diff options
| author | Logan Lyu <Logan.Lyu@myais.com.cn> | 2023-11-11 17:54:35 +0800 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2023-12-01 21:25:39 +0200 |
| commit | 216275bd8098fc4a08fd4c38191c8c217a6b897a (patch) | |
| tree | 40b45a560f1c29bb9520f83420ed474ab8f9904a /libavcodec/aarch64/hevcdsp_init_aarch64.c | |
| parent | 40cf4a5ca3ce1bdb2623ac0f8a956c27203540ea (diff) | |
| download | ffmpeg-216275bd8098fc4a08fd4c38191c8c217a6b897a.tar.gz | |
lavc/aarch64: new optimization for 8-bit hevc_epel_bi_h
put_hevc_epel_bi_h4_8_c: 96.0
put_hevc_epel_bi_h4_8_neon: 36.3
put_hevc_epel_bi_h6_8_c: 288.3
put_hevc_epel_bi_h6_8_neon: 59.3
put_hevc_epel_bi_h8_8_c: 358.5
put_hevc_epel_bi_h8_8_neon: 61.5
put_hevc_epel_bi_h12_8_c: 759.8
put_hevc_epel_bi_h12_8_neon: 159.5
put_hevc_epel_bi_h16_8_c: 1307.0
put_hevc_epel_bi_h16_8_neon: 182.0
put_hevc_epel_bi_h24_8_c: 2778.3
put_hevc_epel_bi_h24_8_neon: 430.5
put_hevc_epel_bi_h32_8_c: 4952.3
put_hevc_epel_bi_h32_8_neon: 679.5
put_hevc_epel_bi_h48_8_c: 11803.3
put_hevc_epel_bi_h48_8_neon: 1443.5
put_hevc_epel_bi_h64_8_c: 20654.8
put_hevc_epel_bi_h64_8_neon: 2737.0
put_hevc_qpel_bi_h4_8_c: 140.0
put_hevc_qpel_bi_h4_8_neon: 111.5
put_hevc_qpel_bi_h6_8_c: 318.0
put_hevc_qpel_bi_h6_8_neon: 85.8
put_hevc_qpel_bi_h8_8_c: 536.5
put_hevc_qpel_bi_h8_8_neon: 95.3
put_hevc_qpel_bi_h12_8_c: 1188.5
put_hevc_qpel_bi_h12_8_neon: 291.3
put_hevc_qpel_bi_h16_8_c: 2064.3
put_hevc_qpel_bi_h16_8_neon: 365.3
put_hevc_qpel_bi_h24_8_c: 4757.5
put_hevc_qpel_bi_h24_8_neon: 1010.0
put_hevc_qpel_bi_h32_8_c: 8351.8
put_hevc_qpel_bi_h32_8_neon: 2917.8
put_hevc_qpel_bi_h48_8_c: 19299.8
put_hevc_qpel_bi_h48_8_neon: 2976.8
put_hevc_qpel_bi_h64_8_c: 34182.5
put_hevc_qpel_bi_h64_8_neon: 5236.3
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 | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index beb69dc395..f5d9a72ed2 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -160,6 +160,10 @@ 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_bi_h, (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),); @@ -329,6 +333,7 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) 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_epel_bi, 0, 1, epel_bi_h,); 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,); |