diff options
| author | Logan Lyu <Logan.Lyu@myais.com.cn> | 2023-05-28 10:30:28 +0800 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2023-07-14 21:19:12 +0300 |
| commit | d48c89701c0cdad1074a797e8bfc214d8b49123b (patch) | |
| tree | 53c9b30d6d832631aeab17cc989a982645683675 /libavcodec/aarch64/hevcdsp_init_aarch64.c | |
| parent | 668eb4c00e4df76ec8921cfea7c0c7574f605d8f (diff) | |
| download | ffmpeg-d48c89701c0cdad1074a797e8bfc214d8b49123b.tar.gz | |
lavc/aarch64: new optimization for 8-bit hevc_epel_h
put_hevc_epel_h4_8_c: 67.1
put_hevc_epel_h4_8_i8mm: 21.1
put_hevc_epel_h6_8_c: 147.1
put_hevc_epel_h6_8_i8mm: 45.1
put_hevc_epel_h8_8_c: 237.4
put_hevc_epel_h8_8_i8mm: 72.1
put_hevc_epel_h12_8_c: 527.4
put_hevc_epel_h12_8_i8mm: 115.4
put_hevc_epel_h16_8_c: 943.6
put_hevc_epel_h16_8_i8mm: 153.9
put_hevc_epel_h24_8_c: 2105.4
put_hevc_epel_h24_8_i8mm: 384.4
put_hevc_epel_h32_8_c: 3631.4
put_hevc_epel_h32_8_i8mm: 519.9
put_hevc_epel_h48_8_c: 8082.1
put_hevc_epel_h48_8_i8mm: 1110.4
put_hevc_epel_h64_8_c: 14400.6
put_hevc_epel_h64_8_i8mm: 2057.1
put_hevc_qpel_h4_8_c: 124.9
put_hevc_qpel_h4_8_neon: 43.1
put_hevc_qpel_h4_8_i8mm: 33.1
put_hevc_qpel_h6_8_c: 269.4
put_hevc_qpel_h6_8_neon: 90.6
put_hevc_qpel_h6_8_i8mm: 61.4
put_hevc_qpel_h8_8_c: 477.6
put_hevc_qpel_h8_8_neon: 82.1
put_hevc_qpel_h8_8_i8mm: 99.9
put_hevc_qpel_h12_8_c: 1062.4
put_hevc_qpel_h12_8_neon: 226.9
put_hevc_qpel_h12_8_i8mm: 170.9
put_hevc_qpel_h16_8_c: 1880.6
put_hevc_qpel_h16_8_neon: 302.9
put_hevc_qpel_h16_8_i8mm: 251.4
put_hevc_qpel_h24_8_c: 4221.9
put_hevc_qpel_h24_8_neon: 893.9
put_hevc_qpel_h24_8_i8mm: 626.1
put_hevc_qpel_h32_8_c: 7437.6
put_hevc_qpel_h32_8_neon: 1189.9
put_hevc_qpel_h32_8_i8mm: 959.1
put_hevc_qpel_h48_8_c: 16838.4
put_hevc_qpel_h48_8_neon: 2727.9
put_hevc_qpel_h48_8_i8mm: 2163.9
put_hevc_qpel_h64_8_c: 29982.1
put_hevc_qpel_h64_8_neon: 4777.6
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 4a260e1d9a..b448d755b9 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -171,6 +171,10 @@ NEON8_FNPROTO_PARTIAL_4(qpel_uni_w_v, (uint8_t *_dst, ptrdiff_t _dststride, int height, int denom, int wx, int ox, intptr_t mx, intptr_t my, int width),); +NEON8_FNPROTO(epel_h, (int16_t *dst, + const uint8_t *_src, ptrdiff_t _srcstride, + int height, intptr_t mx, intptr_t my, int width), _i8mm); + NEON8_FNPROTO(epel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride, const uint8_t *_src, ptrdiff_t _srcstride, int height, int denom, int wx, int ox, @@ -283,6 +287,7 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) NEON8_FNASSIGN_PARTIAL_4(c->put_hevc_qpel_uni_w, 1, 0, qpel_uni_w_v,); if (have_i8mm(cpu_flags)) { + NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm); NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 0, 1, epel_uni_w_h ,_i8mm); NEON8_FNASSIGN(c->put_hevc_qpel, 0, 1, qpel_h, _i8mm); NEON8_FNASSIGN(c->put_hevc_qpel_uni_w, 0, 1, qpel_uni_w_h, _i8mm); |