Wu Jianhua
9ef6e15b04
tests/checkasm: add checkasm_check_vvc_alf and check_alf_filter
...
Signed-off-by: Wu Jianhua <toqsxw@outlook.com>
2024-05-14 19:21:35 +08:00
Wu Jianhua
ec2a7ef867
avcodec/x86/vvc: add alf filter luma and chroma avx2 optimizations
...
ff_vvc_alf_filter_luma_4x4_10_c: 135
ff_vvc_alf_filter_luma_4x4_10_avx2: 54
ff_vvc_alf_filter_luma_4x8_10_c: 268
ff_vvc_alf_filter_luma_4x8_10_avx2: 106
ff_vvc_alf_filter_luma_4x12_10_c: 400
ff_vvc_alf_filter_luma_4x12_10_avx2: 160
ff_vvc_alf_filter_luma_4x16_10_c: 535
ff_vvc_alf_filter_luma_4x16_10_avx2: 213
ff_vvc_alf_filter_luma_4x20_10_c: 646
ff_vvc_alf_filter_luma_4x20_10_avx2: 262
ff_vvc_alf_filter_luma_4x24_10_c: 783
ff_vvc_alf_filter_luma_4x24_10_avx2: 309
ff_vvc_alf_filter_luma_4x28_10_c: 908
ff_vvc_alf_filter_luma_4x28_10_avx2: 361
ff_vvc_alf_filter_luma_4x32_10_c: 1039
ff_vvc_alf_filter_luma_4x32_10_avx2: 412
ff_vvc_alf_filter_luma_8x4_10_c: 260
ff_vvc_alf_filter_luma_8x4_10_avx2: 53
ff_vvc_alf_filter_luma_8x8_10_c: 516
ff_vvc_alf_filter_luma_8x8_10_avx2: 105
ff_vvc_alf_filter_luma_8x12_10_c: 779
ff_vvc_alf_filter_luma_8x12_10_avx2: 157
ff_vvc_alf_filter_luma_8x16_10_c: 1038
ff_vvc_alf_filter_luma_8x16_10_avx2: 210
ff_vvc_alf_filter_luma_8x20_10_c: 1293
ff_vvc_alf_filter_luma_8x20_10_avx2: 259
ff_vvc_alf_filter_luma_8x24_10_c: 1553
ff_vvc_alf_filter_luma_8x24_10_avx2: 309
ff_vvc_alf_filter_luma_8x28_10_c: 1815
ff_vvc_alf_filter_luma_8x28_10_avx2: 361
ff_vvc_alf_filter_luma_8x32_10_c: 2067
ff_vvc_alf_filter_luma_8x32_10_avx2: 419
ff_vvc_alf_filter_luma_12x4_10_c: 390
ff_vvc_alf_filter_luma_12x4_10_avx2: 54
ff_vvc_alf_filter_luma_12x8_10_c: 773
ff_vvc_alf_filter_luma_12x8_10_avx2: 107
ff_vvc_alf_filter_luma_12x12_10_c: 1159
ff_vvc_alf_filter_luma_12x12_10_avx2: 155
ff_vvc_alf_filter_luma_12x16_10_c: 1550
ff_vvc_alf_filter_luma_12x16_10_avx2: 207
ff_vvc_alf_filter_luma_12x20_10_c: 1970
ff_vvc_alf_filter_luma_12x20_10_avx2: 260
ff_vvc_alf_filter_luma_12x24_10_c: 2379
ff_vvc_alf_filter_luma_12x24_10_avx2: 309
ff_vvc_alf_filter_luma_12x28_10_c: 2763
ff_vvc_alf_filter_luma_12x28_10_avx2: 362
ff_vvc_alf_filter_luma_12x32_10_c: 3158
ff_vvc_alf_filter_luma_12x32_10_avx2: 419
ff_vvc_alf_filter_luma_16x4_10_c: 523
ff_vvc_alf_filter_luma_16x4_10_avx2: 53
ff_vvc_alf_filter_luma_16x8_10_c: 1049
ff_vvc_alf_filter_luma_16x8_10_avx2: 103
ff_vvc_alf_filter_luma_16x12_10_c: 1566
ff_vvc_alf_filter_luma_16x12_10_avx2: 159
ff_vvc_alf_filter_luma_16x16_10_c: 2078
ff_vvc_alf_filter_luma_16x16_10_avx2: 211
ff_vvc_alf_filter_luma_16x20_10_c: 2631
ff_vvc_alf_filter_luma_16x20_10_avx2: 259
