diff options
| author | Logan Lyu <Logan.Lyu@myais.com.cn> | 2023-11-05 16:33:17 +0800 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2023-12-01 21:25:39 +0200 |
| commit | 40cf4a5ca3ce1bdb2623ac0f8a956c27203540ea (patch) | |
| tree | 82e923b80deafab780e475890816a364ae2aa038 /libavcodec/aarch64/hevcdsp_init_aarch64.c | |
| parent | d0ec826077c49f4cbf286621771a4a43a9bf57b8 (diff) | |
| download | ffmpeg-40cf4a5ca3ce1bdb2623ac0f8a956c27203540ea.tar.gz | |
lavc/aarch64: new optimization for 8-bit hevc_pel_bi_pixels
put_hevc_pel_bi_pixels4_8_c: 54.7
put_hevc_pel_bi_pixels4_8_neon: 43.0
put_hevc_pel_bi_pixels6_8_c: 94.7
put_hevc_pel_bi_pixels6_8_neon: 37.0
put_hevc_pel_bi_pixels8_8_c: 171.0
put_hevc_pel_bi_pixels8_8_neon: 24.0
put_hevc_pel_bi_pixels12_8_c: 354.0
put_hevc_pel_bi_pixels12_8_neon: 68.7
put_hevc_pel_bi_pixels16_8_c: 588.2
put_hevc_pel_bi_pixels16_8_neon: 77.5
put_hevc_pel_bi_pixels24_8_c: 1670.7
put_hevc_pel_bi_pixels24_8_neon: 173.0
put_hevc_pel_bi_pixels32_8_c: 2267.7
put_hevc_pel_bi_pixels32_8_neon: 281.2
put_hevc_pel_bi_pixels48_8_c: 5787.5
put_hevc_pel_bi_pixels48_8_neon: 673.5
put_hevc_pel_bi_pixels64_8_c: 9897.0
put_hevc_pel_bi_pixels64_8_neon: 1159.5
Co-Authored-By: J. Dekker <jdek@itanimul.li>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/aarch64/hevcdsp_init_aarch64.c')
| -rw-r--r-- | libavcodec/aarch64/hevcdsp_init_aarch64.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index c51488275c..beb69dc395 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -156,6 +156,10 @@ NEON8_FNPROTO(pel_pixels, (int16_t *dst, const uint8_t *src, ptrdiff_t srcstride, int height, intptr_t mx, intptr_t my, int width),); +NEON8_FNPROTO(pel_bi_pixels, (uint8_t *dst, ptrdiff_t dststride, + const uint8_t *_src, ptrdiff_t _srcstride, const int16_t *src2, + int height, intptr_t mx, intptr_t my, int width),); + NEON8_FNPROTO(epel_v, (int16_t *dst, const uint8_t *src, ptrdiff_t srcstride, int height, intptr_t mx, intptr_t my, int width),); @@ -324,6 +328,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) NEON8_FNASSIGN(c->put_hevc_epel, 1, 0, epel_v,); NEON8_FNASSIGN(c->put_hevc_qpel, 0, 0, pel_pixels,); NEON8_FNASSIGN(c->put_hevc_qpel, 1, 0, qpel_v,); + NEON8_FNASSIGN(c->put_hevc_epel_bi, 0, 0, pel_bi_pixels,); + NEON8_FNASSIGN(c->put_hevc_qpel_bi, 0, 0, pel_bi_pixels,); NEON8_FNASSIGN(c->put_hevc_epel_uni, 0, 0, pel_uni_pixels,); NEON8_FNASSIGN(c->put_hevc_epel_uni, 1, 0, epel_uni_v,); NEON8_FNASSIGN(c->put_hevc_qpel_uni, 0, 0, pel_uni_pixels,); |