diff options
author | Mark Reid <mindmark@gmail.com> | 2021-11-24 13:15:20 -0800 |
---|---|---|
committer | James Almer <jamrial@gmail.com> | 2022-01-11 16:33:17 -0300 |
commit | 9e445a5be2dca30a1f1103c73440648ccf5af9b1 (patch) | |
tree | 400817a50debefa499ca5b7445c4596dc0724444 /libswscale/x86/swscale.c | |
parent | 4b053b8db18eb0610b62a2c40d0327ae53f2387c (diff) |
swscale/x86/output.asm: add x86-optimized planer gbr yuv2anyX functions
changes since v2:
* fixed label
changes since v1:
* remove vex intruction on sse4 path
* some load/pack marcos use less intructions
* fixed some typos
yuv2gbrp_full_X_4_512_c: 12757.6
yuv2gbrp_full_X_4_512_sse2: 8946.6
yuv2gbrp_full_X_4_512_sse4: 5138.6
yuv2gbrp_full_X_4_512_avx2: 3889.6
yuv2gbrap_full_X_4_512_c: 15368.6
yuv2gbrap_full_X_4_512_sse2: 11916.1
yuv2gbrap_full_X_4_512_sse4: 6294.6
yuv2gbrap_full_X_4_512_avx2: 3477.1
yuv2gbrp9be_full_X_4_512_c: 14381.6
yuv2gbrp9be_full_X_4_512_sse2: 9139.1
yuv2gbrp9be_full_X_4_512_sse4: 5150.1
yuv2gbrp9be_full_X_4_512_avx2: 2834.6
yuv2gbrp9le_full_X_4_512_c: 12990.1
yuv2gbrp9le_full_X_4_512_sse2: 9118.1
yuv2gbrp9le_full_X_4_512_sse4: 5132.1
yuv2gbrp9le_full_X_4_512_avx2: 2833.1
yuv2gbrp10be_full_X_4_512_c: 14401.6
yuv2gbrp10be_full_X_4_512_sse2: 9133.1
yuv2gbrp10be_full_X_4_512_sse4: 5126.1
yuv2gbrp10be_full_X_4_512_avx2: 2837.6
yuv2gbrp10le_full_X_4_512_c: 12718.1
yuv2gbrp10le_full_X_4_512_sse2: 9106.1
yuv2gbrp10le_full_X_4_512_sse4: 5120.1
yuv2gbrp10le_full_X_4_512_avx2: 2826.1
yuv2gbrap10be_full_X_4_512_c: 18535.6
yuv2gbrap10be_full_X_4_512_sse2: 33617.6
yuv2gbrap10be_full_X_4_512_sse4: 6264.1
yuv2gbrap10be_full_X_4_512_avx2: 3422.1
yuv2gbrap10le_full_X_4_512_c: 16724.1
yuv2gbrap10le_full_X_4_512_sse2: 11787.1
yuv2gbrap10le_full_X_4_512_sse4: 6282.1
yuv2gbrap10le_full_X_4_512_avx2: 3441.6
yuv2gbrp12be_full_X_4_512_c: 13723.6
yuv2gbrp12be_full_X_4_512_sse2: 9128.1
yuv2gbrp12be_full_X_4_512_sse4: 7997.6
yuv2gbrp12be_full_X_4_512_avx2: 2844.1
yuv2gbrp12le_full_X_4_512_c: 12257.1
yuv2gbrp12le_full_X_4_512_sse2: 9107.6
yuv2gbrp12le_full_X_4_512_sse4: 5142.6
yuv2gbrp12le_full_X_4_512_avx2: 2837.6
yuv2gbrap12be_full_X_4_512_c: 18511.1
yuv2gbrap12be_full_X_4_512_sse2: 12156.6
yuv2gbrap12be_full_X_4_512_sse4: 6251.1
yuv2gbrap12be_full_X_4_512_avx2: 3444.6
yuv2gbrap12le_full_X_4_512_c: 16687.1
yuv2gbrap12le_full_X_4_512_sse2: 11785.1
yuv2gbrap12le_full_X_4_512_sse4: 6243.6
yuv2gbrap12le_full_X_4_512_avx2: 3446.1
yuv2gbrp14be_full_X_4_512_c: 13690.6
yuv2gbrp14be_full_X_4_512_sse2: 9120.6
yuv2gbrp14be_full_X_4_512_sse4: 5138.1
yuv2gbrp14be_full_X_4_512_avx2: 2843.1
yuv2gbrp14le_full_X_4_512_c: 14995.6
yuv2gbrp14le_full_X_4_512_sse2: 9119.1
yuv2gbrp14le_full_X_4_512_sse4: 5126.1
yuv2gbrp14le_full_X_4_512_avx2: 2843.1