ff_vvc_alf_filter_luma_16x24_10_c: 3149
ff_vvc_alf_filter_luma_16x24_10_avx2: 316
ff_vvc_alf_filter_luma_16x28_10_c: 3631
ff_vvc_alf_filter_luma_16x28_10_avx2: 359
ff_vvc_alf_filter_luma_16x32_10_c: 4233
ff_vvc_alf_filter_luma_16x32_10_avx2: 428
ff_vvc_alf_filter_luma_20x4_10_c: 649
ff_vvc_alf_filter_luma_20x4_10_avx2: 106
ff_vvc_alf_filter_luma_20x8_10_c: 1294
ff_vvc_alf_filter_luma_20x8_10_avx2: 206
ff_vvc_alf_filter_luma_20x12_10_c: 1936
ff_vvc_alf_filter_luma_20x12_10_avx2: 310
ff_vvc_alf_filter_luma_20x16_10_c: 2594
ff_vvc_alf_filter_luma_20x16_10_avx2: 411
ff_vvc_alf_filter_luma_20x20_10_c: 3234
ff_vvc_alf_filter_luma_20x20_10_avx2: 517
ff_vvc_alf_filter_luma_20x24_10_c: 3894
ff_vvc_alf_filter_luma_20x24_10_avx2: 621
ff_vvc_alf_filter_luma_20x28_10_c: 4542
ff_vvc_alf_filter_luma_20x28_10_avx2: 722
ff_vvc_alf_filter_luma_20x32_10_c: 5205
ff_vvc_alf_filter_luma_20x32_10_avx2: 832
ff_vvc_alf_filter_luma_24x4_10_c: 774
ff_vvc_alf_filter_luma_24x4_10_avx2: 104
ff_vvc_alf_filter_luma_24x8_10_c: 1546
ff_vvc_alf_filter_luma_24x8_10_avx2: 206
ff_vvc_alf_filter_luma_24x12_10_c: 2318
ff_vvc_alf_filter_luma_24x12_10_avx2: 312
ff_vvc_alf_filter_luma_24x16_10_c: 3104
ff_vvc_alf_filter_luma_24x16_10_avx2: 411
ff_vvc_alf_filter_luma_24x20_10_c: 3893
ff_vvc_alf_filter_luma_24x20_10_avx2: 513
ff_vvc_alf_filter_luma_24x24_10_c: 4681
ff_vvc_alf_filter_luma_24x24_10_avx2: 616
ff_vvc_alf_filter_luma_24x28_10_c: 5474
ff_vvc_alf_filter_luma_24x28_10_avx2: 721
ff_vvc_alf_filter_luma_24x32_10_c: 6271
ff_vvc_alf_filter_luma_24x32_10_avx2: 832
ff_vvc_alf_filter_luma_28x4_10_c: 907
ff_vvc_alf_filter_luma_28x4_10_avx2: 103
ff_vvc_alf_filter_luma_28x8_10_c: 1797
ff_vvc_alf_filter_luma_28x8_10_avx2: 206
ff_vvc_alf_filter_luma_28x12_10_c: 2708
ff_vvc_alf_filter_luma_28x12_10_avx2: 309
ff_vvc_alf_filter_luma_28x16_10_c: 3632
ff_vvc_alf_filter_luma_28x16_10_avx2: 413
ff_vvc_alf_filter_luma_28x20_10_c: 4537
ff_vvc_alf_filter_luma_28x20_10_avx2: 519
ff_vvc_alf_filter_luma_28x24_10_c: 5463
ff_vvc_alf_filter_luma_28x24_10_avx2: 616
ff_vvc_alf_filter_luma_28x28_10_c: 6372
ff_vvc_alf_filter_luma_28x28_10_avx2: 719
ff_vvc_alf_filter_luma_28x32_10_c: 7274
ff_vvc_alf_filter_luma_28x32_10_avx2: 823
ff_vvc_alf_filter_luma_32x4_10_c: 1029
ff_vvc_alf_filter_luma_32x4_10_avx2: 104
ff_vvc_alf_filter_luma_32x8_10_c: 2060
ff_vvc_alf_filter_luma_32x8_10_avx2: 206
ff_vvc_alf_filter_luma_32x12_10_c: 3112
ff_vvc_alf_filter_luma_32x12_10_avx2: 307
ff_vvc_alf_filter_luma_32x16_10_c: 4161
ff_vvc_alf_filter_luma_32x16_10_avx2: 413
ff_vvc_alf_filter_luma_32x20_10_c: 5211
