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
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
|
/*
* Copyright 2013 The LibYuv Project Authors. All rights reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#ifndef INCLUDE_LIBYUV_SCALE_ROW_H_
#define INCLUDE_LIBYUV_SCALE_ROW_H_
#include "libyuv/basic_types.h"
#include "libyuv/scale.h"
#ifdef __cplusplus
namespace libyuv {
extern "C" {
#endif
#if defined(__pnacl__) || defined(__CLR_VER) || \
(defined(__native_client__) && defined(__x86_64__)) || \
(defined(__i386__) && !defined(__SSE__) && !defined(__clang__))
#define LIBYUV_DISABLE_X86
#endif
#if defined(__native_client__)
#define LIBYUV_DISABLE_NEON
#endif
// MemorySanitizer does not support assembly code yet. http://crbug.com/344505
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
#define LIBYUV_DISABLE_X86
#endif
#endif
// GCC >= 4.7.0 required for AVX2.
#if defined(__GNUC__) && (defined(__x86_64__) || defined(__i386__))
#if (__GNUC__ > 4) || (__GNUC__ == 4 && (__GNUC_MINOR__ >= 7))
#define GCC_HAS_AVX2 1
#endif // GNUC >= 4.7
#endif // __GNUC__
// clang >= 3.4.0 required for AVX2.
#if defined(__clang__) && (defined(__x86_64__) || defined(__i386__))
#if (__clang_major__ > 3) || (__clang_major__ == 3 && (__clang_minor__ >= 4))
#define CLANG_HAS_AVX2 1
#endif // clang >= 3.4
#endif // __clang__
// Visual C 2012 required for AVX2.
#if defined(_M_IX86) && !defined(__clang__) && defined(_MSC_VER) && \
_MSC_VER >= 1700
#define VISUALC_HAS_AVX2 1
#endif // VisualStudio >= 2012
// The following are available on all x86 platforms:
#if !defined(LIBYUV_DISABLE_X86) && \
(defined(_M_IX86) || defined(__x86_64__) || defined(__i386__))
#define HAS_FIXEDDIV1_X86
#define HAS_FIXEDDIV_X86
#define HAS_SCALEADDROW_SSE2
#define HAS_SCALEARGBCOLS_SSE2
#define HAS_SCALEARGBCOLSUP2_SSE2
#define HAS_SCALEARGBFILTERCOLS_SSSE3
#define HAS_SCALEARGBROWDOWN2_SSE2
#define HAS_SCALEARGBROWDOWNEVEN_SSE2
#define HAS_SCALECOLSUP2_SSE2
#define HAS_SCALEFILTERCOLS_SSSE3
#define HAS_SCALEROWDOWN2_SSSE3
#define HAS_SCALEROWDOWN34_SSSE3
#define HAS_SCALEROWDOWN38_SSSE3
#define HAS_SCALEROWDOWN4_SSSE3
#endif
// The following are available on all x86 platforms, but
// require VS2012, clang 3.4 or gcc 4.7.
// The code supports NaCL but requires a new compiler and validator.
