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
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
|
;******************************************************************************
;* VP9 Intra prediction SIMD optimizations
;*
;* Copyright (c) 2015 Ronald S. Bultje <rsbultje gmail com>
;* Copyright (c) 2015 Henrik Gramner <henrik gramner com>
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg is free software; you can redistribute it and/or
;* modify it under the terms of the GNU Lesser General Public
;* License as published by the Free Software Foundation; either
;* version 2.1 of the License, or (at your option) any later version.
;*
;* FFmpeg is distributed in the hope that it will be useful,
;* but WITHOUT ANY WARRANTY; without even the implied warranty of
;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
;* Lesser General Public License for more details.
;*
;* You should have received a copy of the GNU Lesser General Public
;* License along with FFmpeg; if not, write to the Free Software
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
;******************************************************************************
%include "libavutil/x86/x86util.asm"
SECTION_RODATA 32
pd_2: times 8 dd 2
pd_4: times 8 dd 4
pd_8: times 8 dd 8
cextern pw_1
cextern pw_1023
cextern pw_4095
cextern pd_16
cextern pd_32
SECTION .text
INIT_MMX mmx
cglobal vp9_ipred_v_4x4_16, 2, 4, 1, dst, stride, l, a
movifnidn aq, amp
mova m0, [aq]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
RET
INIT_XMM sse
cglobal vp9_ipred_v_8x8_16, 2, 4, 1, dst, stride, l, a
movifnidn aq, amp
mova m0, [aq]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
lea dstq, [dstq+strideq*4]
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
RET
INIT_XMM sse
cglobal vp9_ipred_v_16x16_16, 2, 4, 2, dst, stride, l, a
movifnidn aq, amp
mova m0, [aq]
mova m1, [aq+mmsize]
DEFINE_ARGS dst, stride, stride3, cnt
lea stride3q, [strideq*3]
mov cntd, 4
.loop:
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m1
mova [dstq+strideq*1+ 0], m0
mova [dstq+strideq*1+16], m1
mova [dstq+strideq*2+ 0], m0
mova [dstq+strideq*2+16], m1
mova [dstq+stride3q + 0], m0
mova [dstq+stride3q +16], m1
lea dstq, [dstq+strideq*4]
dec cntd
jg .loop
RET
INIT_XMM sse
cglobal vp9_ipred_v_32x32_16, 2, 4, 4, dst, stride, l, a
movifnidn aq, amp
mova m0, [aq+mmsize*0]
mova m1, [aq+mmsize*1]
mova m2, [aq+mmsize*2]
mova m3, [aq+mmsize*3]
DEFINE_ARGS dst, stride, cnt
mov cntd, 16
.loop:
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m1
mova [dstq+strideq*0+32], m2
mova [dstq+strideq*0+48], m3
mova [dstq+strideq*1+ 0], m0
mova [dstq+strideq*1+16], m1
mova [dstq+strideq*1+32], m2
mova [dstq+strideq*1+48], m3
lea dstq, [dstq+strideq*2]
dec cntd
jg .loop
RET
INIT_MMX mmxext
cglobal vp9_ipred_h_4x4_16, 3, 3, 4, dst, stride, l, a
mova m3, [lq]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
pshufw m0, m3, q3333
pshufw m1, m3, q2222
pshufw m2, m3, q1111
pshufw m3, m3, q0000
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m1
mova [dstq+strideq*2], m2
mova [dstq+stride3q ], m3
RET
INIT_XMM sse2
cglobal vp9_ipred_h_8x8_16, 3, 3, 4, dst, stride, l, a
mova m2, [lq]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
punpckhwd m3, m2, m2