ff_vvc_alf_filter_luma_32x20_10_avx2: 514
ff_vvc_alf_filter_luma_32x24_10_c: 6238
ff_vvc_alf_filter_luma_32x24_10_avx2: 614
ff_vvc_alf_filter_luma_32x28_10_c: 7261
ff_vvc_alf_filter_luma_32x28_10_avx2: 720
ff_vvc_alf_filter_luma_32x32_10_c: 8312
ff_vvc_alf_filter_luma_32x32_10_avx2: 819
ff_vvc_alf_filter_chroma_4x4_10_c: 70
ff_vvc_alf_filter_chroma_4x4_10_avx2: 53
ff_vvc_alf_filter_chroma_4x8_10_c: 139
ff_vvc_alf_filter_chroma_4x8_10_avx2: 104
ff_vvc_alf_filter_chroma_4x12_10_c: 208
ff_vvc_alf_filter_chroma_4x12_10_avx2: 155
ff_vvc_alf_filter_chroma_4x16_10_c: 275
ff_vvc_alf_filter_chroma_4x16_10_avx2: 218
ff_vvc_alf_filter_chroma_4x20_10_c: 344
ff_vvc_alf_filter_chroma_4x20_10_avx2: 257
ff_vvc_alf_filter_chroma_4x24_10_c: 411
ff_vvc_alf_filter_chroma_4x24_10_avx2: 309
ff_vvc_alf_filter_chroma_4x28_10_c: 481
ff_vvc_alf_filter_chroma_4x28_10_avx2: 361
ff_vvc_alf_filter_chroma_4x32_10_c: 545
ff_vvc_alf_filter_chroma_4x32_10_avx2: 411
ff_vvc_alf_filter_chroma_8x4_10_c: 138
ff_vvc_alf_filter_chroma_8x4_10_avx2: 53
ff_vvc_alf_filter_chroma_8x8_10_c: 274
ff_vvc_alf_filter_chroma_8x8_10_avx2: 106
ff_vvc_alf_filter_chroma_8x12_10_c: 422
ff_vvc_alf_filter_chroma_8x12_10_avx2: 158
ff_vvc_alf_filter_chroma_8x16_10_c: 545
ff_vvc_alf_filter_chroma_8x16_10_avx2: 206
ff_vvc_alf_filter_chroma_8x20_10_c: 683
ff_vvc_alf_filter_chroma_8x20_10_avx2: 257
ff_vvc_alf_filter_chroma_8x24_10_c: 816
ff_vvc_alf_filter_chroma_8x24_10_avx2: 312
ff_vvc_alf_filter_chroma_8x28_10_c: 951
ff_vvc_alf_filter_chroma_8x28_10_avx2: 359
ff_vvc_alf_filter_chroma_8x32_10_c: 1098
ff_vvc_alf_filter_chroma_8x32_10_avx2: 409
ff_vvc_alf_filter_chroma_12x4_10_c: 204
ff_vvc_alf_filter_chroma_12x4_10_avx2: 53
ff_vvc_alf_filter_chroma_12x8_10_c: 410
ff_vvc_alf_filter_chroma_12x8_10_avx2: 104
ff_vvc_alf_filter_chroma_12x12_10_c: 614
ff_vvc_alf_filter_chroma_12x12_10_avx2: 155
ff_vvc_alf_filter_chroma_12x16_10_c: 814
ff_vvc_alf_filter_chroma_12x16_10_avx2: 210
ff_vvc_alf_filter_chroma_12x20_10_c: 1017
ff_vvc_alf_filter_chroma_12x20_10_avx2: 258
ff_vvc_alf_filter_chroma_12x24_10_c: 1221
ff_vvc_alf_filter_chroma_12x24_10_avx2: 308
ff_vvc_alf_filter_chroma_12x28_10_c: 1423
ff_vvc_alf_filter_chroma_12x28_10_avx2: 366
ff_vvc_alf_filter_chroma_12x32_10_c: 1624
ff_vvc_alf_filter_chroma_12x32_10_avx2: 410
ff_vvc_alf_filter_chroma_16x4_10_c: 272
ff_vvc_alf_filter_chroma_16x4_10_avx2: 52
ff_vvc_alf_filter_chroma_16x8_10_c: 541
ff_vvc_alf_filter_chroma_16x8_10_avx2: 105
ff_vvc_alf_filter_chroma_16x12_10_c: 812
ff_vvc_alf_filter_chroma_16x12_10_avx2: 155
