RepoMirrors/ffmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2025-03-24 11:59:38 +00:00
Code Issues Projects Releases Wiki Activity
FFmpeg git repo
43,980 Commits 37 Branches 403 Tags 293 MiB
C 90.3%
Assembly 7.8%
Makefile 1.3%
C++ 0.2%
Objective-C 0.1%
Other 0.1%
9d2afd1eb8
Go to file
Martin Storsjö 9d2afd1eb8 aarch64: vp9: Implement NEON loop filters 
This work is sponsored by, and copyright, Google.

These are ported from the ARM version; thanks to the larger
amount of registers available, we can do the loop filters with
16 pixels at a time. The implementation is fully templated, with
a single macro which can generate versions for both 8 and
16 pixels wide, for both 4, 8 and 16 pixels loop filters
(and the 4/8 mixed versions as well).

For the 8 pixel wide versions, it is pretty close in speed (the
v_4_8 and v_8_8 filters are the best examples of this; the h_4_8
and h_8_8 filters seem to get some gain in the load/transpose/store
part). For the 16 pixels wide ones, we get a speedup of around
1.2-1.4x compared to the 32 bit version.

Examples of runtimes vs the 32 bit version, on a Cortex A53:
                                       ARM AArch64
vp9_loop_filter_h_4_8_neon:          144.0   127.2
vp9_loop_filter_h_8_8_neon:          207.0   182.5
vp9_loop_filter_h_16_8_neon:         415.0   328.7
vp9_loop_filter_h_16_16_neon:        672.0   558.6
vp9_loop_filter_mix2_h_44_16_neon:   302.0   203.5
vp9_loop_filter_mix2_h_48_16_neon:   365.0   305.2
vp9_loop_filter_mix2_h_84_16_neon:   365.0   305.2
vp9_loop_filter_mix2_h_88_16_neon:   376.0   305.2
vp9_loop_filter_mix2_v_44_16_neon:   193.2   128.2
vp9_loop_filter_mix2_v_48_16_neon:   246.7   218.4
vp9_loop_filter_mix2_v_84_16_neon:   248.0   218.5
vp9_loop_filter_mix2_v_88_16_neon:   302.0   218.2
vp9_loop_filter_v_4_8_neon:           89.0    88.7
vp9_loop_filter_v_8_8_neon:          141.0   137.7
vp9_loop_filter_v_16_8_neon:         295.0   272.7
vp9_loop_filter_v_16_16_neon:        546.0   453.7

The speedup vs C code in checkasm tests is around 2-7x, which is
pretty much the same as for the 32 bit version. Even if these functions
are faster than their 32 bit equivalent, the C version that we compare
to also became around 1.3-1.7x faster than the C version in 32 bit.

Based on START_TIMER/STOP_TIMER wrapping around a few individual
functions, the speedup vs C code is around 4-5x.

Examples of runtimes vs C on a Cortex A57 (for a slightly older version
of the patch):
                         A57 gcc-5.3  neon
loop_filter_h_4_8_neon:        256.6  93.4
loop_filter_h_8_8_neon:        307.3 139.1
loop_filter_h_16_8_neon:       340.1 254.1
loop_filter_h_16_16_neon:      827.0 407.9
loop_filter_mix2_h_44_16_neon: 524.5 155.4
loop_filter_mix2_h_48_16_neon: 644.5 173.3
loop_filter_mix2_h_84_16_neon: 630.5 222.0
loop_filter_mix2_h_88_16_neon: 697.3 222.0
loop_filter_mix2_v_44_16_neon: 598.5 100.6
loop_filter_mix2_v_48_16_neon: 651.5 127.0
loop_filter_mix2_v_84_16_neon: 591.5 167.1
loop_filter_mix2_v_88_16_neon: 855.1 166.7
loop_filter_v_4_8_neon:        271.7  65.3
loop_filter_v_8_8_neon:        312.5 106.9
loop_filter_v_16_8_neon:       473.3 206.5
loop_filter_v_16_16_neon:      976.1 327.8

The speed-up compared to the C functions is 2.5 to 6 and the cortex-a57
is again 30-50% faster than the cortex-a53.

