diff options
| author | Zhao Zhili <zhilizhao@tencent.com> | 2024-09-11 21:40:59 +0800 |
|---|---|---|
| committer | Nuo Mi <nuomi2021@gmail.com> | 2024-09-14 16:36:34 +0800 |
| commit | 3f84d1d1fb75e4192c35664b4dd4741e8381b667 (patch) | |
| tree | 7a5f74c75873c303891c7959a858e77d37934524 /libavcodec/aarch64/vvc/dsp_init.c | |
| parent | 1be5a2374f224a1fc5e429aafe2ac8fc4efb548c (diff) | |
| download | ffmpeg-3f84d1d1fb75e4192c35664b4dd4741e8381b667.tar.gz | |
aarch64/vvc: Add avg
avg_8_2x2_c: 0.2 ( 1.00x)
avg_8_2x2_neon: 0.2 ( 1.00x)
avg_8_4x4_c: 0.2 ( 1.00x)
avg_8_4x4_neon: 0.2 ( 1.00x)
avg_8_8x8_c: 0.9 ( 1.00x)
avg_8_8x8_neon: 0.2 ( 5.29x)
avg_8_16x16_c: 3.7 ( 1.00x)
avg_8_16x16_neon: 0.7 ( 5.44x)
avg_8_32x32_c: 14.9 ( 1.00x)
avg_8_32x32_neon: 1.7 ( 8.91x)
avg_8_64x64_c: 59.7 ( 1.00x)
avg_8_64x64_neon: 6.9 ( 8.62x)
avg_8_128x128_c: 254.7 ( 1.00x)
avg_8_128x128_neon: 26.9 ( 9.46x)
avg_10_2x2_c: 0.2 ( 1.00x)
avg_10_2x2_neon: 0.2 ( 1.00x)
avg_10_4x4_c: 0.2 ( 1.00x)
avg_10_4x4_neon: 0.2 ( 1.00x)
avg_10_8x8_c: 0.9 ( 1.00x)
avg_10_8x8_neon: 0.2 ( 5.29x)
avg_10_16x16_c: 3.4 ( 1.00x)
avg_10_16x16_neon: 0.4 ( 8.06x)
avg_10_32x32_c: 13.9 ( 1.00x)
avg_10_32x32_neon: 1.9 ( 7.23x)
avg_10_64x64_c: 54.2 ( 1.00x)
avg_10_64x64_neon: 8.4 ( 6.43x)
avg_10_128x128_c: 232.4 ( 1.00x)
avg_10_128x128_neon: 30.9 ( 7.52x)
avg_12_2x2_c: 0.0 ( 0.00x)
avg_12_2x2_neon: 0.2 ( 0.00x)
avg_12_4x4_c: 0.4 ( 1.00x)
avg_12_4x4_neon: 0.2 ( 2.43x)
avg_12_8x8_c: 0.7 ( 1.00x)
avg_12_8x8_neon: 0.2 ( 3.86x)
avg_12_16x16_c: 3.7 ( 1.00x)
avg_12_16x16_neon: 0.4 ( 8.65x)
avg_12_32x32_c: 13.7 ( 1.00x)
avg_12_32x32_neon: 2.2 ( 6.29x)
avg_12_64x64_c: 53.9 ( 1.00x)
avg_12_64x64_neon: 7.7 ( 7.03x)
avg_12_128x128_c: 270.9 ( 1.00x)
avg_12_128x128_neon: 30.4 ( 8.90x)
Diffstat (limited to 'libavcodec/aarch64/vvc/dsp_init.c')
| -rw-r--r-- | libavcodec/aarch64/vvc/dsp_init.c | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/libavcodec/aarch64/vvc/dsp_init.c b/libavcodec/aarch64/vvc/dsp_init.c index 4867491620..ad767d17e2 100644 --- a/libavcodec/aarch64/vvc/dsp_init.c +++ b/libavcodec/aarch64/vvc/dsp_init.c @@ -42,6 +42,16 @@ int ff_vvc_sad_neon(const int16_t *src0, const int16_t *src1, int dx, int dy, const int block_w, const int block_h); +void ff_vvc_avg_8_neon(uint8_t *dst, ptrdiff_t dst_stride, + const int16_t *src0, const int16_t *src1, int width, + int height); +void ff_vvc_avg_10_neon(uint8_t *dst, ptrdiff_t dst_stride, + const int16_t *src0, const int16_t *src1, int width, + int height); +void ff_vvc_avg_12_neon(uint8_t *dst, ptrdiff_t dst_stride, + const int16_t *src0, const int16_t *src1, int width, + int height); + void ff_vvc_dsp_init_aarch64(VVCDSPContext *const c, const int bd) { int cpu_flags = av_get_cpu_flags(); @@ -112,6 +122,8 @@ void ff_vvc_dsp_init_aarch64(VVCDSPContext *const c, const int bd) c->inter.put_uni_w[0][5][0][0] = ff_vvc_put_pel_uni_w_pixels64_8_neon; c->inter.put_uni_w[0][6][0][0] = ff_vvc_put_pel_uni_w_pixels128_8_neon; + c->inter.avg = ff_vvc_avg_8_neon; + for (int i = 0; i < FF_ARRAY_ELEMS(c->sao.band_filter); i++) c->sao.band_filter[i] = ff_h26x_sao_band_filter_8x8_8_neon; c->sao.edge_filter[0] = ff_vvc_sao_edge_filter_8x8_8_neon; @@ -150,9 +162,13 @@ void ff_vvc_dsp_init_aarch64(VVCDSPContext *const c, const int bd) c->inter.put[1][6][1][1] = ff_vvc_put_epel_hv128_8_neon_i8mm; } } else if (bd == 10) { + c->inter.avg = ff_vvc_avg_10_neon; + c->alf.filter[LUMA] = alf_filter_luma_10_neon; c->alf.filter[CHROMA] = alf_filter_chroma_10_neon; } else if (bd == 12) { + c->inter.avg = ff_vvc_avg_12_neon; + c->alf.filter[LUMA] = alf_filter_luma_12_neon; c->alf.filter[CHROMA] = alf_filter_chroma_12_neon; } |