Commit Graph
100 Commits
Author SHA1 Message Date
James Almer 6fb96afdd6 avutil/fixed_dsp: remove ff_ prefix from static function
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-20 03:39:09 -03:00
James AlmerandMichael Niedermayer a9af9da631 library.mak: Workaround SDL redefining main and breaking fate tests on mingw
Fixes Ticket3368

Commit message by commiter
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-06-19 12:12:27 +02:00
James AlmerandVittorio Giovara 1e79d5c6e7 libwebpenc: use WebPMemoryWriterClear()
WebPMemoryWriterClear() must be used instead of free() when
libwebp ABI version is > 0x0203.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
2015-06-17 14:13:43 +01:00
James Almer 20abb1afe5 softfloat: make av_div_sf() inline
Removes a defined but not used warning on files including softfloat.h

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-13 22:28:39 -03:00
James Almer 4aebaed0e1 avformat/singlejpeg: fix standalone compilation 2015-06-13 17:47:13 -03:00
James Almer 9f815bc2c2 avcodec/jpeg200dsp: add ff_rct_int_{sse2,avx2}
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-13 16:53:31 -03:00
James Almer 7912a6830d avcodec/jpeg200dsp: add ff_ict_float_{sse,avx}
Original intrinsics version by Nicolas Bertrand.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-13 16:53:27 -03:00
James AlmerandJanne Grunau b380337020 mpjpegdec: don't try to alloc an AVIOContext when probe is guaranteed to fail
The first check is done without the AVIOContext, so alloc it only if said check succeeds

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Janne Grunau <janne-libav@jannau.net>
2015-06-09 10:07:11 +02:00
James Almer 1382add59d mpjpegdec: don't try to alloc an AVIOContext when probe is guaranteed to fail
The first check is done without the AVIOContext, so alloc it only if said check succeeds

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-08 18:26:42 -03:00
James Almer 34d278f983 mpjpegdec: fix memory leak in probe function
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-08 16:03:31 -03:00
James Almer e225f5f232 fate: add missing avdevice dependency to closed caption test
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-07 01:24:50 -03:00
James Almer 1b4dd59e5f configure: improve the checks for gmtime_r and localtime_r
They are inlined wrapper functions inside the time.h header on MinGW-w64, so
neither check_func() or check_func_headers() work with them.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-06 12:07:53 -03:00
James Almer da7c8fd917 fate: add missing lavfi indev dependency to closed caption test
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-03 23:35:00 -03:00
James AlmerandMartin Storsjö 876d441fbe configure: don't enable tls protocols if network is disabled
This was a regression introduced with d8ffb2055f.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
2015-06-02 22:48:50 +03:00
James Almer 7fc6545d5d configure: don't enable any tls protocol if network is disabled
This was a regression introduced with 4a006b9eb7.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-01 17:49:21 -03:00
James Almer 3be811a528 avcodec/Makefile: fix checkheaders for nvenc_b
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-01 13:57:50 -03:00
James Almer f10497042f nvenc: remove cuda.h requirement for nvenc_a
Reviewed-by: Philip Langdale <philipl@overt.org>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-06-01 01:33:47 -03:00
James AlmerandMichael Niedermayer c16e99e3b3 x86: check for AV_CPU_FLAG_AVXSLOW where useful
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-06-01 00:15:35 +02:00
James AlmerandLuca Barbato d68c05380c x86: check for AV_CPU_FLAG_AVXSLOW where useful
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2015-05-31 12:07:11 +02:00
James AlmerandLuca Barbato cae3985120 x86: Add helper macros to check for slow cpuflags
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2015-05-31 12:07:11 +02:00
James AlmerandLuca Barbato f7cafb5d02 x86: add AV_CPU_FLAG_AVXSLOW flag
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2015-05-31 12:07:11 +02:00
James Almer c312bfac4c x86/cpu: add AV_CPU_FLAG_AVXSLOW flag
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-27 03:31:11 -03:00
James Almer c5a07f1f84 libdcadec: search for frames that start late in a packet
Based on commit 4ae15605f6