ff_vvc_alf_filter_chroma_16x16_10_c: 1091
ff_vvc_alf_filter_chroma_16x16_10_avx2: 206
ff_vvc_alf_filter_chroma_16x20_10_c: 1354
ff_vvc_alf_filter_chroma_16x20_10_avx2: 257
ff_vvc_alf_filter_chroma_16x24_10_c: 1637
ff_vvc_alf_filter_chroma_16x24_10_avx2: 313
ff_vvc_alf_filter_chroma_16x28_10_c: 1899
ff_vvc_alf_filter_chroma_16x28_10_avx2: 359
ff_vvc_alf_filter_chroma_16x32_10_c: 2161
ff_vvc_alf_filter_chroma_16x32_10_avx2: 410
ff_vvc_alf_filter_chroma_20x4_10_c: 339
ff_vvc_alf_filter_chroma_20x4_10_avx2: 103
ff_vvc_alf_filter_chroma_20x8_10_c: 681
ff_vvc_alf_filter_chroma_20x8_10_avx2: 207
ff_vvc_alf_filter_chroma_20x12_10_c: 1013
ff_vvc_alf_filter_chroma_20x12_10_avx2: 307
ff_vvc_alf_filter_chroma_20x16_10_c: 1349
ff_vvc_alf_filter_chroma_20x16_10_avx2: 415
ff_vvc_alf_filter_chroma_20x20_10_c: 1685
ff_vvc_alf_filter_chroma_20x20_10_avx2: 522
ff_vvc_alf_filter_chroma_20x24_10_c: 2037
ff_vvc_alf_filter_chroma_20x24_10_avx2: 622
ff_vvc_alf_filter_chroma_20x28_10_c: 2380
ff_vvc_alf_filter_chroma_20x28_10_avx2: 733
ff_vvc_alf_filter_chroma_20x32_10_c: 2712
ff_vvc_alf_filter_chroma_20x32_10_avx2: 838
ff_vvc_alf_filter_chroma_24x4_10_c: 408
ff_vvc_alf_filter_chroma_24x4_10_avx2: 104
ff_vvc_alf_filter_chroma_24x8_10_c: 818
ff_vvc_alf_filter_chroma_24x8_10_avx2: 207
ff_vvc_alf_filter_chroma_24x12_10_c: 1219
ff_vvc_alf_filter_chroma_24x12_10_avx2: 308
ff_vvc_alf_filter_chroma_24x16_10_c: 1648
ff_vvc_alf_filter_chroma_24x16_10_avx2: 420
ff_vvc_alf_filter_chroma_24x20_10_c: 2061
ff_vvc_alf_filter_chroma_24x20_10_avx2: 525
ff_vvc_alf_filter_chroma_24x24_10_c: 2437
ff_vvc_alf_filter_chroma_24x24_10_avx2: 617
ff_vvc_alf_filter_chroma_24x28_10_c: 2832
ff_vvc_alf_filter_chroma_24x28_10_avx2: 722
ff_vvc_alf_filter_chroma_24x32_10_c: 3271
ff_vvc_alf_filter_chroma_24x32_10_avx2: 830
ff_vvc_alf_filter_chroma_28x4_10_c: 476
ff_vvc_alf_filter_chroma_28x4_10_avx2: 104
ff_vvc_alf_filter_chroma_28x8_10_c: 948
ff_vvc_alf_filter_chroma_28x8_10_avx2: 205
ff_vvc_alf_filter_chroma_28x12_10_c: 1420
ff_vvc_alf_filter_chroma_28x12_10_avx2: 310
ff_vvc_alf_filter_chroma_28x16_10_c: 1889
ff_vvc_alf_filter_chroma_28x16_10_avx2: 423
ff_vvc_alf_filter_chroma_28x20_10_c: 2372
ff_vvc_alf_filter_chroma_28x20_10_avx2: 513
ff_vvc_alf_filter_chroma_28x24_10_c: 2843
ff_vvc_alf_filter_chroma_28x24_10_avx2: 618
ff_vvc_alf_filter_chroma_28x28_10_c: 3307
ff_vvc_alf_filter_chroma_28x28_10_avx2: 724
ff_vvc_alf_filter_chroma_28x32_10_c: 3801
ff_vvc_alf_filter_chroma_28x32_10_avx2: 827
ff_vvc_alf_filter_chroma_32x4_10_c: 543
ff_vvc_alf_filter_chroma_32x4_10_avx2: 105
ff_vvc_alf_filter_chroma_32x8_10_c: 1084
