MrBesen
/
ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

libswscale/x86/rgb2rgb: add shuffle_bytes avx2 

Performance data(Less is better):
    shuffle_bytes_ssse3   3.64654
    shuffle_bytes_avx2    0.94288

Signed-off-by: Wu Jianhua <jianhua.wu@intel.com>
This commit is contained in:
Wu Jianhua 2021-09-30 09:56:09 +08:00 committed by Paul B Mahol
parent 767f162432
commit 2c734a8496
2 changed files with 27 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
libswscale/x86/rgb2rgb.c
View File

@ -146,6 +146,12 @@ void ff_shuffle_bytes_3012_ssse3(const uint8_t *src, uint8_t *dst, int src_size)
void ff_shuffle_bytes_3210_ssse3(const uint8_t *src, uint8_t *dst, int src_size);
#if ARCH_X86_64
void ff_shuffle_bytes_2103_avx2(const uint8_t *src, uint8_t *dst, int src_size);
void ff_shuffle_bytes_0321_avx2(const uint8_t *src, uint8_t *dst, int src_size);
void ff_shuffle_bytes_1230_avx2(const uint8_t *src, uint8_t *dst, int src_size);
void ff_shuffle_bytes_3012_avx2(const uint8_t *src, uint8_t *dst, int src_size);
void ff_shuffle_bytes_3210_avx2(const uint8_t *src, uint8_t *dst, int src_size);
void ff_uyvytoyuv422_sse2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
const uint8_t *src, int width, int height,
int lumStride, int chromStride, int srcStride);
@ -186,9 +192,16 @@ av_cold void rgb2rgb_init_x86(void)
shuffle_bytes_3012 = ff_shuffle_bytes_3012_ssse3;
shuffle_bytes_3210 = ff_shuffle_bytes_3210_ssse3;
}
if (EXTERNAL_AVX(cpu_flags)) {
#if ARCH_X86_64
uyvytoyuv422 = ff_uyvytoyuv422_avx;
#endif
if (EXTERNAL_AVX2_FAST(cpu_flags)) {
shuffle_bytes_0321 = ff_shuffle_bytes_0321_avx2;
shuffle_bytes_2103 = ff_shuffle_bytes_2103_avx2;
shuffle_bytes_1230 = ff_shuffle_bytes_1230_avx2;
shuffle_bytes_3012 = ff_shuffle_bytes_3012_avx2;
shuffle_bytes_3210 = ff_shuffle_bytes_3210_avx2;
}
if (EXTERNAL_AVX(cpu_flags)) {
uyvytoyuv422 = ff_uyvytoyuv422_avx;
}
#endif
}

11
libswscale/x86/rgb_2_rgb.asm
View File

@ -159,6 +159,17 @@ SHUFFLE_BYTES 1, 2, 3, 0
SHUFFLE_BYTES 3, 0, 1, 2
SHUFFLE_BYTES 3, 2, 1, 0
%if ARCH_X86_64
%if HAVE_AVX2_EXTERNAL
INIT_YMM avx2
SHUFFLE_BYTES 2, 1, 0, 3
SHUFFLE_BYTES 0, 3, 2, 1
SHUFFLE_BYTES 1, 2, 3, 0
SHUFFLE_BYTES 3, 0, 1, 2
SHUFFLE_BYTES 3, 2, 1, 0
%endif
%endif
;-----------------------------------------------------------------------------------------------
; uyvytoyuv422(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
; const uint8_t *src, int width, int height,