pshufd m0, m3, q3333
pshufd m1, m3, q2222
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m1
pshufd m0, m3, q1111
pshufd m1, m3, q0000
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m1
lea dstq, [dstq+strideq*4]
punpcklwd m2, m2
pshufd m0, m2, q3333
pshufd m1, m2, q2222
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m1
pshufd m0, m2, q1111
pshufd m1, m2, q0000
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m1
RET
INIT_XMM sse2
cglobal vp9_ipred_h_16x16_16, 3, 5, 4, dst, stride, l, stride3, cnt
mov cntd, 3
lea stride3q, [strideq*3]
.loop:
movh m3, [lq+cntq*8]
punpcklwd m3, m3
pshufd m0, m3, q3333
pshufd m1, m3, q2222
pshufd m2, m3, q1111
pshufd m3, m3, q0000
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m0
mova [dstq+strideq*1+ 0], m1
mova [dstq+strideq*1+16], m1
mova [dstq+strideq*2+ 0], m2
mova [dstq+strideq*2+16], m2
mova [dstq+stride3q + 0], m3
mova [dstq+stride3q +16], m3
lea dstq, [dstq+strideq*4]
dec cntd
jge .loop
RET
INIT_XMM sse2
cglobal vp9_ipred_h_32x32_16, 3, 5, 4, dst, stride, l, stride3, cnt
mov cntd, 7
lea stride3q, [strideq*3]
.loop:
movh m3, [lq+cntq*8]
punpcklwd m3, m3
pshufd m0, m3, q3333
pshufd m1, m3, q2222
pshufd m2, m3, q1111
pshufd m3, m3, q0000
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m0
mova [dstq+strideq*0+32], m0
mova [dstq+strideq*0+48], m0
mova [dstq+strideq*1+ 0], m1
mova [dstq+strideq*1+16], m1
mova [dstq+strideq*1+32], m1
mova [dstq+strideq*1+48], m1
mova [dstq+strideq*2+ 0], m2
mova [dstq+strideq*2+16], m2
mova [dstq+strideq*2+32], m2
mova [dstq+strideq*2+48], m2
mova [dstq+stride3q + 0], m3
mova [dstq+stride3q +16], m3
mova [dstq+stride3q +32], m3
mova [dstq+stride3q +48], m3
lea dstq, [dstq+strideq*4]
dec cntd
jge .loop
RET
INIT_MMX mmxext
cglobal vp9_ipred_dc_4x4_16, 4, 4, 2, dst, stride, l, a
mova m0, [lq]
paddw m0, [aq]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
pmaddwd m0, [pw_1]
pshufw m1, m0, q3232
paddd m0, [pd_4]
paddd m0, m1
psrad m0, 3
pshufw m0, m0, q0000
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
RET
INIT_XMM sse2
cglobal vp9_ipred_dc_8x8_16, 4, 4, 2, dst, stride, l, a
mova m0, [lq]
paddw m0, [aq]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
pmaddwd m0, [pw_1]
pshufd m1, m0, q3232
paddd m0, m1
pshufd m1, m0, q1111
paddd m0, [pd_8]
paddd m0, m1
psrad m0, 4
pshuflw m0, m0, q0000
punpcklqdq m0, m0
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
lea dstq, [dstq+strideq*4]
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
RET
INIT_XMM sse2
cglobal vp9_ipred_dc_16x16_16, 4, 4, 2, dst, stride, l, a
mova m0, [lq]
paddw m0, [lq+mmsize]
paddw m0, [aq]
paddw m0, [aq+mmsize]
DEFINE_ARGS dst, stride, stride3, cnt
lea stride3q, [strideq*3]
mov cntd, 4
pmaddwd m0, [pw_1]
pshufd m1, m0, q3232
paddd m0, m1
pshufd m1, m0, q1111
paddd m0, [pd_16]
paddd m0, m1
psrad m0, 5
pshuflw m0, m0, q0000
punpcklqdq m0, m0
.loop:
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m0
mova [dstq+strideq*1+ 0], m0
mova [dstq+strideq*1+16], m0
mova [dstq+strideq*2+ 0], m0
mova [dstq+strideq*2+16], m0
mova [dstq+stride3q + 0], m0
mova [dstq+stride3q +16], m0
lea dstq, [dstq+strideq*4]
dec cntd
jg .loop
RET
INIT_XMM sse2
cglobal vp9_ipred_dc_32x32_16, 4, 4, 2, dst, stride, l, a
