diff options
| author | James Almer <jamrial@gmail.com> | 2015-02-01 15:01:36 -0300 |
|---|---|---|
| committer | James Almer <jamrial@gmail.com> | 2015-02-01 20:22:35 -0300 |
| commit | fa3eccb4f9f3ecc9e2bb3c5924c2aa343b808076 (patch) | |
| tree | 3cb8dd1f22abc025929deedb3cd90c672d68ad53 /libavcodec/hevcdsp.h | |
| parent | a1684311b3de0766932c42b1ffdd59823d786bc2 (diff) | |
| download | ffmpeg-fa3eccb4f9f3ecc9e2bb3c5924c2aa343b808076.tar.gz | |
x86/hevc: add ff_hevc_sao_band_filter_{8,10,12}_{sse2,avx,avx2}
Original x86 intrinsics code and initial 8bit yasm port by Pierre-Edouard Lepere.
10/12bit yasm ports, refactoring and optimizations by James Almer
Benchmarks of BQTerrace_1920x1080_60_qp22.bin with an Intel Core i5-4200U
width 32
40338 decicycles in sao_band_filter_0_8, 2048 runs, 0 skips
8056 decicycles in ff_hevc_sao_band_filter_8_32_sse2, 2048 runs, 0 skips
7458 decicycles in ff_hevc_sao_band_filter_8_32_avx, 2048 runs, 0 skips
4504 decicycles in ff_hevc_sao_band_filter_8_32_avx2, 2048 runs, 0 skips
width 64
136046 decicycles in sao_band_filter_0_8, 16384 runs, 0 skips
28576 decicycles in ff_hevc_sao_band_filter_8_32_sse2, 16384 runs, 0 skips
26707 decicycles in ff_hevc_sao_band_filter_8_32_avx, 16384 runs, 0 skips
14387 decicycles in ff_hevc_sao_band_filter_8_32_avx2, 16384 runs, 0 skips
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
Diffstat (limited to 'libavcodec/hevcdsp.h')
| -rw-r--r-- | libavcodec/hevcdsp.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/libavcodec/hevcdsp.h b/libavcodec/hevcdsp.h index a798fb1dc4..6fb161b462 100644 --- a/libavcodec/hevcdsp.h +++ b/libavcodec/hevcdsp.h @@ -58,8 +58,8 @@ typedef struct HEVCDSPContext { void (*idct_dc[4])(int16_t *coeffs); - void (*sao_band_filter)(uint8_t *_dst, uint8_t *_src, ptrdiff_t _stride_dst, ptrdiff_t _stride_src, - int16_t *sao_offset_val, int sao_left_class, int width, int height); + void (*sao_band_filter[5])(uint8_t *_dst, uint8_t *_src, ptrdiff_t _stride_dst, ptrdiff_t _stride_src, + int16_t *sao_offset_val, int sao_left_class, int width, int height); void (*sao_edge_filter[2])(uint8_t *_dst, uint8_t *_src, ptrdiff_t _stride_dst, ptrdiff_t _stride_src, struct SAOParams *sao, int *borders, int _width, |