#if !defined(LIBYUV_DISABLE_X86) && \
(defined(VISUALC_HAS_AVX2) || defined(CLANG_HAS_AVX2) || \
defined(GCC_HAS_AVX2))
#define HAS_SCALEADDROW_AVX2
#define HAS_SCALEROWDOWN2_AVX2
#define HAS_SCALEROWDOWN4_AVX2
#endif
// The following are available on Neon platforms:
#if !defined(LIBYUV_DISABLE_NEON) && \
(defined(__ARM_NEON__) || defined(LIBYUV_NEON) || defined(__aarch64__))
#define HAS_SCALEADDROW_NEON
#define HAS_SCALEARGBCOLS_NEON
#define HAS_SCALEARGBFILTERCOLS_NEON
#define HAS_SCALEARGBROWDOWN2_NEON
#define HAS_SCALEARGBROWDOWNEVEN_NEON
#define HAS_SCALEFILTERCOLS_NEON
#define HAS_SCALEROWDOWN2_NEON
#define HAS_SCALEROWDOWN34_NEON
#define HAS_SCALEROWDOWN38_NEON
#define HAS_SCALEROWDOWN4_NEON
#endif
#if !defined(LIBYUV_DISABLE_MSA) && defined(__mips_msa)
#define HAS_SCALEADDROW_MSA
#define HAS_SCALEARGBCOLS_MSA
#define HAS_SCALEARGBFILTERCOLS_MSA
#define HAS_SCALEARGBROWDOWN2_MSA
#define HAS_SCALEARGBROWDOWNEVEN_MSA
#define HAS_SCALEFILTERCOLS_MSA
#define HAS_SCALEROWDOWN2_MSA
#define HAS_SCALEROWDOWN34_MSA
#define HAS_SCALEROWDOWN38_MSA
#define HAS_SCALEROWDOWN4_MSA
#endif
#if !defined(LIBYUV_DISABLE_MMI) && defined(_MIPS_ARCH_LOONGSON3A)
#define HAS_FIXEDDIV1_MIPS
#define HAS_FIXEDDIV_MIPS
#define HAS_SCALEADDROW_16_MMI
#define HAS_SCALEADDROW_MMI
#define HAS_SCALEARGBCOLS_MMI
#define HAS_SCALEARGBCOLSUP2_MMI
#define HAS_SCALEARGBROWDOWN2_MMI
#define HAS_SCALEARGBROWDOWNEVEN_MMI
#define HAS_SCALECOLS_16_MMI
#define HAS_SCALECOLS_MMI
#define HAS_SCALEROWDOWN2_16_MMI
#define HAS_SCALEROWDOWN2_MMI
#define HAS_SCALEROWDOWN4_16_MMI
#define HAS_SCALEROWDOWN4_MMI
#define HAS_SCALEROWDOWN34_MMI
#endif
// Scale ARGB vertically with bilinear interpolation.
void ScalePlaneVertical(int src_height,
int dst_width,
int dst_height,
int src_stride,
int dst_stride,
const uint8_t* src_argb,
uint8_t* dst_argb,
int x,
int y,
int dy,
int bpp,
enum FilterMode filtering);
void ScalePlaneVertical_16(int src_height,
int dst_width,
int dst_height,
int src_stride,
int dst_stride,
const uint16_t* src_argb,
uint16_t* dst_argb,
int x,
int y,
int dy,
int wpp,
enum FilterMode filtering);
// Simplify the filtering based on scale factors.
enum FilterMode ScaleFilterReduce(int src_width,
int src_height,
int dst_width,
int dst_height,
enum FilterMode filtering);
// Divide num by div and return as 16.16 fixed point result.
int FixedDiv_C(int num, int div);
int FixedDiv_X86(int num, int div);
int FixedDiv_MIPS(int num, int div);
// Divide num - 1 by div - 1 and return as 16.16 fixed point result.
int FixedDiv1_C(int num, int div);
int FixedDiv1_X86(int num, int div);
int FixedDiv1_MIPS(int num, int div);
#ifdef HAS_FIXEDDIV_X86
#define FixedDiv FixedDiv_X86
#define FixedDiv1 FixedDiv1_X86
#elif defined HAS_FIXEDDIV_MIPS
#define FixedDiv FixedDiv_MIPS
#define FixedDiv1 FixedDiv1_MIPS
#else
#define FixedDiv FixedDiv_C
#define FixedDiv1 FixedDiv1_C
#endif
// Compute slope values for stepping.
