diff options
| author | James Darnley <james.darnley@gmail.com> | 2016-01-15 18:30:03 +0000 |
|---|---|---|
| committer | James Darnley <james.darnley@gmail.com> | 2016-01-17 16:03:43 +0100 |
| commit | 2cba1825f70c301f5513a799302f755967680651 (patch) | |
| tree | c39ebf1ac76c35ab1852cd4555fa155b78d77f4d /libavcodec/x86/v210enc_init.c | |
| parent | 3836f404a8c0ffd7c565260434768ef4ebba85a7 (diff) | |
| download | ffmpeg-2cba1825f70c301f5513a799302f755967680651.tar.gz | |
avcodec/v210: add avx2 version of the 10-bit line encoder
Around 25% faster than the ssse3 version.
Diffstat (limited to 'libavcodec/x86/v210enc_init.c')
| -rw-r--r-- | libavcodec/x86/v210enc_init.c | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/libavcodec/x86/v210enc_init.c b/libavcodec/x86/v210enc_init.c index be6698c512..ee48e80538 100644 --- a/libavcodec/x86/v210enc_init.c +++ b/libavcodec/x86/v210enc_init.c @@ -29,6 +29,9 @@ void ff_v210_planar_pack_8_avx2(const uint8_t *y, const uint8_t *u, void ff_v210_planar_pack_10_ssse3(const uint16_t *y, const uint16_t *u, const uint16_t *v, uint8_t *dst, ptrdiff_t width); +void ff_v210_planar_pack_10_avx2(const uint16_t *y, const uint16_t *u, + const uint16_t *v, uint8_t *dst, + ptrdiff_t width); av_cold void ff_v210enc_init_x86(V210EncContext *s) { @@ -44,6 +47,7 @@ av_cold void ff_v210enc_init_x86(V210EncContext *s) if (EXTERNAL_AVX2(cpu_flags)) { s->pack_line_8 = ff_v210_planar_pack_8_avx2; + s->pack_line_10 = ff_v210_planar_pack_10_avx2; s->sample_factor = 2; } } |