop16b:
	MOVOU (SRC0)(POS*1), X0
	XORPD (SRC1)(POS*1), X0
	MOVOU X0, (DST)(POS*1)
	ADDQ  $16, POS
	CMPQ  LEN, POS
	JNE   loop16b
	RET

loop_1b:
	MOVB  -1(SRC0)(LEN*1), TMP1
	MOVB  -1(SRC1)(LEN*1), TMP2
	XORB  TMP1, TMP2
	MOVB  TMP2, -1(DST)(LEN*1)
	SUBQ  $1, LEN
	TESTQ $7, LEN
	JNZ   loop_1b
	CMPQ  LEN, $0
	JE    ret
	TESTQ $15, LEN
	JZ    aligned

not_aligned:
	TESTQ $7, LEN
	JNE   loop_1b
	MOVQ  LEN, TMP1
	ANDQ  $15, TMP1

loop_8b:
	MOVQ -8(SRC0)(LEN*1), TMP2
	MOVQ -8(SRC1)(LEN*1), TMP3
	XORQ TMP2, TMP3
	MOVQ TMP3, -8(DST)(LEN*1)
	SUBQ $8, LEN
	SUBQ $8, TMP1
	JG   loop_8b

	CMPQ LEN, $16
	JGE  aligned
	RET

ret:
	RET

// func bytesSSE2mini(dst, src0, src1 []byte, size int)
TEXT ·bytesSSE2mini(SB), NOSPLIT, $0
	MOVQ  len+72(FP), LEN
	CMPQ  LEN, $0
	JE    ret
	MOVQ  dst+0(FP), DST
	MOVQ  src0+24(FP), SRC0
	MOVQ  src1+48(FP), SRC1
	TESTQ $15, LEN
	JNZ   not_aligned

aligned:
	MOVQ $0, POS

loop16b:
	MOVOU (SRC0)(POS*1), X0
	XORPD (SRC1)(POS*1), X0

	// MOVOU (SRC1)(POS*1), X4
	// PXOR X4, X0
	MOVOU X0, (DST)(POS*1)
	ADDQ  $16, POS
	CMPQ  LEN, POS
	JNE   loop16b
	RET

loop_1b:
	MOVB  -1(SRC0)(LEN*1), TMP1
	MOVB  -1(SRC1)(LEN*1), TMP2
	XORB  TMP1, TMP2
	MOVB  TMP2, -1(DST)(LEN*1)
	SUBQ  $1, LEN
	TESTQ $7, LEN
	JNZ   loop_1b
	CMPQ  LEN, $0
	JE    ret
	TESTQ $15, LEN
	JZ    aligned

not_aligned:
	TESTQ $7, LEN
	JNE   loop_1b
	MOVQ  LEN, TMP1
	ANDQ  $15, TMP1

loop_8b:
	MOVQ -8(SRC0)(LEN*1), TMP2
	MOVQ -8(SRC1)(LEN*1), TMP3
	XORQ TMP2, TMP3
	MOVQ TMP3, -8(DST)(LEN*1)
	SUBQ $8, LEN
	SUBQ $8, TMP1
	JG   loop_8b

	CMPQ LEN, $16
	JGE  aligned
	RET

ret:
	RET

// func bytesSSE2small(dst, src0, src1 []byte, size int)
TEXT ·bytesSSE2small(SB), NOSPLIT, $0
	MOVQ  len+72(FP), LEN
	CMPQ  LEN, $0
	JE    ret
	MOVQ  dst+0(FP), DST
	MOVQ  src0+24(FP), SRC0
	MOVQ  src1+48(FP), SRC1
	TESTQ $63, LEN
	JNZ   not_aligned

aligned:
	MOVQ $0, POS

loop64b:
	MOVOU (SRC0)(POS*1), X0
	MOVOU 16(SRC0)(POS*1), X1
	MOVOU 32(SRC0)(POS*1), X2
	MOVOU 48(SRC0)(POS*1), X3

	MOVOU (SRC1)(POS*1), X4
	MOVOU 16(SRC1)(POS*1), X5
	MOVOU 32(SRC1)(POS*1), X6
	MOVOU 48(SRC1)(POS*1), X7

	PXOR X4, X0
	PXOR X5, X1
	PXOR X6, X2
	PXOR X7, X3

	MOVOU X0, (DST)(POS*1)
	MOVOU X1, 16(DST)(POS*1)
	MOVOU X2, 32(DST)(POS*1)
	MOVOU X3, 48(DST)(POS*1)