mova m0, [lq+mmsize*0]
paddw m0, [lq+mmsize*1]
paddw m0, [lq+mmsize*2]
paddw m0, [lq+mmsize*3]
paddw m0, [aq+mmsize*0]
paddw m0, [aq+mmsize*1]
paddw m0, [aq+mmsize*2]
paddw m0, [aq+mmsize*3]
DEFINE_ARGS dst, stride, stride3, cnt
lea stride3q, [strideq*3]
mov cntd, 16
pmaddwd m0, [pw_1]
pshufd m1, m0, q3232
paddd m0, m1
pshufd m1, m0, q1111
paddd m0, [pd_32]
paddd m0, m1
psrad m0, 6
pshuflw m0, m0, q0000
punpcklqdq m0, m0
.loop:
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m0
mova [dstq+strideq*0+32], m0
mova [dstq+strideq*0+48], m0
mova [dstq+strideq*1+ 0], m0
mova [dstq+strideq*1+16], m0
mova [dstq+strideq*1+32], m0
mova [dstq+strideq*1+48], m0
lea dstq, [dstq+strideq*2]
dec cntd
jg .loop
RET
%macro DC_1D_FNS 2
INIT_MMX mmxext
cglobal vp9_ipred_dc_%1_4x4_16, 4, 4, 2, dst, stride, l, a
mova m0, [%2]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
pmaddwd m0, [pw_1]
pshufw m1, m0, q3232
paddd m0, [pd_2]
paddd m0, m1
psrad m0, 2
pshufw m0, m0, q0000
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
RET
INIT_XMM sse2
cglobal vp9_ipred_dc_%1_8x8_16, 4, 4, 2, dst, stride, l, a
mova m0, [%2]
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
pmaddwd m0, [pw_1]
pshufd m1, m0, q3232
paddd m0, m1
pshufd m1, m0, q1111
paddd m0, [pd_4]
paddd m0, m1
psrad m0, 3
pshuflw m0, m0, q0000
punpcklqdq m0, m0
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
lea dstq, [dstq+strideq*4]
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m0
mova [dstq+strideq*2], m0
mova [dstq+stride3q ], m0
RET
INIT_XMM sse2
cglobal vp9_ipred_dc_%1_16x16_16, 4, 4, 2, dst, stride, l, a
mova m0, [%2]
paddw m0, [%2+mmsize]
DEFINE_ARGS dst, stride, stride3, cnt
lea stride3q, [strideq*3]
mov cntd, 4
pmaddwd m0, [pw_1]
pshufd m1, m0, q3232
paddd m0, m1
pshufd m1, m0, q1111
paddd m0, [pd_8]
paddd m0, m1
psrad m0, 4
pshuflw m0, m0, q0000
punpcklqdq m0, m0
.loop:
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m0
mova [dstq+strideq*1+ 0], m0
mova [dstq+strideq*1+16], m0
mova [dstq+strideq*2+ 0], m0
mova [dstq+strideq*2+16], m0
mova [dstq+stride3q + 0], m0
mova [dstq+stride3q +16], m0
lea dstq, [dstq+strideq*4]
dec cntd
jg .loop
RET
INIT_XMM sse2
cglobal vp9_ipred_dc_%1_32x32_16, 4, 4, 2, dst, stride, l, a
mova m0, [%2+mmsize*0]
paddw m0, [%2+mmsize*1]
paddw m0, [%2+mmsize*2]
paddw m0, [%2+mmsize*3]
DEFINE_ARGS dst, stride, cnt
mov cntd, 16
pmaddwd m0, [pw_1]
pshufd m1, m0, q3232
paddd m0, m1
pshufd m1, m0, q1111
paddd m0, [pd_16]
paddd m0, m1
psrad m0, 5
pshuflw m0, m0, q0000
punpcklqdq m0, m0
.loop:
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m0
mova [dstq+strideq*0+32], m0
mova [dstq+strideq*0+48], m0
mova [dstq+strideq*1+ 0], m0
mova [dstq+strideq*1+16], m0
mova [dstq+strideq*1+32], m0
mova [dstq+strideq*1+48], m0
lea dstq, [dstq+strideq*2]
dec cntd
jg .loop
RET
%endmacro
DC_1D_FNS top, aq
DC_1D_FNS left, lq
INIT_MMX mmxext
cglobal vp9_ipred_tm_4x4_10, 4, 4, 6, dst, stride, l, a
mova m5, [pw_1023]
.body:
mova m4, [aq]
mova m3, [lq]
movd m0, [aq-4]
pshufw m0, m0, q1111
psubw m4, m0
DEFINE_ARGS dst, stride, stride3
lea stride3q, [strideq*3]
pshufw m0, m3, q3333
pshufw m1, m3, q2222
pshufw m2, m3, q1111
pshufw m3, m3, q0000
paddw m0, m4
paddw m1, m4
paddw m2, m4
paddw m3, m4
pxor m4, m4