ff_vvc_alf_filter_chroma_32x8_10_avx2: 206
ff_vvc_alf_filter_chroma_32x12_10_c: 1621
ff_vvc_alf_filter_chroma_32x12_10_avx2: 309
ff_vvc_alf_filter_chroma_32x16_10_c: 2173
ff_vvc_alf_filter_chroma_32x16_10_avx2: 408
ff_vvc_alf_filter_chroma_32x20_10_c: 2703
ff_vvc_alf_filter_chroma_32x20_10_avx2: 513
ff_vvc_alf_filter_chroma_32x24_10_c: 3245
ff_vvc_alf_filter_chroma_32x24_10_avx2: 612
ff_vvc_alf_filter_chroma_32x28_10_c: 3795
ff_vvc_alf_filter_chroma_32x28_10_avx2: 722
ff_vvc_alf_filter_chroma_32x32_10_c: 4339
ff_vvc_alf_filter_chroma_32x32_10_avx2: 820
Signed-off-by: Wu Jianhua <toqsxw@outlook.com>
2024-05-14 19:21:35 +08:00
Rémi Denis-Courmont
cdcb4b98b7
lavc/riscv: use ff_rv_vlen_least()
2024-05-13 18:36:07 +03:00
Rémi Denis-Courmont
247c5b2b97
lavu/riscv: add ff_rv_vlen_least()
...
This inline function checks that the vector length is at least a given
value. With this, most run-time VLEN checks can be optimised away.
2024-05-13 18:36:07 +03:00
Rémi Denis-Courmont
38e7b0ecf8
lavc/vp9dsp: fix indentation
2024-05-13 18:36:07 +03:00
James Almer
b450c44630
x86/flacdsp: remove unused parameters to pmacsdql macro
...
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-13 12:18:38 -03:00
James Almer
eb5733f38f
x86/flacdsp: add an SSE4 version of wasted33
...
flac_wasted_33_c: 214.1
flac_wasted_33_sse4: 103.2
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-13 12:18:10 -03:00
James Almer
5ba6f4e63e
checkasm/flacdsp: add a test for wasted33
...
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-13 12:18:10 -03:00
Ramiro Polla
d4d09c8e42
lavc/aarch64/fdct: add neon-optimized fdct for aarch64
...
The code is imported from libjpeg-turbo-3.0.1. The neon registers used
have been changed to avoid modifying v8-v15.
Reviewed-by: Martin Storsjö <martin@martin.st>
2024-05-13 14:54:10 +02:00
Ramiro Polla
27f6211c74
lavc/aarch64: fix include for cpu.h
2024-05-13 14:50:38 +02:00
Andreas Rheinhardt
b7b1a4e6c3
configure: Add missing ftr_parser->adts_header,mpeg4audio dependencies
...
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2024-05-13 14:32:21 +02:00
Andreas Rheinhardt
06d1840b56
configure, avcodec/Makefile: Add h264parse->h264data,golomb dependencies
...
Fixes standalone compilation of the dts2pts BSF.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2024-05-13 14:32:21 +02:00
Andreas Rheinhardt
4df43df6e1
avcodec/bsf/dts2pts: Fix shadowing
...
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2024-05-13 14:32:21 +02:00
Lynne
baf8651d56
aacdec: restore arm32 dequantization optimizations
...