void ScaleSlope(int src_width,
int src_height,
int dst_width,
int dst_height,
enum FilterMode filtering,
int* x,
int* y,
int* dx,
int* dy);
void ScaleRowDown2_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown2Linear_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Linear_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown2Box_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Box_Odd_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Box_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown4_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown4Box_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4Box_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown34_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown34_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown34_0_Box_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* d,
int dst_width);
void ScaleRowDown34_0_Box_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* d,
int dst_width);
void ScaleRowDown34_1_Box_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* d,
int dst_width);
void ScaleRowDown34_1_Box_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* d,
int dst_width);
void ScaleCols_C(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleCols_16_C(uint16_t* dst_ptr,
const uint16_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleColsUp2_C(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int,
int);
void ScaleColsUp2_16_C(uint16_t* dst_ptr,
const uint16_t* src_ptr,
int dst_width,
int,
int);
void ScaleFilterCols_C(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleFilterCols_16_C(uint16_t* dst_ptr,
const uint16_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleFilterCols64_C(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x32,
int dx);
void ScaleFilterCols64_16_C(uint16_t* dst_ptr,
const uint16_t* src_ptr,
int dst_width,
int x32,
int dx);
void ScaleRowDown38_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown38_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown38_3_Box_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_3_Box_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst_ptr,
int dst_width);
void ScaleRowDown38_2_Box_C(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_2_Box_16_C(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst_ptr,
int dst_width);
void ScaleAddRow_C(const uint8_t* src_ptr, uint16_t* dst_ptr, int src_width);
void ScaleAddRow_16_C(const uint16_t* src_ptr,
uint32_t* dst_ptr,
int src_width);
void ScaleARGBRowDown2_C(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Linear_C(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Box_C(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEven_C(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEvenBox_C(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBCols_C(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBCols64_C(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x32,
int dx);
void ScaleARGBColsUp2_C(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int,
int);
void ScaleARGBFilterCols_C(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBFilterCols64_C(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x32,
int dx);
// Specialized scalers for x86.
void ScaleRowDown2_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Linear_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Linear_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_1_Box_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_0_Box_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_3_Box_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_2_Box_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Linear_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Odd_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2_Any_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Linear_Any_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Any_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Odd_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4_Any_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_Any_AVX2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_1_Box_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_0_Box_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_3_Box_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_2_Box_Any_SSSE3(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleAddRow_SSE2(const uint8_t* src_ptr, uint16_t* dst_ptr, int src_width);
void ScaleAddRow_AVX2(const uint8_t* src_ptr, uint16_t* dst_ptr, int src_width);
void ScaleAddRow_Any_SSE2(const uint8_t* src_ptr,
uint16_t* dst_ptr,
int src_width);
void ScaleAddRow_Any_AVX2(const uint8_t* src_ptr,
uint16_t* dst_ptr,
int src_width);
void ScaleFilterCols_SSSE3(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleColsUp2_SSE2(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
// ARGB Column functions
void ScaleARGBCols_SSE2(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBFilterCols_SSSE3(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBColsUp2_SSE2(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBFilterCols_NEON(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBCols_NEON(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBFilterCols_Any_NEON(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleARGBCols_Any_NEON(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleARGBFilterCols_MSA(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBCols_MSA(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBFilterCols_Any_MSA(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleARGBCols_Any_MSA(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleARGBCols_MMI(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleARGBCols_Any_MMI(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
// ARGB Row functions
void ScaleARGBRowDown2_SSE2(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Linear_SSE2(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Box_SSE2(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleARGBRowDown2Linear_NEON(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Box_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleARGBRowDown2_MSA(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Linear_MSA(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Box_MSA(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2_MMI(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Linear_MMI(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2Box_MMI(const uint8_t* src_argb,
ptrdiff_t src_stride,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDown2_Any_SSE2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Linear_Any_SSE2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Box_Any_SSE2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Linear_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Box_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Linear_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Box_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Linear_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDown2Box_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEven_SSE2(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEvenBox_SSE2(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEven_NEON(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEvenBox_NEON(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEven_MSA(const uint8_t* src_argb,
ptrdiff_t src_stride,
int32_t src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEvenBox_MSA(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEven_MMI(const uint8_t* src_argb,
ptrdiff_t src_stride,
int32_t src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEvenBox_MMI(const uint8_t* src_argb,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_argb,
int dst_width);
void ScaleARGBRowDownEven_Any_SSE2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEvenBox_Any_SSE2(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEven_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEvenBox_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEven_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int32_t src_stepx,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEvenBox_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEven_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int32_t src_stepx,
uint8_t* dst_ptr,
int dst_width);
void ScaleARGBRowDownEvenBox_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
int src_stepx,
uint8_t* dst_ptr,
int dst_width);
// ScaleRowDown2Box also used by planar functions
// NEON downscalers with interpolation.