	ADDQ $64, POS
	CMPQ LEN, POS
	JNE  loop64b
	RET

loop_1b:
	MOVB  -1(SRC0)(LEN*1), TMP1
	MOVB  -1(SRC1)(LEN*1), TMP2
	XORB  TMP1, TMP2
	MOVB  TMP2, -1(DST)(LEN*1)
	SUBQ  $1, LEN
	TESTQ $7, LEN
	JNZ   loop_1b
	CMPQ  LEN, $0
	JE    ret
	TESTQ $63, LEN
	JZ    aligned

not_aligned:
	TESTQ $7, LEN
	JNE   loop_1b
	MOVQ  LEN, TMP1
	ANDQ  $63, TMP1

loop_8b:
	MOVQ -8(SRC0)(LEN*1), TMP2
	MOVQ -8(SRC1)(LEN*1), TMP3
	XORQ TMP2, TMP3
	MOVQ TMP3, -8(DST)(LEN*1)
	SUBQ $8, LEN
	SUBQ $8, TMP1
	JG   loop_8b

	CMPQ LEN, $64
	JGE  aligned
	RET

ret:
	RET

// func bytesSSE2big(dst, src0, src1 []byte, size int)
TEXT ·bytesSSE2big(SB), NOSPLIT, $0
	MOVQ  len+72(FP), LEN
	CMPQ  LEN, $0
	JE    ret
	MOVQ  dst+0(FP), DST
	MOVQ  src0+24(FP), SRC0
	MOVQ  src1+48(FP), SRC1
	TESTQ $63, LEN
	JNZ   not_aligned

aligned:
	MOVQ $0, POS

loop64b:
	MOVOU (SRC0)(POS*1), X0
	MOVOU 16(SRC0)(POS*1), X1
	MOVOU 32(SRC0)(POS*1), X2
	MOVOU 48(SRC0)(POS*1), X3

	MOVOU (SRC1)(POS*1), X4
	MOVOU 16(SRC1)(POS*1), X5
	MOVOU 32(SRC1)(POS*1), X6
	MOVOU 48(SRC1)(POS*1), X7

	PXOR X4, X0
	PXOR X5, X1
	PXOR X6, X2
	PXOR X7, X3

	LONG $0xe70f4266; WORD $0x0304             // MOVNTDQ
	LONG $0xe70f4266; WORD $0x034c; BYTE $0x10
	LONG $0xe70f4266; WORD $0x0354; BYTE $0x20
	LONG $0xe70f4266; WORD $0x035c; BYTE $0x30

	ADDQ $64, POS
	CMPQ LEN, POS
	JNE  loop64b
	RET

loop_1b:
	MOVB  -1(SRC0)(LEN*1), TMP1
	MOVB  -1(SRC1)(LEN*1), TMP2
	XORB  TMP1, TMP2
	MOVB  TMP2, -1(DST)(LEN*1)
	SUBQ  $1, LEN
	TESTQ $7, LEN
	JNZ   loop_1b
	CMPQ  LEN, $0
	JE    ret
	TESTQ $63, LEN
	JZ    aligned

not_aligned:
	TESTQ $7, LEN
	JNE   loop_1b
	MOVQ  LEN, TMP1
	ANDQ  $63, TMP1

loop_8b:
	MOVQ -8(SRC0)(LEN*1), TMP2
	MOVQ -8(SRC1)(LEN*1), TMP3
	XORQ TMP2, TMP3
	MOVQ TMP3, -8(DST)(LEN*1)
	SUBQ $8, LEN
	SUBQ $8, TMP1
	JG   loop_8b

	CMPQ LEN, $64
	JGE  aligned
	RET

ret:
	RET

// func matrixSSE2small(dst []byte, src [][]byte)
TEXT ·matrixSSE2small(SB), NOSPLIT, $0
	MOVQ  dst+0(FP), DST
	MOVQ  src+24(FP), SRC
	MOVQ  vec+32(FP), VECT
	MOVQ  len+8(FP), LEN
	TESTQ $63, LEN
	JNZ   not_aligned

aligned:
	MOVQ $0, POS

loop64b:
	MOVQ  VECT, TMP1
	SUBQ  $2, TMP1
	MOVQ  $0, TMP2
	MOVQ  (SRC)(TMP2*1), TMP3
	MOVQ  TMP3, TMP4
	MOVOU (TMP3)(POS*1), X0
	MOVOU 16(TMP4)(POS*1), X1
	MOVOU 32(TMP3)(POS*1), X2
	MOVOU 48(TMP4)(POS*1), X3

next_vect:
	ADDQ  $24, TMP2
	MOVQ  (SRC)(TMP2*1), TMP3
	MOVQ  TMP3, TMP4
	MOVOU (TMP3)(POS*1), X4
	MOVOU 16(TMP4)(POS*1), X5
	MOVOU 32(TMP3)(POS*1), X6
	MOVOU 48(TMP4)(POS*1), X7
	PXOR  X4, X0
	PXOR  X5, X1
	PXOR  X6, X2
	PXOR  X7, X3
	SUBQ  $1, TMP1
	JGE   next_vect

	MOVOU X0, (DST)(POS*1)
	MOVOU X1, 16(DST)(POS*1)
	MOVOU X2, 32(DST)(POS*1)
	MOVOU X3, 48(DST)(POS*1)

