[FFmpeg-cvslog] armv6: Accelerate ff_imdct_half for general case (mdct_bits != 6)

ffmpeg | branch: master | Ben Avison | Fri Jul 11 00:14:28 2014 +0100| [42c1cc35b7623ce76c7b55c6bc100f135e17cd4f] | committer: Michael Niedermayer armv6: Accelerate ff_imdct_half for general case (mdct_bits != 6) The previous implementation targeted DTS Coherent Acoustics, which only requires

[FFmpeg-cvslog] armv6: Accelerate butterflies_float

ffmpeg | branch: master | Ben Avison | Fri Jul 11 00:14:31 2014 +0100| [57641410d1a386937bec3fddd6c75119550916ec] | committer: Michael Niedermayer armv6: Accelerate butterflies_float I benchmarked the result by measuring the number of gperftools samples that hit anywhere in the AAC decoder

[FFmpeg-cvslog] armv6: Accelerate vector_fmul_window

ffmpeg | branch: master | Ben Avison | Fri Jul 11 00:14:30 2014 +0100| [649c666137f43542b45941f42034ab3f44a31d38] | committer: Michael Niedermayer armv6: Accelerate vector_fmul_window I benchmarked the result by measuring the number of gperftools samples that hit anywhere in the AAC decoder

[FFmpeg-cvslog] armv6: Accelerate ff_imdct_half for general case (mdct_bits != 6)

ffmpeg | branch: master | Ben Avison | Fri Jul 11 00:12:31 2014 +0100| [5c22e8e4ad0852d61d5c4ba8d67d33fd72339497] | committer: Martin Storsjö armv6: Accelerate ff_imdct_half for general case (mdct_bits != 6) The previous implementation targeted DTS Coherent Acoustics, which only requires

[FFmpeg-cvslog] armv6: Accelerate ff_fft_calc for general case (nbits != 4)

ffmpeg | branch: master | Ben Avison | Wed Jul 16 16:02:01 2014 +0100| [87552d54d3337c3241e8a9e1a05df16eaa821496] | committer: Martin Storsjö armv6: Accelerate ff_fft_calc for general case (nbits != 4) The previous implementation targeted DTS Coherent Acoustics, which only requires nbits == 4

[FFmpeg-cvslog] armv6: Accelerate vector_fmul_window

ffmpeg | branch: master | Ben Avison | Fri Jul 11 00:12:33 2014 +0100| [5edad2c4a1f46bcc56be755af86ab355c2f1b37f] | committer: Martin Storsjö armv6: Accelerate vector_fmul_window I benchmarked the result by measuring the number of gperftools samples that hit anywhere in the AAC decoder

[FFmpeg-cvslog] armv6: Accelerate butterflies_float

ffmpeg | branch: master | Ben Avison | Fri Jul 11 00:12:34 2014 +0100| [5a272190a04666f0fe41be767396b30712638c21] | committer: Martin Storsjö armv6: Accelerate butterflies_float I benchmarked the result by measuring the number of gperftools samples that hit anywhere in the AAC decoder

[FFmpeg-cvslog] arm: Macroize the test for 'setend' CPU instruction support

ffmpeg | branch: master | Ben Avison | Mon Jul 21 14:53:06 2014 +0100| [6869612f5c7d4d2f20f69a5658328a761deadb1c] | committer: Diego Biurrun arm: Macroize the test for 'setend' CPU instruction support Signed-off-by: Diego Biurrun > http://git.videolan.org/gitweb.cgi/ffmpeg.gi

[FFmpeg-cvslog] h264: Move start code search functions into separate source files.

ffmpeg | branch: master | Ben Avison | Mon Jul 21 16:25:48 2014 +0100| [db7f1c7c5a1d37e7f4da64a79a97bea1c4b6e9f8] | committer: Luca Barbato h264: Move start code search functions into separate source files. This permits re-use with parsers for codecs which use similar start codes. Signed-off

[FFmpeg-cvslog] vc-1: Add platform-specific start code search routine to VC1DSPContext.

ffmpeg | branch: master | Ben Avison | Mon Jul 21 14:53:08 2014 +0100| [adf8227cf4e7b4fccb2ad88e1e09b6dc00dd00ed] | committer: Luca Barbato vc-1: Add platform-specific start code search routine to VC1DSPContext. Initialise VC1DSPContext for parser as well as for decoder. Note, the VC-1 code