pmaxsw m0, m4
pmaxsw m1, m4
pmaxsw m2, m4
pmaxsw m3, m4
pminsw m0, m5
pminsw m1, m5
pminsw m2, m5
pminsw m3, m5
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m1
mova [dstq+strideq*2], m2
mova [dstq+stride3q ], m3
RET
cglobal vp9_ipred_tm_4x4_12, 4, 4, 6, dst, stride, l, a
mova m5, [pw_4095]
jmp mangle(private_prefix %+ _ %+ vp9_ipred_tm_4x4_10 %+ SUFFIX).body
INIT_XMM sse2
cglobal vp9_ipred_tm_8x8_10, 4, 5, 7, dst, stride, l, a
mova m4, [pw_1023]
.body:
pxor m6, m6
mova m5, [aq]
movd m0, [aq-4]
pshuflw m0, m0, q1111
punpcklqdq m0, m0
psubw m5, m0
DEFINE_ARGS dst, stride, l, stride3, cnt
lea stride3q, [strideq*3]
mov cntd, 1
.loop:
movh m3, [lq+cntq*8]
punpcklwd m3, m3
pshufd m0, m3, q3333
pshufd m1, m3, q2222
pshufd m2, m3, q1111
pshufd m3, m3, q0000
paddw m0, m5
paddw m1, m5
paddw m2, m5
paddw m3, m5
pmaxsw m0, m6
pmaxsw m1, m6
pmaxsw m2, m6
pmaxsw m3, m6
pminsw m0, m4
pminsw m1, m4
pminsw m2, m4
pminsw m3, m4
mova [dstq+strideq*0], m0
mova [dstq+strideq*1], m1
mova [dstq+strideq*2], m2
mova [dstq+stride3q ], m3
lea dstq, [dstq+strideq*4]
dec cntd
jge .loop
RET
cglobal vp9_ipred_tm_8x8_12, 4, 5, 7, dst, stride, l, a
mova m4, [pw_4095]
jmp mangle(private_prefix %+ _ %+ vp9_ipred_tm_8x8_10 %+ SUFFIX).body
INIT_XMM sse2
cglobal vp9_ipred_tm_16x16_10, 4, 4, 8, dst, stride, l, a
mova m7, [pw_1023]
.body:
pxor m6, m6
mova m4, [aq]
mova m5, [aq+mmsize]
movd m0, [aq-4]
pshuflw m0, m0, q1111
punpcklqdq m0, m0
psubw m4, m0
psubw m5, m0
DEFINE_ARGS dst, stride, l, cnt
mov cntd, 7
.loop:
movd m3, [lq+cntq*4]
punpcklwd m3, m3
pshufd m2, m3, q1111
pshufd m3, m3, q0000
paddw m0, m2, m4
paddw m2, m5
paddw m1, m3, m4
paddw m3, m5
pmaxsw m0, m6
pmaxsw m2, m6
pmaxsw m1, m6
pmaxsw m3, m6
pminsw m0, m7
pminsw m2, m7
pminsw m1, m7
pminsw m3, m7
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m2
mova [dstq+strideq*1+ 0], m1
mova [dstq+strideq*1+16], m3
lea dstq, [dstq+strideq*2]
dec cntd
jge .loop
RET
cglobal vp9_ipred_tm_16x16_12, 4, 4, 8, dst, stride, l, a
mova m7, [pw_4095]
jmp mangle(private_prefix %+ _ %+ vp9_ipred_tm_16x16_10 %+ SUFFIX).body
INIT_XMM sse2
cglobal vp9_ipred_tm_32x32_10, 4, 4, 10, 32 * ARCH_X86_32, dst, stride, l, a
mova m0, [pw_1023]
.body:
pxor m1, m1
%if ARCH_X86_64
SWAP 0, 8
SWAP 1, 9
%define reg_min m9
%define reg_max m8
%else
mova [rsp+ 0], m0
mova [rsp+16], m1
%define reg_min [rsp+16]
%define reg_max [rsp+ 0]
%endif
mova m4, [aq+mmsize*0]
mova m5, [aq+mmsize*1]
mova m6, [aq+mmsize*2]
mova m7, [aq+mmsize*3]
movd m0, [aq-4]
pshuflw m0, m0, q1111
punpcklqdq m0, m0
psubw m4, m0
psubw m5, m0
psubw m6, m0
psubw m7, m0
DEFINE_ARGS dst, stride, l, cnt
mov cntd, 31
.loop:
pinsrw m3, [lq+cntq*2], 0
punpcklwd m3, m3
pshufd m3, m3, q0000
paddw m0, m3, m4
paddw m1, m3, m5
paddw m2, m3, m6
paddw m3, m7
pmaxsw m0, reg_min
pmaxsw m1, reg_min
pmaxsw m2, reg_min
pmaxsw m3, reg_min
pminsw m0, reg_max
pminsw m1, reg_max
pminsw m2, reg_max
pminsw m3, reg_max
mova [dstq+strideq*0+ 0], m0
mova [dstq+strideq*0+16], m1
mova [dstq+strideq*0+32], m2
mova [dstq+strideq*0+48], m3
add dstq, strideq
dec cntd
jge .loop
RET
cglobal vp9_ipred_tm_32x32_12, 4, 4, 10, 32 * ARCH_X86_32, dst, stride, l, a
mova m0, [pw_4095]
jmp mangle(private_prefix %+ _ %+ vp9_ipred_tm_32x32_10 %+ SUFFIX).body
|
