diff options
| author | Martin Storsjö <martin@martin.st> | 2024-03-20 12:18:07 +0200 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2024-03-26 09:03:18 +0200 |
| commit | ad01d06f919f25147f857efc4f143b5469e2f92f (patch) | |
| tree | 956c81dd7a88c6f3b85745b832070a5276bdbca5 /libavcodec/aarch64/hevcdsp_init_aarch64.c | |
| parent | de23b384fd7c098132ba1745342cb0d3ed1a7af6 (diff) | |
| download | ffmpeg-ad01d06f919f25147f857efc4f143b5469e2f92f.tar.gz | |
aarch64: hevc: Implement a neon version of hevc_qpel_uni_w_h*_8
AWS Graviton 3:
put_hevc_qpel_uni_w_h4_8_c: 159.0
put_hevc_qpel_uni_w_h4_8_neon: 64.2
put_hevc_qpel_uni_w_h4_8_i8mm: 40.0
put_hevc_qpel_uni_w_h6_8_c: 344.7
put_hevc_qpel_uni_w_h6_8_neon: 114.5
put_hevc_qpel_uni_w_h6_8_i8mm: 82.0
put_hevc_qpel_uni_w_h8_8_c: 596.2
put_hevc_qpel_uni_w_h8_8_neon: 132.2
put_hevc_qpel_uni_w_h8_8_i8mm: 106.0
put_hevc_qpel_uni_w_h12_8_c: 1325.0
put_hevc_qpel_uni_w_h12_8_neon: 299.0
put_hevc_qpel_uni_w_h12_8_i8mm: 211.5
put_hevc_qpel_uni_w_h16_8_c: 2300.0
put_hevc_qpel_uni_w_h16_8_neon: 422.0
put_hevc_qpel_uni_w_h16_8_i8mm: 286.2
put_hevc_qpel_uni_w_h24_8_c: 5059.0
put_hevc_qpel_uni_w_h24_8_neon: 912.2
put_hevc_qpel_uni_w_h24_8_i8mm: 664.2
put_hevc_qpel_uni_w_h32_8_c: 9198.2
put_hevc_qpel_uni_w_h32_8_neon: 1638.2
put_hevc_qpel_uni_w_h32_8_i8mm: 1033.7
put_hevc_qpel_uni_w_h48_8_c: 20754.7
put_hevc_qpel_uni_w_h48_8_neon: 3633.7
put_hevc_qpel_uni_w_h48_8_i8mm: 2300.7
put_hevc_qpel_uni_w_h64_8_c: 36854.7
put_hevc_qpel_uni_w_h64_8_neon: 6435.7
put_hevc_qpel_uni_w_h64_8_i8mm: 4039.2
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 | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index 6110a360d8..ea0d26c019 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -280,6 +280,11 @@ NEON8_FNPROTO(qpel_uni_hv, (uint8_t *dst, ptrdiff_t dststride, NEON8_FNPROTO(qpel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride, const uint8_t *_src, ptrdiff_t _srcstride, int height, int denom, int wx, int ox, + intptr_t mx, intptr_t my, int width),); + +NEON8_FNPROTO(qpel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride, + const uint8_t *_src, ptrdiff_t _srcstride, + int height, int denom, int wx, int ox, intptr_t mx, intptr_t my, int width), _i8mm); NEON8_FNPROTO(epel_uni_w_hv, (uint8_t *_dst, ptrdiff_t _dststride, @@ -429,6 +434,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 1, 1, epel_uni_w_hv,); NEON8_FNASSIGN(c->put_hevc_epel_bi, 1, 1, epel_bi_hv,); + NEON8_FNASSIGN_SHARED_32(c->put_hevc_qpel_uni_w, 0, 1, qpel_uni_w_h,); + if (have_i8mm(cpu_flags)) { NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm); NEON8_FNASSIGN(c->put_hevc_epel, 1, 1, epel_hv, _i8mm); |