Reviewed-by: Hendrik Leppkes <h.leppkes@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-24 13:06:42 -03:00
James Almer 8952254ffe libwebp: simplify AVCodec.close functions
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-23 14:46:46 -03:00
James Almer 57d9788d1b configure: simplify libwebp checks
The libwebpmux pkg-config file already has an explicit dependecy on libwebp >= 0.2.0.
Also remove the warning and silently disable the anim encoder when libwebpmux is not new enough.
This is more in line with other library components, like libvpx-vp9

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-23 14:18:54 -03:00
James Almer 1096c46c55 libwebp: use a separate AVClass for each encoder
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-23 01:52:16 -03:00
James Almer 44ca8a6adb libwebpenc_common: add header guards
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-23 01:44:54 -03:00
James Almer 98be2d94ea libwebp: remove unneeded defines
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-23 01:29:23 -03:00
James AlmerandMartin Storsjö 29216d7fd1 tls: fix compilation when both gnutls and openssl are enabled
Signed-off-by: Martin Storsjö <martin@martin.st>
2015-05-22 12:21:38 +03:00
James Almer e91fbfd9cf tls: fix compilation when both gnutls and openssl are enabled
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-22 00:33:33 -03:00
James Almer 40bf3687a1 libvpx: add support for yuv440p and yuv440p10/12 encoding
Reviewed-by: James Zern <jzern@google.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-20 20:08:56 -03:00
James AlmerandMichael Niedermayer 32a4177a62 dashenc: replace attribute id with contentType for the AdaptationSet element
id should be an integer, not a string. It is also optional, so use
contentType instead which is the proper attribute for these values.

This addresses ticket #4545, fixing an MPD validation error.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-05-11 01:37:39 +02:00
James AlmerandMartin Storsjö ac1a1cb948 dashenc: replace attribute id with contentType for the AdaptationSet element
id should be an integer, not a string. It is also optional, so use
contentType instead which is the proper attribute for these values.

This fixes an MPD validation error.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
2015-05-10 22:57:20 +03:00
James Almer 28eaf46da9 doc/APIchanges: fill missing versions and hashes
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-07 18:56:26 -03:00
James Almer e0a403e1c2 vp9: add missing changelog and APIchanges entries for new VP9 profiles
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-07 18:35:12 -03:00
James AlmerandMichael Niedermayer aa70801aaf ripemd: move ripemd{256, 320} into separate functions
This allows the removal of a few branches.

Before:
lavu       RIPEMD-160   size: 1048576  runs:   1024  time:    7.052 +- 0.010

After:
lavu       RIPEMD-160   size: 1048576  runs:   1024  time:    6.865 +- 0.015

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-05-07 15:40:56 +02:00
James Almer 858f81fde2 cmdutils: move get_rotation() up in the file
Fixes compilation of fftools without libavdevice

Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-05 02:47:21 -03:00
James Almer 3f7986f983 avfilter/Makefile: add missing lavfutils.c dependency to cover_rect and find_rect filters
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-05 02:16:37 -03:00
James Almer 079b7f6eac vp9: add profile names
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-05-04 18:39:51 -03:00
James Almer 39fbb27ec3 avutil/softfloat_tables: add missing stdint.h include
Fixes make checkheaders

Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-30 17:38:41 -03:00
James AlmerandMichael Niedermayer d7f62f033c fate: add cinepak encoder vsynth tests
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-04-23 04:44:45 +02:00
James Almer ba625dd8a1 avcodec: use av_mod_uintp2() where useful
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-21 22:41:20 -03:00
James AlmerandVittorio Giovara a1d58e3b38 avutil: remove pointless bmi1 define
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-19 23:45:35 +01:00
James Almer a40cee03a3 avutil: remove pointless bmi1 define
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-18 22:15:25 -03:00
James Almer 5cd2169344 wavpackenc: use put_sbits()
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-18 18:07:54 -03:00
James Almer d8c52f5d04 proresenc_anatoliy: use put_sbits()
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-18 14:15:57 -03:00
James Almer 778bac2788 adpcm: use av_clip_intp2()
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-18 14:15:07 -03:00
James Almer 979b77eec5 dca_xll: use av_clip_intp2()
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-18 14:14:24 -03:00
James Almer b5564e041b dcaenc: use put_sbits()
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-18 14:14:11 -03:00
James Almer 6863249b34 aaccoder: use put_sbits()
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-18 14:13:59 -03:00
James Almer 8254011b21 configure: remove old libdcadec check
It's obsolete after the addition of the pkg-config check.
See http://comments.gmane.org/gmane.comp.video.ffmpeg.devel/191983 for the
relevant discussion

