[FFmpeg-cvslog] checkasm/sw_scale: hscale does not requires cpuflag test.

2022-08-18 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Fri Jul 15 17:01:31 2022 +0200| [da0a37bab7434ef485146ce8575c7948db1fe3e2] | committer: Anton Khirnov checkasm/sw_scale: hscale does not requires cpuflag test. This is done in ff_shuffle_filter_coefficients. Signed-off-by: Anton Khirnov > h

[FFmpeg-cvslog] libswscale: Enable hscale_avx2 for all input sizes.

2022-08-18 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Fri Jul 15 16:59:43 2022 +0200| [a38293e4448c9389e604af9858984361a5677a20] | committer: Anton Khirnov libswscale: Enable hscale_avx2 for all input sizes. ff_shuffle_filter_coefficients shuffles the tail as required. Signed-off-by: Anton Khirnov > h

[FFmpeg-cvslog] sws: allow avx2 hscale to process inputs of any size.

2022-08-18 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Tue Apr 26 10:00:02 2022 +0200| [a6724285fd45111436dd5242eab2c489182aa5c2] | committer: Anton Khirnov sws: allow avx2 hscale to process inputs of any size. The main loop processes blocks of 16 pixels. The tail processes blocks of size 4. Signed-off

[FFmpeg-cvslog] sws: Replace call to yuv2yuvX_mmx by yuv2yuvX_mmxext

2022-08-18 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Wed Aug 17 11:20:39 2022 +0200| [51a34e8525fea2bbc29b42831d7a17f34e8518d3] | committer: Andreas Rheinhardt sws: Replace call to yuv2yuvX_mmx by yuv2yuvX_mmxext Signed-off-by: Andreas Rheinhardt > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=com

[FFmpeg-cvslog] libswscale: Re-factor ff_shuffle_filter_coefficients.

2022-02-17 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Feb 17 11:03:52 2022 +0100| [e534d98af3bfdc2c926b15301404e2d85524a048] | committer: Michael Niedermayer libswscale: Re-factor ff_shuffle_filter_coefficients. Make the code more readable and follow the style guide. Signed-off-by: Michael Niedermayer

[FFmpeg-cvslog] libswscale: Check and propagate memory allocation errors from ff_shuffle_filter_coefficients.

2022-02-17 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Feb 17 11:03:21 2022 +0100| [f1a5414c97a594d6f1d011860753794681ec56c5] | committer: Michael Niedermayer libswscale: Check and propagate memory allocation errors from ff_shuffle_filter_coefficients. Signed-off-by: Michael Niedermayer > h

[FFmpeg-cvslog] libavutil/cpu: Add AV_CPU_FLAG_SLOW_GATHER.

2021-12-21 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Tue Dec 21 20:56:41 2021 +0100| [ffbab99f2c22be06ef3c564fd38320d40e48a2b5] | committer: James Almer libavutil/cpu: Add AV_CPU_FLAG_SLOW_GATHER. This flag is set on Haswell and earlier and all AMD cpus. > http://git.videolan.org/gitweb.cgi/ffmpeg.

[FFmpeg-cvslog] libswscale: Test AV_CPU_FLAG_SLOW_GATHER for hscale functions.

2021-12-21 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Mon Dec 20 15:45:45 2021 +0100| [eebe406c808e6061ee76e93a616537b5369dbf40] | committer: James Almer libswscale: Test AV_CPU_FLAG_SLOW_GATHER for hscale functions. This is instead of EXTERNAL_AVX2_FAST so that the avx2 hscale functions are only used where

[FFmpeg-cvslog] x86/scale_avx2: Change asm indent from 2 to 4 spaces.

2021-12-16 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Dec 16 17:27:10 2021 +0100| [9092e58c4469f5488f305fdb85e34e61bba7b04a] | committer: James Almer x86/scale_avx2: Change asm indent from 2 to 4 spaces. Signed-off-by: James Almer > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commi

[FFmpeg-cvslog] x86/swscale: fix minor coding style issues

2021-12-16 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Dec 16 17:05:48 2021 +0100| [86663963e6419a127cf52a03758855f4f8f8689f] | committer: James Almer x86/swscale: fix minor coding style issues Signed-off-by: James Almer > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commi

[FFmpeg-cvslog] libswscale: Adds ff_hscale8to15_4_avx2 and ff_hscale8to15_X4_avx2 for all filter sizes.