yuv2gbrp16be_full_X_4_512_c: 12367.1
yuv2gbrp16be_full_X_4_512_sse2: 8233.6
yuv2gbrp16be_full_X_4_512_sse4: 4820.1
yuv2gbrp16be_full_X_4_512_avx2: 2666.6
yuv2gbrp16le_full_X_4_512_c: 10904.1
yuv2gbrp16le_full_X_4_512_sse2: 8214.1
yuv2gbrp16le_full_X_4_512_sse4: 4824.1
yuv2gbrp16le_full_X_4_512_avx2: 2629.1
yuv2gbrap16be_full_X_4_512_c: 26569.6
yuv2gbrap16be_full_X_4_512_sse2: 10884.1
yuv2gbrap16be_full_X_4_512_sse4: 5488.1
yuv2gbrap16be_full_X_4_512_avx2: 3272.1
yuv2gbrap16le_full_X_4_512_c: 14010.1
yuv2gbrap16le_full_X_4_512_sse2: 10562.1
yuv2gbrap16le_full_X_4_512_sse4: 5463.6
yuv2gbrap16le_full_X_4_512_avx2: 3255.1
yuv2gbrpf32be_full_X_4_512_c: 14524.1
yuv2gbrpf32be_full_X_4_512_sse2: 8552.6
yuv2gbrpf32be_full_X_4_512_sse4: 4636.1
yuv2gbrpf32be_full_X_4_512_avx2: 2474.6
yuv2gbrpf32le_full_X_4_512_c: 13060.6
yuv2gbrpf32le_full_X_4_512_sse2: 9682.6
yuv2gbrpf32le_full_X_4_512_sse4: 4298.1
yuv2gbrpf32le_full_X_4_512_avx2: 2453.1
yuv2gbrapf32be_full_X_4_512_c: 18629.6
yuv2gbrapf32be_full_X_4_512_sse2: 11363.1
yuv2gbrapf32be_full_X_4_512_sse4: 15201.6
yuv2gbrapf32be_full_X_4_512_avx2: 3727.1
yuv2gbrapf32le_full_X_4_512_c: 16677.6
yuv2gbrapf32le_full_X_4_512_sse2: 10221.6
yuv2gbrapf32le_full_X_4_512_sse4: 5693.6
yuv2gbrapf32le_full_X_4_512_avx2: 3656.6
Reviewed-by: Paul B Mahol <onemda@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
Diffstat (limited to 'libswscale/x86/swscale.c')
-rw-r--r-- | libswscale/x86/swscale.c | 98 |
1 files changed, 98 insertions, 0 deletions
diff --git a/libswscale/x86/swscale.c b/libswscale/x86/swscale.c index fdc93866a6..d5a467da0e 100644 --- a/libswscale/x86/swscale.c +++ b/libswscale/x86/swscale.c @@ -353,6 +353,43 @@ void ff_yuv2 ## fmt ## cX_ ## opt(enum AVPixelFormat format, const uint8_t *dith YUV2NV_DECL(nv12, avx2); YUV2NV_DECL(nv21, avx2); + +#define YUV2GBRP_FN_DECL(fmt, opt) \ +void ff_yuv2##fmt##_full_X_ ##opt(SwsContext *c, const int16_t *lumFilter, \ + const int16_t **lumSrcx, int lumFilterSize, \ + const int16_t *chrFilter, const int16_t **chrUSrcx, \ + const int16_t **chrVSrcx, int chrFilterSize, \ + const int16_t **alpSrcx, uint8_t **dest, \ + int dstW, int y) + +#define YUV2GBRP_DECL(opt) \ +YUV2GBRP_FN_DECL(gbrp, opt); \ +YUV2GBRP_FN_DECL(gbrap, opt); \ +YUV2GBRP_FN_DECL(gbrp9le, opt); \ +YUV2GBRP_FN_DECL(gbrp10le, opt); \ +YUV2GBRP_FN_DECL(gbrap10le, opt); \ +YUV2GBRP_FN_DECL(gbrp12le, opt); \ +YUV2GBRP_FN_DECL(gbrap12le, opt); \ +YUV2GBRP_FN_DECL(gbrp14le, opt); \ +YUV2GBRP_FN_DECL(gbrp16le, opt); \ +YUV2GBRP_FN_DECL(gbrap16le, opt); \ +YUV2GBRP_FN_DECL(gbrpf32le, opt); \ +YUV2GBRP_FN_DECL(gbrapf32le, opt); \ +YUV2GBRP_FN_DECL(gbrp9be, opt); \ +YUV2GBRP_FN_DECL(gbrp10be, opt); \ +YUV2GBRP_FN_DECL(gbrap10be, opt); \ +YUV2GBRP_FN_DECL(gbrp12be, opt); \ +YUV2GBRP_FN_DECL(gbrap12be, opt); \ +YUV2GBRP_FN_DECL(gbrp14be, opt); \ +YUV2GBRP_FN_DECL(gbrp16be, opt); \ +YUV2GBRP_FN_DECL(gbrap16be, opt); \ +YUV2GBRP_FN_DECL(gbrpf32be, opt); \ +YUV2GBRP_FN_DECL(gbrapf32be, opt); + +YUV2GBRP_DECL(sse2); +YUV2GBRP_DECL(sse4); +YUV2GBRP_DECL(avx2); + #endif av_cold void ff_sws_init_swscale_x86(SwsContext *c) @@ -601,5 +638,66 @@ switch(c->dstBpc){ \ break; } } + + if(c->flags & SWS_FULL_CHR_H_INT) { + + /* yuv2gbrp uses the SwsContext for yuv coefficients + if struct offsets change the asm needs to be updated too */ + av_assert0(offsetof(SwsContext, yuv2rgb_y_offset) == 40292); + +#define YUV2ANYX_FUNC_CASE(fmt, name, opt) \ + case fmt: \ + c->yuv2anyX = ff_yuv2##name##_full_X_##opt; \ + break; + +#define YUV2ANYX_GBRAP_CASES(opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP, gbrp, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAP, gbrap, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP9LE, gbrp9le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP10LE, gbrp10le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAP10LE, gbrap10le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP12LE, gbrp12le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAP12LE, gbrap12le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP14LE, gbrp14le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP16LE, gbrp16le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAP16LE, gbrap16le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRPF32LE, gbrpf32le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAPF32LE, gbrapf32le, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP9BE, gbrp9be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP10BE, gbrp10be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAP10BE, gbrap10be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP12BE, gbrp12be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAP12BE, gbrap12be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP14BE, gbrp14be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRP16BE, gbrp16be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAP16BE, gbrap16be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRPF32BE, gbrpf32be, opt) \ + YUV2ANYX_FUNC_CASE(AV_PIX_FMT_GBRAPF32BE, gbrapf32be, opt) + + if (EXTERNAL_SSE2(cpu_flags)) { + switch (c->dstFormat) { + YUV2ANYX_GBRAP_CASES(sse2) + default: + break; + } + } + + if (EXTERNAL_SSE4(cpu_flags)) { + switch (c->dstFormat) { + YUV2ANYX_GBRAP_CASES(sse4) + default: + break; + } + } + + if (EXTERNAL_AVX2_FAST(cpu_flags)) { + switch (c->dstFormat) { + YUV2ANYX_GBRAP_CASES(avx2) + default: + break; + } + } + } + #endif } |