Reviewed-by: Hendrik Leppkes <h.leppkes@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-16 20:10:19 -03:00
James Almer 1577b29c82 configure: add missing dependencies for MIPS and PPC features
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-16 13:17:12 -03:00
James AlmerandMichael Niedermayer 30ce065ffe fate: add tta encoder test
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-04-13 11:33:02 +02:00
James Almer 14edc9f3a3 configure: add missing h263p decoder dependencies
Should fix ticket #4480

Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-12 15:48:55 -03:00
James AlmerandDerek Buitenhuis bbdb50d7a8 libx265: print supported presets and tunes on error
Based on code from libavcodec/libx264.c

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2015-04-11 11:13:28 -04:00
James Almer 9fc45681e0 doc: add aarch64 cpuflags to fftools documentation
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-10 20:57:19 -03:00
James Almer 666ec9bd09 doc: add missing arm cpuflags to fftools documentation
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-10 20:57:15 -03:00
James Almer 410c93cfd5 doc: add missing x86 cpuflags to fftools documentation
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-10 20:57:11 -03:00
James Almer 61090db29a avcodec/libx265: print supported presets and tunes on error
Based on code from libavcodec/libx264.c

Reviewed-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-10 16:47:29 -03:00
James Almer 3553b815f6 avcodec/libdcadec: honor AVCodecContext bitexact flag
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-04-09 22:37:39 -03:00
James AlmerandMichael Niedermayer 43482bd1a5 swr/resample: use av_clip functions
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-04-05 22:46:40 +02:00
James AlmerandMichael Niedermayer 3000183732 avcodec/pngenc: don't return a value in a void function
Should fix compilation failures with strict compilers

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-04-02 23:22:28 +02:00
James Almer 1f5d1eed78 avutil/cpu: add missing check for mmxext to av_force_cpu_flags
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-26 22:54:15 -03:00
James Almer 23e1303c0a avcodec/nvenc_h265: add missing version bump and changelog entry
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-25 03:59:34 -03:00
James Almer 7c4910758a configure: add missing dependency for nvenc_h265
Should fix compilation of builds without nvenc

Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-25 03:51:10 -03:00
James Almer 60b9373dbd libavutil: add bmi2 optimized av_mod_uintp2
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-20 15:47:43 -03:00
James Almer d13e521cc8 libavutil: add av_mod_uintp2
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-20 15:47:31 -03:00
James Almer 6b940b8c99 x86/xvididct: add some yasm guards
Should fix compilation on compilers with less-than-ideal dead code elimination

Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-20 02:38:20 -03:00
James Almer b0fea4ad7e x86/xvididct: remove obsolete function prototypes
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-20 02:38:14 -03:00
James Almer 03e9b1931b avcodec/libdcadec: add missing version bump and changelog entry 2015-03-19 21:09:42 -03:00
James Almer bf2bd5b807 avcodec/ac3dec_fixed: fix compilation when ac3dec is disabled
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-17 19:25:55 -03:00
James Almer e8374d7202 x86/proresdsp: remove ff_prores_idct_put_10_sse4
It's exactly the same as the sse2 version.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-16 01:52:44 -03:00
James Almer bdd179c8cb x86/proresdsp: remove unused macro
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-16 01:49:34 -03:00
James AlmerandMichael Niedermayer d5addf1555 hevcdsp: fix compilation for arm and aarch64
Also add av_cold to ff_hevcdsp_init_arm.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-03-12 20:01:01 +01:00
James Almer 1b47760bbe RELEASE: update to 2.6.git
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-08 18:59:57 -03:00
James Almer 0d1acb944c fate: add test for vp90-2-trac4359.webm
Regression test for the bug from trac ticket #4359 fixed in commit efff3854

