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
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
|
/*
* Copyright 2000-2013 Intel Corporation All Rights Reserved
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
* Authors:
* Zhao Yakui <yakui.zhao@intel.com>
*/
// Module name: common.inc
//
// Common header file for all Video-Processing kernels
//
.default_execution_size (16)
.default_register_type :ub
.reg_count_total 128
.reg_count_payload 7
//========== Common constants ==========
//========== Macros ==========
//Fast Jump, For more details see "Set_Layer_N.asm"
//========== Defines ====================
//========== Static Parameters (Common To All) ==========
//r1
//r2
// e.g. byte0 byte1 byte2
// YUYV 0 1 3
// YVYU 0 3 1
//Color Pipe (IECP) parameters
//ByteCopy
//r4
// e.g. byte0 byte1 byte2
// YUYV 0 1 3
// YVYU 0 3 1
//========== Inline parameters (Common To All) ===========
//============== Binding Index Table===========
//Common between DNDI and DNUV
//================= Common Message Descriptor =====
// Message descriptor for thread spawning
// Message Descriptors
// = 000 0001 (min message len 1 ) 0,0000 (resp len 0 -add later)
// 0000,0000,0000
// 0001(Spawn a root thread),0001 (Root thread spawn thread)
// = 0x02000011
// Thread Spawner Message Descriptor
// Message descriptor for atomic operation add
// Message Descriptors
// = 000 0110 (min message len 6 ) 0,0000 (resp len 0 -add later)
// 1(header present)001,10(typed atomic operation)0(return enabled)0(slot group, low 8 bits),0111 (AOP_Add)
// 0000,0000 (Binding table index, added later)
// = 0x02000011
// Atomic Operation Add Message Descriptor
// Message descriptor for dataport media write
// Message Descriptors
// = 000 0001 (min message len 1 - add later) 00000 (resp len 0)
// 1 (header present 1) 0 1010 (media block write) 000000
// 00000000 (binding table index - set later)
// = 0x020A8000
// Message Length defines
// Response Length defines
// Block Width and Height Size defines
// Extended Message Descriptors
// Common message descriptors:
//===================== Math Function Control ===================================
//============ Message Registers ===============
// buf4 starts from r28
//#define mMSGHDR_EOT r43 // Dummy Message Register for EOT
.declare mubMSGPAYLOAD Base=r30 ElementSize=1 SrcRegion=<16;16,1> Type=ub
.declare muwMSGPAYLOAD Base=r30 ElementSize=2 SrcRegion=<16;16,1> Type=uw
.declare mudMSGPAYLOAD Base=r30 ElementSize=4 SrcRegion=<8;8,1> Type=ud
.declare mfMSGPAYLOAD Base=r30 ElementSize=4 SrcRegion=<8;8,1> Type=f
//=================== End of thread instruction ===========================
//=====================Pointers Used=====================================
//=======================================================================
//r11-r17
// Define temp space for any usages
// Common Buffers
// temp space for rotation
.declare fROBUF Base=r11.0 ElementSize=4 SrcRegion=<8;8,1> DstRegion=<1> Type=f
.declare udROBUF Base=r11.0 ElementSize=4 SrcRegion=<8;8,1> DstRegion=<1> Type=ud
.declare uwROBUF Base=r11.0 ElementSize=2 SrcRegion=<16;16,1> DstRegion=<1> Type=uw
.declare ubROBUF Base=r11.0 ElementSize=1 SrcRegion=<16;16,1> DstRegion=<1> Type=ub
.declare ub4ROBUF Base=r11.0 ElementSize=1 SrcRegion=<32;8,4> DstRegion=<4> Type=ub
// End of common.inc
// Module name: YUV_to_RGB.asm
//
// Convert YUV to RGB, handle it by 16x4 block
//
// Description: Includes all definitions explicit to Fast Composite.