Unintentionally removed as part of 03cf101645
2024-05-13 13:02:02 +02:00
Tomas Härdin
37db0454e4
lavc/speedhqdec: Obey AVDISCARD_ALL
2024-05-13 08:35:09 +02:00
Tomas Härdin
5b32685d77
lavc/speedhqdec: Add AV_CODEC_CAP_FRAME_THREADS
2024-05-13 08:35:09 +02:00
Michael Niedermayer
36126e4c14
avcodec/exr: Fix preview overflow
...
Fixes: CID1515456 Unintentional integer overflow
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:19 +02:00
Michael Niedermayer
73d6d9f129
avcodec/dovi_rpuenc: fix compaatibility
...
Fixes: a frequency
Found while reviewing: CID1596607
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:18 +02:00
Michael Niedermayer
46ad68084e
avcodec/dovi_rpuenc: initialize profile
...
Code is taken from dovi_rpudec
Fixes: CID1596604 Uninitialized scalar variable
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:18 +02:00
Michael Niedermayer
e9bb586543
avcodec/decode: decode_simple_internal() only implements audio and video
...
Fixes: CID1538861 Uninitialized scalar variable
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:18 +02:00
Michael Niedermayer
96c1162545
avcodec/fmvc: remove dead assignment
...
Fixes: CID1529220 Unused value
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:17 +02:00
Michael Niedermayer
fdaa6ae2b6
avcodec/h2645_sei: Remove dead checks
...
Fixes: CID1596534 Dereference after null check
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:17 +02:00
Michael Niedermayer
a68aa951b2
avcodec/h264_slice: Remove dead sps check
...
Fixes: CID1439574 Dereference after null check
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:17 +02:00
Brad Smith
950a7891a9
MAINTAINERS: add myself as *BSD maintainer
...
I try to help out with *BSD patches or build related issues where I can.
Signed-off-by: Brad Smith <brad@comstyle.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:16 +02:00
Michael Niedermayer
c2d897f356
avcodec/lpc: copy levenson coeffs only when they have been computed
...
Fixes: CID1473514 Uninitialized scalar variable
Sponsored-by: Sovereign Tech Fund
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:40:16 +02:00
Michael Niedermayer
c304784a86
avutil/tests/base64: Check with too short output array
...
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:26:57 +02:00
Michael Niedermayer
2d216566f2
libavutil/base64: Try not to write over the array end
...
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2024-05-13 03:26:57 +02:00
James Almer
0664cbd732
x86/flacdsp: add a SSE2 version of wasted32
...
flac_wasted_32_c: 851.3
flac_wasted_32_sse2: 41.3
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-12 17:24:08 -03:00
James Almer
5acec189af
checkasm/flacdsp: add a test for wasted32
...
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-12 17:24:08 -03:00
James Almer
1ba5287697
avcodec/flacdsp: split off wasted bit handling into dsp functions
...
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-12 17:23:58 -03:00
James Almer
c00c8679ed
x86/flacdsp: add a SSE4 version of lpc16
...
flac_lpc_16_13_c: 2841.3
flac_lpc_16_13_sse4: 2151.8
flac_lpc_16_16_c: 3382.8
flac_lpc_16_16_sse4: 2228.3
flac_lpc_16_29_c: 5800.3
flac_lpc_16_29_sse4: 3727.3
flac_lpc_16_32_c: 5972.8
flac_lpc_16_32_sse4: 4052.3
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-12 12:54:19 -03:00
James Almer
479d26cea2
checkasm/flacdsp: sanitize lpc arguments
...
Fixes signed integer overflows as reported by ubsan.
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-12 12:36:46 -03:00
James Almer
467d84a06d
checkasm/flacdsp: run lpc benchmarks with an unmodified buffer
...
Signed-off-by: James Almer <jamrial@gmail.com>
2024-05-12 12:36:46 -03:00
Yotam Ofek
02c032abcd
avcodec/aacenc_tns: remove unreachable code branch
...
the condition being tested was the same as the stop condition for the containing loop,
so inside the loop it would always test positive
2024-05-12 16:01:44 +02:00
Rémi Denis-Courmont
0d9591841b
lavc/ac3dsp: add R-V Zvbb extract_exponents
2024-05-11 11:38:49 +03:00
Rémi Denis-Courmont
5d8f62feb5
lavu/riscv: add Zvbb CPU capability detection
...