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-08 17:03:42 -03:00
James Almer 5c8f747085 x86/hevc_sao: use unaligned movs for sao_{band,filter} with width 8
Suggested-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-03-01 20:02:43 -03:00
James Almer bc65abc8d7 libavutil: add x86 optimized av_popcount
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-25 19:58:00 -03:00
James Almer 03616af2c9 Revert "takdec: pad filter coeff buffer for DSP functions"
This reverts commit e0c7ba40cf.

Valgrind complains about invalid reads, which generate segfaults in some
systems.
2015-02-23 18:22:37 -03:00
James Almer 6e3651983c avcodec/hevcdsp: add missing () to CMP macro
Found-by: Clément Bœsch <u@pkh.me>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-16 18:56:16 -03:00
James Almer 22596383f3 avcodec/hevcdsp: optimize pixel comparison in sao_edge_filter
GCC 4.9.2 on a Core i5-4200U @ 1.60GHz, Linux x86_64

Before
715487 decicycles in sao_edge_filter_8, 262144 runs, 0 skips

After
672104 decicycles in sao_edge_filter_8, 262144 runs, 0 skips

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-16 17:47:47 -03:00
James Almer 03adafb318 x86/g722dsp: add ff_g722_apply_qmf_sse2
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-16 00:41:21 -03:00
James Almer f7ed997a6d x86/swr: make pack_8ch functions work with compilers without aligned stack
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-15 13:57:37 -03:00
James Almer 1679d68dbf x86/hevc_mc: optimize AVX2 mc functions
Before
40766 decicycles in ff_hevc_put_hevc_qpel_h64_8_avx2, 8192 runs, 0 skips

After
37975 decicycles in ff_hevc_put_hevc_qpel_h64_8_avx2, 8192 runs, 0 skips

Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-12 13:21:58 -03:00
James Almer 14b44c1614 x86/hevc_sao: make sao_edge_filter_{10,12} work on x86_32
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-12 13:21:30 -03:00
James Almer 06fe6dfe12 x86/hevc_sao: make sao_band_filter work on x86_32
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-09 20:41:21 -03:00
James Almer 92d903afaa x86/vp9dsp: fix clobbering of xmm6 on IDCT sse2 functions
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-08 00:50:39 -03:00
James Almer 383fddeec6 x86/lossless_audiodsp: fix compilation with --disable-yasm
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-06 17:30:17 -03:00
James Almer aea29a891f x86/hevc_sao: fix loading of RIP address
pb_eo must be handled as a rip relative address for MSVC64, so an
intermediate register is needed. Should fix link failures.

Suggested by Hendrik Leppkes and Christophe Gisquet.

Tested-By: Hendrik Leppkes <h.leppkes@gmail.com>
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-06 15:06:15 -03:00
James Almer 15a88468ae avformat/tta: only check for header and seek table crc if requested
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-05 23:20:40 -03:00
James Almer 15574c505b x86/hevcdsp: add ff_hevc_sao_edge_filter_{10,12}_{sse2,avx2}
Original x86 intrinsics code by Pierre-Edouard Lepere.
Yasm port, refactoring and optimizations by James Almer.

Benchmarks of BQTerrace_1920x1080_60_qp22.bin with an Intel Core i5-4200U

Width 32
342694 decicycles in sao_edge_filter_10, 16384 runs, 0 skips
29476 decicycles in ff_hevc_sao_edge_filter_32_10_ssse3, 16384 runs, 0 skips
13996 decicycles in ff_hevc_sao_edge_filter_32_10_avx2, 16381 runs, 3 skips

Width 64
581163 decicycles in sao_edge_filter_10, 8192 runs, 0 skips
59774 decicycles in ff_hevc_sao_edge_filter_64_10_ssse3, 8192 runs, 0 skips
28383 decicycles in ff_hevc_sao_edge_filter_64_10_avx2, 8191 runs, 1 skips

Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-05 15:02:33 -03:00
James Almer 042c1159fc x86/hevcdsp: add ff_hevc_sao_edge_filter_8_{ssse3,avx2}
Original x86 intrinsics code and initial yasm port by Pierre-Edouard Lepere.
Refactoring and optimizations by James Almer.

