Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | libswscale/x86/yuv2yuvX: Removes unrolling for mmx and mmxext | Alan Kelly | 2021-04-01 |
| | | | | Signed-off-by: Michael Niedermayer <michael@niedermayer.cc> | ||
* | swscale/x86/yuv2yuvX: use the movsxdifnidn helper macro | James Almer | 2021-02-18 |
| | | | | | | Simplifies code Signed-off-by: James Almer <jamrial@gmail.com> | ||
* | swscale/x86/yuv2yuvX: use movq to load 8 bytes in all non-AVX2 functions | James Almer | 2021-02-18 |
| | | | | | | mova expands to movq on non-XMM functions Signed-off-by: James Almer <jamrial@gmail.com> | ||
* | swscale/x86/yuv2yuvX: use the SPLATW helper macro | James Almer | 2021-02-18 |
| | | | | | | Simplifies code Signed-off-by: James Almer <jamrial@gmail.com> | ||
* | swscale/x86/swscale: fix compilation with old yasm | James Almer | 2021-02-17 |
| | | | | | | Where AVX2 may not be supported. Signed-off-by: James Almer <jamrial@gmail.com> | ||
* | swscale: move yuv2yuvX_sse3 to yasm, unrolls main loop | Alan Kelly | 2021-02-17 |
And other small optimizations for ~20% speedup. |