2021-12-15 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Wed Dec 15 10:35:02 2021 +0100| [f900a19fa94b1a55b660ec2e5c13419d59754bc0] | committer: James Almer libswscale: Adds ff_hscale8to15_4_avx2 and ff_hscale8to15_X4_avx2 for all filter sizes. Fixes so that fate under 64 bit Windows passes. These functions

[FFmpeg-cvslog] libswscale/x86/swscale: Only call ff_yuv2yuvX functions if the input size is > 0

2021-04-03 Thread Alan Kelly
ffmpeg | branch: release/4.4 | Alan Kelly | Thu Apr 1 12:00:16 2021 +0200| [95aacf30e3803c57d91ff62975b375e394f61d49] | committer: Michael Niedermayer libswscale/x86/swscale: Only call ff_yuv2yuvX functions if the input size is > 0 Signed-off-by: Michael Niedermayer (cherry picked f

[FFmpeg-cvslog] libswscale/x86/yuv2yuvX: Removes unrolling for mmx and mmxext

2021-04-03 Thread Alan Kelly
ffmpeg | branch: release/4.4 | Alan Kelly | Thu Apr 1 12:00:15 2021 +0200| [4aeedf4c2a8f35be667d5dd40c84bd27730ef1db] | committer: Michael Niedermayer libswscale/x86/yuv2yuvX: Removes unrolling for mmx and mmxext Signed-off-by: Michael Niedermayer (cherry picked from commit

[FFmpeg-cvslog] tests/checkasm/sw_scale: adds additional tests sizes for yux2yuvX

2021-04-03 Thread Alan Kelly
ffmpeg | branch: release/4.4 | Alan Kelly | Thu Apr 1 12:00:17 2021 +0200| [6bc2058d00b119d265c9970eac213d2922d15129] | committer: Michael Niedermayer tests/checkasm/sw_scale: adds additional tests sizes for yux2yuvX Signed-off-by: Michael Niedermayer (cherry picked from commit

[FFmpeg-cvslog] libswscale/x86/swscale: Only call ff_yuv2yuvX functions if the input size is > 0

2021-04-01 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Apr 1 12:00:16 2021 +0200| [dc57762cb43619f91fd2a5d95510fa3b14cfeaaf] | committer: Michael Niedermayer libswscale/x86/swscale: Only call ff_yuv2yuvX functions if the input size is > 0 Signed-off-by: Michael Niedermayer > http://git.videol

[FFmpeg-cvslog] libswscale/x86/yuv2yuvX: Removes unrolling for mmx and mmxext

2021-04-01 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Apr 1 12:00:15 2021 +0200| [3ce8d092448827842c451807f03010ad5129fd8f] | committer: Michael Niedermayer libswscale/x86/yuv2yuvX: Removes unrolling for mmx and mmxext Signed-off-by: Michael Niedermayer > http://git.videolan.org/gitweb.cgi/ffmpeg.

[FFmpeg-cvslog] tests/checkasm/sw_scale: adds additional tests sizes for yux2yuvX

2021-04-01 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Apr 1 12:00:17 2021 +0200| [e1484bc455dff500f8b35b58d434924bca0e03d6] | committer: Michael Niedermayer tests/checkasm/sw_scale: adds additional tests sizes for yux2yuvX Signed-off-by: Michael Niedermayer > http://git.videolan.org/gitweb.

[FFmpeg-cvslog] checkasm/sw_scale: properly initialize src_pixer and filter_coeff buffers

2021-02-19 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Fri Feb 19 14:55:39 2021 +0100| [ee18edb13a9ae3041df961dd5003c2055b5cab35] | committer: James Almer checkasm/sw_scale: properly initialize src_pixer and filter_coeff buffers Fixes valgrind uninitialised value warnings. Signed-off-by: James Almer

[FFmpeg-cvslog] swscale: move yuv2yuvX_sse3 to yasm, unrolls main loop

2021-02-17 Thread Alan Kelly
ffmpeg | branch: master | Alan Kelly | Thu Jan 14 15:47:03 2021 +0100| [554c2bc7086f49ef5a6a989ad6bc4bc11807eb6f] | committer: Paul B Mahol swscale: move yuv2yuvX_sse3 to yasm, unrolls main loop And other small optimizations for ~20% speedup. > http://git.videolan.org/gitweb.cgi/ffmpeg.