[FFmpeg-cvslog] vc-1: Optimise parser (with special attention to ARM)

ffmpeg | branch: master | Ben Avison | Mon Jul 21 14:53:09 2014 +0100| [701e8b42e12ad625c64ceae2252acb1de390278c] | committer: Luca Barbato vc-1: Optimise parser (with special attention to ARM) The previous implementation of the parser made four passes over each input buffer (reduced to two

[FFmpeg-cvslog] checkasm: Add vc1dsp in-loop deblocking filter tests

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:42 2022 +0100| [20cb43ea8ba0471dcba442b8de8fa17ff41f6281] | committer: Martin Storsjö checkasm: Add vc1dsp in-loop deblocking filter tests Note that the benchmarking results for these functions are highly dependent upon the input data

[FFmpeg-cvslog] checkasm: Add vc1dsp inverse transform tests

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:43 2022 +0100| [2698bfdc93d456d304a38b570052e1a238d64c54] | committer: Martin Storsjö checkasm: Add vc1dsp inverse transform tests This test deliberately doesn't exercise the full range of inputs described in the committee draft

[FFmpeg-cvslog] checkasm: Add idctdsp add/put-pixels-clamped tests

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:44 2022 +0100| [bd3615a81a3387cafb51444927e852423f8f4a6e] | committer: Martin Storsjö checkasm: Add idctdsp add/put-pixels-clamped tests Signed-off-by: Ben Avison Signed-off-by: Martin Storsjö > http://git.videolan.org/gitweb.

[FFmpeg-cvslog] avcodec/vc1: Introduce fast path for unescaping bitstream buffer

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:45 2022 +0100| [2e268477802d64aa75b9c3c2cb2fc89d1ef7c87d] | committer: Martin Storsjö avcodec/vc1: Introduce fast path for unescaping bitstream buffer Includes a checkasm test. Signed-off-by: Ben Avison Signed-off-by: Martin Storsjö

[FFmpeg-cvslog] avcodec/vc1: Arm 64-bit NEON deblocking filter fast paths

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:46 2022 +0100| [c62bbd4d2015ffa717369e687601fb2d481af6b0] | committer: Martin Storsjö avcodec/vc1: Arm 64-bit NEON deblocking filter fast paths checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. Note that the C version can still

[FFmpeg-cvslog] avcodec/vc1: Arm 32-bit NEON deblocking filter fast paths

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:47 2022 +0100| [c07de58a725a508c628ddea7d936771c42c189aa] | committer: Martin Storsjö avcodec/vc1: Arm 32-bit NEON deblocking filter fast paths checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. Note that the C version can still

[FFmpeg-cvslog] avcodec/vc1: Arm 64-bit NEON inverse transform fast paths

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:48 2022 +0100| [501fdc017deb1b57ecc17420ba41686a14932fcc] | committer: Martin Storsjö avcodec/vc1: Arm 64-bit NEON inverse transform fast paths checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. vc1dsp.vc1_inv_trans_4x4_c: 158.2

[FFmpeg-cvslog] avcodec/vc1: Arm 32-bit NEON unescape fast path

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:51 2022 +0100| [23c92e14f5fdb0c2928b44bb94d4c0711439e1c7] | committer: Martin Storsjö avcodec/vc1: Arm 32-bit NEON unescape fast path checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. vc1dsp.vc1_unescape_buffer_c: 918624.7

[FFmpeg-cvslog] avcodec/idctdsp: Arm 64-bit NEON block add and clamp fast paths

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:49 2022 +0100| [5379412ed0c587d82788c6fc46b7787cfe10f72d] | committer: Martin Storsjö avcodec/idctdsp: Arm 64-bit NEON block add and clamp fast paths checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. idctdsp.add_pixels_clamped_c

[FFmpeg-cvslog] avcodec/vc1: Arm 64-bit NEON unescape fast path

ffmpeg | branch: master | Ben Avison | Thu Mar 31 18:23:50 2022 +0100| [6eee65028957c3b16287a204e648caebcc86b06c] | committer: Martin Storsjö avcodec/vc1: Arm 64-bit NEON unescape fast path checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. vc1dsp.vc1_unescape_buffer_c: 655617.7