This requires Linux kernel version 6.8 or later.
2024-05-11 11:38:49 +03:00
Rémi Denis-Courmont
01c5f4ad9f
riscv: add Zvbb vector bit manipulation extension
2024-05-11 11:38:49 +03:00
sunyuechi
11f689317d
checkasm: Fix h264chroma test name
...
Signed-off-by: Rémi Denis-Courmont <remi@remlab.net>
2024-05-11 11:36:20 +03:00
Ramiro Polla
250c0defa2
checkasm: add test for fdct
...
Reviewed-by: Martin Storsjö <martin@martin.st>
Reviewed-by: Rémi Denis-Courmont <remi@remlab.net>
2024-05-11 10:28:59 +02:00
Ramiro Polla
b8af0809fb
libavcodec/mpegvideo_enc: fix multi-threaded motion estimation rounding for mpeg4
...
ff_init_me() was being called after ff_update_duplicate_context(),
which caused the propagation of the initialization to other thread
contexts to be delayed by one frame.
In the case of mpeg4 (or flipflop_rounding), this would make the
hpel_put functions differ between the first thread (which would be
correctly initialized) and the other threads (which would be stale
from the previous frame).
2024-05-11 10:13:58 +02:00
Ramiro Polla
713c6eba8d
libavcodec/motion_est: fix penalty_factor for b frames
...
In direct_search() and ff_estimate_b_frame_motion(), penalty_factor
would be used before being initialized in estimate_motion_b(). Also,
the initialization would happen more than once unnecessarily.
2024-05-11 09:38:34 +02:00
Haihao Xiang
ceace488ff
lavc/vaapi_encode_av1: insert HDR_CLL metadata if have
...
Only look for HDR_CLL on key frame on the output.
Signed-off-by: Haihao Xiang <haihao.xiang@intel.com>
2024-05-11 15:21:57 +08:00
Haihao Xiang
0bdf71ada7
lavc/vaapi_encode_av1: Insert HDR_MDCV metadata if have
...
Only look for HDR_MDVC on key frame on the output.
Signed-off-by: Haihao Xiang <haihao.xiang@intel.com>
2024-05-11 15:21:57 +08:00
Haihao Xiang
7f3ba6bbfa
lavc/vaapi_encode_av1: implement write_extra_header callback
...
This can be used to insert a metadata OBU to the stream later.
Signed-off-by: Haihao Xiang <haihao.xiang@intel.com>
2024-05-11 15:21:57 +08:00
Niklas Haas
9c6c4f3d47
avcodec/libaomenc: properly clean up image metadata
...
This does not get consumed by aom_codec_encode().
2024-05-11 01:25:15 +02:00
Rémi Denis-Courmont
5afe734b6d
lavu/riscv: remove bespoke assembler for MIN
...
This is no longer necessary as Zbb is now always explicitly required.
2024-05-10 18:59:06 +03:00
Rémi Denis-Courmont
6c6313f1b5
swscale/riscv: explicitly require Zbb for MIN
2024-05-10 18:59:06 +03:00
Rémi Denis-Courmont
c07af340ae
lavc/riscv: explicitly require Zbb for MIN
2024-05-10 18:59:06 +03:00
Rémi Denis-Courmont
89029baebd
lavu/riscv: allow requesting a second extension
2024-05-10 18:59:06 +03:00
sunyuechi
6e77af1c22
lavc/vp8dsp: R-V V put_epel v
...
C908:
vp8_put_epel4_v4_c: 11.0
vp8_put_epel4_v4_rvv_i32: 5.0
vp8_put_epel4_v6_c: 16.5
vp8_put_epel4_v6_rvv_i32: 6.2
vp8_put_epel8_v4_c: 43.7
vp8_put_epel8_v4_rvv_i32: 11.2
vp8_put_epel8_v6_c: 68.7
vp8_put_epel8_v6_rvv_i32: 13.2
vp8_put_epel16_v4_c: 92.5
vp8_put_epel16_v4_rvv_i32: 13.7
vp8_put_epel16_v6_c: 135.7
vp8_put_epel16_v6_rvv_i32: 16.5
Signed-off-by: Rémi Denis-Courmont <remi@remlab.net>
2024-05-10 18:41:13 +03:00