//========== GRF partition ==========
// r0 header : r0 (1 GRF)
// Static parameters : r1 - r6 (6 GRFS)
// Inline parameters : r7 - r8 (2 GRFs)
// MSGSRC : r27 (1 GRF)
//===================================
//Interface:
//========== Static Parameters (Explicit To Fast Composite) ==========
//r1
//CSC Set 0
.declare udCSC_CURBE Base=r1.0 ElementSize=4 Type=ud
//Constant alpha
//r2
// Gen7 AVS WA
// WiDi Definitions
//Colorfill
// 0: 0-degree, 1: 90, 2: 180, 3: 270-degree, clockwise.
.declare ubCOLOR_PIXEL_VAL Base=r2.20 ElementSize=1 SrcRegion=<0;1,0> DstRegion=<1> Type=ub
//r3
//Normalised Ratio of Horizontal step size with main video for all layers
//Normalised Ratio of Horizontal step size with main video for all layers becomes
//Normalised Horizontal step size for all layers in VP_Setup.asm
//r4
//Normalised Vertical step size for all layers
//r5
//Normalised Vertical Frame Origin for all layers
//r6
//Normalised Horizontal Frame Origin for all layers
//========== Inline Parameters (Explicit To Fast Composite) ==========
//Main video Step X
//====================== Binding table (Explicit To Fast Composite)=========================================
//Used by Interlaced Scaling Kernels
//========== Sampler State Table Index (Explicit To Fast Composite)==========
//Sampler Index for AVS/IEF messages
//Sampler Index for SIMD16 sampler messages
//=============================================================================
.declare fBUFFER_0 Base=r64.0 ElementSize=4 SrcRegion=<8;8,1> DstRegion=<1> Type=f
.declare fBUFFER_1 Base=r80.0 ElementSize=4 SrcRegion=<8;8,1> DstRegion=<1> Type=f
.declare fBUFFER_2 Base=r96.0 ElementSize=4 SrcRegion=<8;8,1> DstRegion=<1> Type=f
.declare fBUFFER_3 Base=r112.0 ElementSize=4 SrcRegion=<8;8,1> DstRegion=<1> Type=f
.declare bBUFFER_0 Base=r64.0 ElementSize=1 SrcRegion=<16;16,1> DstRegion=<1> Type=ub
.declare bBUFFER_1 Base=r80.0 ElementSize=1 SrcRegion=<16;16,1> DstRegion=<1> Type=ub
.declare bBUFFER_2 Base=r96.0 ElementSize=1 SrcRegion=<16;16,1> DstRegion=<1> Type=ub
.declare bBUFFER_3 Base=r112.0 ElementSize=1 SrcRegion=<16;16,1> DstRegion=<1> Type=ub
//Pointer to mask reg
//r18
//Always keep Cannel Pointers and Offsets in same GRF, so that we can use
// NODDCLR, NODDCHK flags. -rT
.declare udCSC_COEFF_0 Base=r18.0 ElementSize=4 Type=ud // 1 GRF
//r19
.declare udCSC_COEFF_1 Base=r19.0 ElementSize=4 Type=ud // 1 GRF
//r20
.declare uwALPHA_MASK_REG_TEMP Base=r20.0 ElementSize=2 SrcRegion=<16;16,1> Type=uw // 1 GRF
//r21
.declare uwALPHA_MASK_REG Base=r21.0 ElementSize=2 SrcRegion=<16;16,1> Type=uw // 1 GRF
//r22
//Always keep Cannel Pointers and Offsets in same GRF, so that we can use
// NODDCLR, NODDCHK flags. -rT
//Keep fORIGIN_X_NLAS, fY_OFFSET_2ND_BLOCK, fSTEP_X_NLAS, pMSGDSC_COPY, ubCONST_ALPHA_COPY as
//sub registers of same GRF to enable using NODDCLR NODDCHK. -rT
//r23
//Lumakey
//r24
//r25
//r26
//defines to generate LABELS during compile time.