// Note - not static due to reuse in convert for 444 to 420.
void ScaleRowDown2_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Linear_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Box_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
// Down scale from 4 to 3 pixels. Use the neon multilane read/write
// to load up the every 4th pixel into a 4 different registers.
// Point samples 32 pixels to 24 pixels.
void ScaleRowDown34_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_0_Box_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_1_Box_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
// 32 -> 12
void ScaleRowDown38_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
// 32x3 -> 12x1
void ScaleRowDown38_3_Box_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
// 32x2 -> 12x1
void ScaleRowDown38_2_Box_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Linear_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Odd_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_0_Box_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_1_Box_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
// 32 -> 12
void ScaleRowDown38_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
// 32x3 -> 12x1
void ScaleRowDown38_3_Box_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
// 32x2 -> 12x1
void ScaleRowDown38_2_Box_Any_NEON(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleAddRow_NEON(const uint8_t* src_ptr, uint16_t* dst_ptr, int src_width);
void ScaleAddRow_Any_NEON(const uint8_t* src_ptr,
uint16_t* dst_ptr,
int src_width);
void ScaleFilterCols_NEON(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleFilterCols_Any_NEON(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleRowDown2_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Linear_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Box_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4Box_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown38_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown38_2_Box_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_3_Box_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleAddRow_MSA(const uint8_t* src_ptr, uint16_t* dst_ptr, int src_width);
void ScaleFilterCols_MSA(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleRowDown34_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown34_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown34_0_Box_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* d,
int dst_width);
void ScaleRowDown34_1_Box_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* d,
int dst_width);
void ScaleRowDown2_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Linear_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_2_Box_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown38_3_Box_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleAddRow_Any_MSA(const uint8_t* src_ptr,
uint16_t* dst_ptr,
int src_width);
void ScaleFilterCols_Any_MSA(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleRowDown34_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_0_Box_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown34_1_Box_Any_MSA(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2_16_MMI(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown2Linear_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Linear_16_MMI(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown2Box_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown2Box_16_MMI(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown2Box_Odd_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4_16_MMI(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleRowDown4Box_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst,
int dst_width);
void ScaleRowDown4Box_16_MMI(const uint16_t* src_ptr,
ptrdiff_t src_stride,
uint16_t* dst,
int dst_width);
void ScaleAddRow_MMI(const uint8_t* src_ptr, uint16_t* dst_ptr, int src_width);
void ScaleAddRow_16_MMI(const uint16_t* src_ptr,
uint32_t* dst_ptr,
int src_width);
void ScaleColsUp2_MMI(uint8_t* dst_ptr,
const uint8_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleColsUp2_16_MMI(uint16_t* dst_ptr,
const uint16_t* src_ptr,
int dst_width,
int x,
int dx);
void ScaleARGBColsUp2_MMI(uint8_t* dst_argb,
const uint8_t* src_argb,
int dst_width,
int x,
int dx);
void ScaleRowDown2_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Linear_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown2Box_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleRowDown4Box_Any_MMI(const uint8_t* src_ptr,
ptrdiff_t src_stride,
uint8_t* dst_ptr,
int dst_width);
void ScaleAddRow_Any_MMI(const uint8_t* src_ptr,
uint16_t* dst_ptr,
int src_width);
#ifdef __cplusplus
} // extern "C"
} // namespace libyuv
#endif
#endif // INCLUDE_LIBYUV_SCALE_ROW_H_
|