	ADDQ $64, POS
	CMPQ LEN, POS
	JNE  loop64b
	RET

loop_1b:
	MOVQ VECT, TMP1
	MOVQ $0, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	SUBQ $2, TMP1
	MOVB -1(TMP3)(LEN*1), TMP5

next_vect_1b:
	ADDQ $24, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	MOVB -1(TMP3)(LEN*1), TMP6
	XORB TMP6, TMP5
	SUBQ $1, TMP1
	JGE  next_vect_1b

	MOVB  TMP5, -1(DST)(LEN*1)
	SUBQ  $1, LEN
	TESTQ $7, LEN
	JNZ   loop_1b

	CMPQ  LEN, $0
	JE    ret
	TESTQ $63, LEN
	JZ    aligned

not_aligned:
	TESTQ $7, LEN
	JNE   loop_1b
	MOVQ  LEN, TMP4
	ANDQ  $63, TMP4

loop_8b:
	MOVQ VECT, TMP1
	MOVQ $0, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	SUBQ $2, TMP1
	MOVQ -8(TMP3)(LEN*1), TMP5

next_vect_8b:
	ADDQ $24, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	MOVQ -8(TMP3)(LEN*1), TMP6
	XORQ TMP6, TMP5
	SUBQ $1, TMP1
	JGE  next_vect_8b

	MOVQ TMP5, -8(DST)(LEN*1)
	SUBQ $8, LEN
	SUBQ $8, TMP4
	JG   loop_8b

	CMPQ LEN, $64
	JGE  aligned
	RET

ret:
	RET

// func matrixSSE2big(dst []byte, src [][]byte)
TEXT ·matrixSSE2big(SB), NOSPLIT, $0
	MOVQ  dst+0(FP), DST
	MOVQ  src+24(FP), SRC
	MOVQ  vec+32(FP), VECT
	MOVQ  len+8(FP), LEN
	TESTQ $63, LEN
	JNZ   not_aligned

aligned:
	MOVQ $0, POS

loop64b:
	MOVQ  VECT, TMP1
	SUBQ  $2, TMP1
	MOVQ  $0, TMP2
	MOVQ  (SRC)(TMP2*1), TMP3
	MOVQ  TMP3, TMP4
	MOVOU (TMP3)(POS*1), X0
	MOVOU 16(TMP4)(POS*1), X1
	MOVOU 32(TMP3)(POS*1), X2
	MOVOU 48(TMP4)(POS*1), X3

next_vect:
	ADDQ  $24, TMP2
	MOVQ  (SRC)(TMP2*1), TMP3
	MOVQ  TMP3, TMP4
	MOVOU (TMP3)(POS*1), X4
	MOVOU 16(TMP4)(POS*1), X5
	MOVOU 32(TMP3)(POS*1), X6
	MOVOU 48(TMP4)(POS*1), X7
	PXOR  X4, X0
	PXOR  X5, X1
	PXOR  X6, X2
	PXOR  X7, X3
	SUBQ  $1, TMP1
	JGE   next_vect

	LONG $0xe70f4266; WORD $0x0304
	LONG $0xe70f4266; WORD $0x034c; BYTE $0x10
	LONG $0xe70f4266; WORD $0x0354; BYTE $0x20
	LONG $0xe70f4266; WORD $0x035c; BYTE $0x30

	ADDQ $64, POS
	CMPQ LEN, POS
	JNE  loop64b
	RET

loop_1b:
	MOVQ VECT, TMP1
	MOVQ $0, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	SUBQ $2, TMP1
	MOVB -1(TMP3)(LEN*1), TMP5

next_vect_1b:
	ADDQ $24, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	MOVB -1(TMP3)(LEN*1), TMP6
	XORB TMP6, TMP5
	SUBQ $1, TMP1
	JGE  next_vect_1b

	MOVB  TMP5, -1(DST)(LEN*1)
	SUBQ  $1, LEN
	TESTQ $7, LEN
	JNZ   loop_1b

	CMPQ  LEN, $0
	JE    ret
	TESTQ $63, LEN
	JZ    aligned

not_aligned:
	TESTQ $7, LEN
	JNE   loop_1b
	MOVQ  LEN, TMP4
	ANDQ  $63, TMP4

loop_8b:
	MOVQ VECT, TMP1
	MOVQ $0, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	SUBQ $2, TMP1
	MOVQ -8(TMP3)(LEN*1), TMP5

next_vect_8b:
	ADDQ $24, TMP2
	MOVQ (SRC)(TMP2*1), TMP3
	MOVQ -8(TMP3)(LEN*1), TMP6
	XORQ TMP6, TMP5
	SUBQ $1, TMP1
	JGE  next_vect_8b

	MOVQ TMP5, -8(DST)(LEN*1)
	SUBQ $8, LEN
	SUBQ $8, TMP4
	JG   loop_8b

	CMPQ LEN, $64
	JGE  aligned
	RET

ret:
	RET

TEXT ·hasSSE2(SB), NOSPLIT, $0
	XORQ AX, AX
	INCL AX
	CPUID
	SHRQ $26, DX
	ANDQ $1, DX
	MOVB DX, ret+0(FP)
	RET