//Msg payload buffers; upto 4 full-size messages can be written
//Unnecessary to use the MSGPayLoad, So it is temporiarily used for conversion of YUV->RGB
.declare fBUFFER_R Base=r28.0 ElementSize=4 SrcRegion=<8;8,1> Type=f
.declare fBUFFER_G Base=r30.0 ElementSize=4 SrcRegion=<8;8,1> Type=f
.declare fBUFFER_B Base=r32.0 ElementSize=4 SrcRegion=<8;8,1> Type=f
.declare fBUFFER_Y Base=r36.0 ElementSize=4 SrcRegion=<8;8,1> Type=f
.declare fBUFFER_U Base=r38.0 ElementSize=4 SrcRegion=<8;8,1> Type=f
.declare fBUFFER_V Base=r40.0 ElementSize=4 SrcRegion=<8;8,1> Type=f
.declare wTempR Base=r42.0 ElementSize=2 Type=w
.declare wTempG Base=r44.0 ElementSize=2 Type=w
.declare wTempB Base=r46.0 ElementSize=2 Type=w
.declare ubTempR Base=r42.0 ElementSize=1 Type=ub
.declare ubTempG Base=r44.0 ElementSize=1 Type=ub
.declare ubTempB Base=r46.0 ElementSize=1 Type=ub
// the r17 register (nTEMP0) is originally defined from "Common.inc"
// instead of re-defining a nTEMP0 here, we use "SAVE_RGB" suffix for its naming
.declare wTemp0 Base=r17.0 ElementSize=2 Type=uw
//_SAVE_INC_
// NTSC standard
// R = Clamp ( 1.164(Y-16/255) + 1.596(Cr-128/255))
// G = Clamp ( 1.164(Y-16/255) - 0.813(Cr-128/255) - 0.392(Cb-128/255))
// B = Clamp ( 1.164(Y-16/255) + 2.017(Cb-128/255))
// ITU-R conversion, Now we are using ITU-R conversion
// R = clip( Y + 1.402*(Cr-128)) // ITU-R
// G = clip( Y - 0.344*(Cb-128) - 0.714*(Cr-128))
// B = clip( Y + 1.772*(Cb-128))
// At the save module we have all 8 address sub-registers available.
// So we will use PING-PONG type of scheme to save the data using
// pointers pBUF_CHNL_TOP_8x4 and pBUF_CHNL_BOT_8x4. This will help
// reduce dependency. - rT
//wBUFF_CHNL_PTR points to either buffer 0 or buffer 4.
//Add appropriate offsets to get pointers for all buffers (1,2,3 or 5).
//Offsets are zero for buffer 0 and buffer 4.
//Y/U/V is also stored as R/G/B for the internal purpose
//for BUFFER_0
mov (4) a0.0<1>:uw r22.0<4;4,1>:uw
//the first line in the block 0
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 1]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 17]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 1]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 17]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 1]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 17]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,1]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,1]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,1]<2>:ub ubTempB(0, 0)<32;8,4>
//the second line in the block 0
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 33]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 49]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 33]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 49]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 33]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 49]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,33]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,33]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,33]<2>:ub ubTempB(0, 0)<32;8,4>
//the third line in the block 0
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 65]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 81]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 65]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 81]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 65]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 81]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,65]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,65]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,65]<2>:ub ubTempB(0, 0)<32;8,4>
//the fourth line in the block 0
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 97]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 113]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 97]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 113]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 97]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 113]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,97]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,97]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,97]<2>:ub ubTempB(0, 0)<32;8,4>
//for BUFFER_1
add (4) a0.0<1>:uw r22.0<4;4,1>:uw 512:uw
//the first line in the block 1
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 1]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 17]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 1]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 17]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 1]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 17]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,1]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,1]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,1]<2>:ub ubTempB(0, 0)<32;8,4>
//the second line in the block 1
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 33]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 49]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 33]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 49]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 33]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 49]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,33]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,33]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,33]<2>:ub ubTempB(0, 0)<32;8,4>
//the third line in the block 1
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 65]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 81]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 65]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 81]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 65]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 81]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,65]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,65]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,65]<2>:ub ubTempB(0, 0)<32;8,4>
//the fourth line in the block 1