Benchmarks of BQTerrace_1920x1080_60_qp22.bin with an Intel Core i5-4200U

Width 32
158583 decicycles in edge, sao_edge_filter_8 runs, 0 skips
5205 decicycles in ff_hevc_sao_edge_filter_32_8_ssse3, 32767 runs, 1 skips
2942 decicycles in ff_hevc_sao_edge_filter_32_8_avx2, 32767 runs, 1 skips

Width 64
705639 decicycles in sao_edge_filter_8, 262144 runs, 0 skips
19224 decicycles in ff_hevc_sao_edge_filter_64_8_ssse3, 262111 runs, 33 skips
10433 decicycles in ff_hevc_sao_edge_filter_64_8_avx2, 262115 runs, 29 skips

Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-05 15:02:27 -03:00
James Almer 1f1c7c8a57 hevcdsp: remove compilation-time-fixed parameter from sao_edge_filter
The stride_src parameter is always 2 * MAX_PB_SIZE + FF_INPUT_BUFFER_PADDING_SIZE.

Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-05 15:02:22 -03:00
James Almer 7457afc64d hevcdsp: replace the SAOParams struct parameter from sao_edge_filter
As with sao_band_filter, pass instead the two variables from the struct needed in the function.
This simplifies writing asm optimized versions.

Reviewed-by: Mickaël Raulet <mraulet@insa-rennes.fr>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-04 17:53:04 -03:00
James Almer 121ccc3365 hevcdsp: further simplify sao_edge_filter
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Reviewed-by: Mickaël Raulet <mraulet@insa-rennes.fr>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-04 17:52:59 -03:00
James Almer aa945dc112 x86/hevcdsp: add missing vzeroupper in ff_hevc_sao_band_filter_48_*_avx2
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-02 00:01:35 -03:00
James Almer 71e2cb4706 x86/hevcdsp: add missing guards to ff_hevc_sao_band_filter_avx2
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-01 21:45:52 -03:00
James Almer fa3eccb4f9 x86/hevc: add ff_hevc_sao_band_filter_{8,10,12}_{sse2,avx,avx2}
Original x86 intrinsics code and initial 8bit yasm port by Pierre-Edouard Lepere.
10/12bit yasm ports, refactoring and optimizations by James Almer

Benchmarks of BQTerrace_1920x1080_60_qp22.bin with an Intel Core i5-4200U

width 32
40338 decicycles in sao_band_filter_0_8, 2048 runs, 0 skips
8056 decicycles in ff_hevc_sao_band_filter_8_32_sse2, 2048 runs, 0 skips
7458 decicycles in ff_hevc_sao_band_filter_8_32_avx, 2048 runs, 0 skips
4504 decicycles in ff_hevc_sao_band_filter_8_32_avx2, 2048 runs, 0 skips

width 64
136046 decicycles in sao_band_filter_0_8, 16384 runs, 0 skips
28576 decicycles in ff_hevc_sao_band_filter_8_32_sse2, 16384 runs, 0 skips
26707 decicycles in ff_hevc_sao_band_filter_8_32_avx, 16384 runs, 0 skips
14387 decicycles in ff_hevc_sao_band_filter_8_32_avx2, 16384 runs, 0 skips

Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-01 20:22:35 -03:00
James Almer 2929e56006 hevcdsp: replace the SAOParams struct parameter from sao_band_filter
Pass instead the two variables from the struct needed in the function.
This simplifies writing asm optimized versions of the function

Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-01 15:45:20 -03:00
James Almer 65e6ab0c5a hevcdsp: remove unused parameter from sao_band_filter
Signed-off-by: James Almer <jamrial@gmail.com>
2015-02-01 15:45:14 -03:00