Signed-off-by: Martin Storsjö <martin@martin.st>
2016-11-14 00:10:13 +02:00
compat Add a compat dummy stdatomic.h used when threading is disabled 2016-10-02 18:57:56 +02:00
doc examples/decode_audio: Add missing header for av_free() 2016-11-10 10:33:19 +01:00
libavcodec aarch64: vp9: Implement NEON loop filters 2016-11-14 00:10:13 +02:00
libavdevice Use avpriv_report_missing_feature() where appropriate 2016-11-08 17:54:34 +01:00
libavfilter vf_drawtext: Drop wrong void* cast 2016-11-12 16:47:07 +01:00
libavformat Drop pointless void* casts 2016-11-13 18:44:01 +01:00
libavresample build: Change structure of the linker version script templates 2016-05-29 16:43:11 +02:00
libavutil arm: Clear the gp register alias at the end of functions 2016-11-10 14:01:04 +02:00
libswscale swscale: Add GRAY12 2016-11-07 22:42:00 +01:00
presets
tests checkasm: add vp9dsp.itxfm_add tests. 2016-11-11 11:09:05 +02:00
tools aviocat: Support avio options 2016-10-25 15:43:56 +02:00
.gitattributes
.gitignore build: Ignore generated mapfile and remove it on distclean 2016-05-27 11:27:24 +02:00
.travis.yml travis: Enable OSX integration 2015-11-17 16:51:00 +01:00
arch.mak
avconv_dxva2.c avconv_dxva2: add a profile check for hevc 2016-07-20 16:33:09 +02:00
avconv_filter.c avconv: make sure the filtergraph is freed on init failure 2016-10-02 11:41:45 +02:00
avconv_opt.c avconv_opt: Consistently iterate through hwaccels array in all cases 2016-11-13 19:06:38 +01:00
avconv_qsv.c avconv_qsv: use the actual pixel format provided by lavc 2016-07-22 19:08:12 +02:00
avconv_vaapi.c avconv_vaapi: Convert to use hw_frames_ctx only 2016-08-30 22:16:01 +01:00
avconv_vda.c avconv: vda: Unlock the pixel buffer once it is accessed 2015-07-09 00:10:13 +02:00
avconv_vdpau.c avconv_vdpau: use the hwcontext device creation API 2016-05-26 15:40:34 +02:00
avconv.c avconv: Drop stray leftover debug output 2016-11-09 20:51:55 +01:00
avconv.h avconv: support parsing bitstream filter options 2016-11-02 10:08:28 +01:00
avplay.c avplay: Correct function pointer assignments in options array 2016-11-08 17:20:30 +01:00
avprobe.c avprobe: Add -show_stream_entry to get a single stream property 2016-11-01 11:27:52 -04:00
Changelog Changelog: mark the release 12 branch 2016-08-31 08:08:32 +02:00
cmdutils_common_opts.h
cmdutils.c avconv: switch to the new BSF API 2016-03-20 08:15:01 +01:00
cmdutils.h avconv: use read_file() for reading the 2pass stats 2015-07-19 09:37:11 +02:00
common.mak build: Simplify postprocessing of linker version script files 2016-05-29 16:49:16 +02:00
configure libxvid: Require availability of mkstemp() 2016-11-11 10:17:07 +01:00
COPYING.GPLv2
COPYING.GPLv3
COPYING.LGPLv2.1
COPYING.LGPLv3
CREDITS
INSTALL
library.mak build: Drop duplicate asm recipe 2016-10-17 16:25:35 +02:00
LICENSE Remove the legacy X11 screen grabber 2016-07-29 19:03:10 +02:00
Makefile build: Hardcode avversion.h dependency 2016-10-27 11:54:06 +02:00
README
README.md doc: Add travis badge 2015-09-14 00:19:08 +02:00
RELEASE Make the RELEASE file match with the most recent tag 2016-10-14 13:52:51 -04:00
version.sh build: remove hardcoded name of version header 2016-09-15 21:59:15 +02:00

README.md

Libav

Build Status

Libav is a collection of libraries and tools to process multimedia content such as audio, video, subtitles and related metadata.

Libraries

  • libavcodec provides implementation of a wider range of codecs.
  • libavformat implements streaming protocols, container formats and basic I/O access.
  • libavutil includes hashers, decompressors and miscellaneous utility functions.
  • libavfilter provides a mean to alter decoded Audio and Video through chain of filters.
  • libavdevice provides an abstraction to access capture and playback devices.
  • libavresample implements audio mixing and resampling routines.
  • libswscale implements color conversion and scaling routines.

Tools

  • avconv is a command line toolbox to manipulate, convert and stream multimedia content.
  • avplay is a minimalistic multimedia player.
  • avprobe is a simple analisys tool to inspect multimedia content.
  • Additional small tools such as aviocat, ismindex and qt-faststart.

Documentation

The offline documentation is available in the doc/ directory.

The online documentation is available in the main website and in the wiki.

Examples

Conding examples are available in the doc/example directory.

License

Libav codebase is mainly LGPL-licensed with optional components licensed under GPL. Please refer to the LICENSE file for detailed information.