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 97]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 113]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 97]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 113]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 97]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 113]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,97]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,97]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,97]<2>:ub ubTempB(0, 0)<32;8,4>
//for BUFFER_2
add (4) a0.0<1>:uw r22.0<4;4,1>:uw 1024:uw
//the first line in the block 2
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 1]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 17]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 1]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 17]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 1]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 17]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,1]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,1]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,1]<2>:ub ubTempB(0, 0)<32;8,4>
//the second line in the block 2
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 33]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 49]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 33]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 49]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 33]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 49]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,33]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,33]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,33]<2>:ub ubTempB(0, 0)<32;8,4>
//the third line in the block 2
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 65]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 81]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 65]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 81]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 65]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 81]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,65]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,65]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,65]<2>:ub ubTempB(0, 0)<32;8,4>
//the fourth line in the block 2
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 97]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 113]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 97]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 113]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 97]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 113]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,97]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,97]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,97]<2>:ub ubTempB(0, 0)<32;8,4>
//for BUFFER_3
add (4) a0.0<1>:uw r22.0<4;4,1>:uw 1536:uw
//the first line in the block 3
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 1]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 17]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 1]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 17]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 1]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 17]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,1]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,1]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,1]<2>:ub ubTempB(0, 0)<32;8,4>
//the second line in the block 3
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 33]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 49]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 33]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 49]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 33]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 49]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,33]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,33]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,33]<2>:ub ubTempB(0, 0)<32;8,4>
//the third line in the block 3
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 65]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 81]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 65]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 81]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 65]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 81]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,65]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,65]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,65]<2>:ub ubTempB(0, 0)<32;8,4>
//the fourth line in the block 3
mov (8) fBUFFER_Y(0, 0)<1> r[a0.1, 97]<16;8,2>:ub
mov (8) fBUFFER_Y(1, 0)<1> r[a0.1, 113]<16;8,2>:ub
mov (8) fBUFFER_U(0, 0)<1> r[a0.2, 97]<16;8,2>:ub
mov (8) fBUFFER_U(1, 0)<1> r[a0.2, 113]<16;8,2>:ub
mov (8) fBUFFER_V(0, 0)<1> r[a0.0, 97]<16;8,2>:ub
mov (8) fBUFFER_V(1, 0)<1> r[a0.0, 113]<16;8,2>:ub
add (16) fBUFFER_U(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> -128.0f
add (16) fBUFFER_V(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -128.0f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_R(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 1.402f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (8) acc0.0<1>:f fBUFFER_U(0, 0)<8;8,1> -0.344f
mac (8) acc1.0<1>:f fBUFFER_U(1, 0)<8;8,1> -0.344f
mac (16) fBUFFER_G(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> -0.714f
mov (16) acc0.0<1>:f fBUFFER_Y(0, 0)<8;8,1>
mac (16) fBUFFER_B(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 1.772f
mul.sat (16) fBUFFER_Y(0, 0)<1> fBUFFER_R(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_U(0, 0)<1> fBUFFER_G(0, 0)<8;8,1> 0.0039216f
mul.sat (16) fBUFFER_V(0, 0)<1> fBUFFER_B(0, 0)<8;8,1> 0.0039216f
mul (16) fBUFFER_R(0, 0)<1> fBUFFER_Y(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_G(0, 0)<1> fBUFFER_U(0, 0)<8;8,1> 255.0f
mul (16) fBUFFER_B(0, 0)<1> fBUFFER_V(0, 0)<8;8,1> 255.0f
mov (16) wTempR(0, 0)<2> fBUFFER_R(0, 0)<8;8,1>
mov (16) wTempG(0, 0)<2> fBUFFER_G(0, 0)<8;8,1>
mov (16) wTempB(0, 0)<2> fBUFFER_B(0, 0)<8;8,1>
mov (16) r[a0.1,97]<2>:ub ubTempR(0, 0)<32;8,4>
mov (16) r[a0.2,97]<2>:ub ubTempG(0, 0)<32;8,4>
mov (16) r[a0.0,97]<2>:ub ubTempB(0, 0)<32;8,4>
|
