1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-12 19:18:44 +02:00
Commit Graph

669 Commits

Author SHA1 Message Date
Anton Khirnov
85ba17f36d Bump major versions of all libraries.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2021-04-27 11:48:05 -03:00
Andreas Rheinhardt
f3c197b129 Include attributes.h directly
Some files currently rely on libavutil/cpu.h to include it for them;
yet said file won't use include it any more after the currently
deprecated functions are removed, so include attributes.h directly.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2021-04-19 14:34:10 +02:00
Andreas Rheinhardt
64977ed7ae libswresample/audioconvert: Fix undefined NULL + 0
Affected 26 FATE tests like swr-resample_async-s16p-44100-8000.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
2021-04-01 14:15:20 +02:00
Michael Niedermayer
c361fa9e21 Bump minor versions after release branch
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2021-03-20 01:02:11 +01:00
Michael Niedermayer
c67d2a2875 Bump Versions before release/4.4 branch
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2021-03-20 01:01:12 +01:00
Andreas Rheinhardt
9d8f9b2e40 swresample/audioconvert: Fix left shift of negative value
Fixes ticket #8219.

Reviewed-by: Paul B Mahol <onemda@gmail.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
2020-09-30 10:50:45 +02:00
Jan Ekström
1c7e55dd50 swresample/rematrix: handle 22.2 as a 9 channel layout
This is as far as 22.2 follows the same channel order as
WaveFormatExtensible's channel mask (and the AV_CH_* defines).

After LFE2 the side channels would follow, but that offset of
one stops us from utilizing them without further tweaks.

This change was verified by using swresample to downmix to 5.1,
and then feeding that to WASAPI.
2020-08-18 22:47:35 +03:00
Jan Ekström
f5390a9f86 swresample/rematrix: treat 22.2 as 5.1 (back) when mixing
Only this sub-set of channels actually follows the bit mask order
in the official 22.2 channel mapping. Additionally, the 5.1 channels
are there for backwards compatibility with the previous system.

This enables the utilization of 22.2 content until a proper down/up
matrix is added into swresample.
2020-08-04 00:17:56 +03:00
Jan Ekström
2fd8add1ba swresample/matrix: switch internal clean_layout function to not drop high bits
These bits are utilized by channel layouts such as 22.2. If those
are dropped, the returned channel layout is no longer a match
against the AV_CH_LAYOUT define when returned from this function.
2020-08-04 00:17:56 +03:00
Michael Niedermayer
c5079bf3bc Bump minor versions after branching 4.3
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2020-06-08 22:49:04 +02:00
Michael Niedermayer
0a8a96c251 Bump minor versions to separate 4.3 from master
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2020-06-08 22:49:04 +02:00
Carl Eugen Hoyos
96fab29e96 Silence "string-plus-int" warning shown by clang.
libswscale/utils.c:89:42: warning: adding 'unsigned long' to a string does not append to the string [-Wstring-plus-int]
2020-01-06 22:38:56 +01:00
Paul B Mahol
ccd18b4731 swresample/audioconvert: fix invalid left shift for 64bit sample format
Fixes #8002.
2019-09-26 16:22:47 +02:00
Michael Niedermayer
80bb65fafa Bump minor versions again on master to keep 4.2 versions separate from master
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2019-07-21 18:36:31 +02:00
Michael Niedermayer
22db337a40 Bump minor versions to separate 4.2 from master
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2019-07-21 18:36:18 +02:00
Paul B Mahol
a9fa6b8e02 swresample/swresample: check for invalid sample rates 2019-05-26 14:43:32 +02:00
Michael Niedermayer
517573a670 Bump minor version for master after 4.1 branchpoint
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-11-02 00:53:07 +01:00
Michael Niedermayer
780d5e30a0 Bump minor versions for branching 4.1
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-11-02 00:15:32 +01:00
Michael Niedermayer
bce4da85e8 swresample/swresample: Fix input channel count in resample_first computation
Found-by: Marcin Gorzel <gorzel@google.com>
Reviewed-by: Marcin Gorzel <gorzel@google.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-07-26 02:42:42 +02:00
Marcin Gorzel
8b710ea5e7 swresample: Use channel count in rematrix initialization
Rematrixing supports up to 64 channels. However, there is only a limited number of channel layouts defined. Since the in/out channel count is currently obtained from the channel layout, for undefined layouts (e.g. for 9, 10, 11 channels etc.) the rematrixing fails.

This patch changes rematrix init methods to use in (used) and out channel count directly instead of computing it from channel layout.

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-07-26 02:42:42 +02:00
Rahul Chaudhry
e84212b78e swresample/arm: rename labels to fix xcode build error
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-04-28 18:08:52 +02:00
Rahul Chaudhry
b22db4f465 swresample/arm: remove unintentional relocation.
Branch to global symbol results in reference to PLT, and when compiling
for THUMB-2 - in a R_ARM_THM_JUMP19 relocation. Some linkers don't
support this relocation (ld.gold), while others can end up truncating
the relocation to fit (ld.bfd).

Convert this branch through PLT into a direct branch that the assembler
can resolve locally.

See https://github.com/android-ndk/ndk/issues/337 for background.

The current workaround is to disable neon during gstreamer build,
which is not optimal and can be reverted after this patch:
41556c4157

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-04-19 21:49:47 +02:00
Michael Niedermayer
3c1ecb057d Bump minor versions after release/4.0 branching
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-04-16 12:35:12 +02:00
Michael Niedermayer
7e3a070d9a Bump minor versions for branching release/4.0
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-04-16 12:35:12 +02:00
Hendrik Schreiber
647fd4b829 swresample/swresample: Fix for seg fault in swr_convert_internal() -> sum2_float during dithering.
Removed +len1 in call to s->mix_2_1_f() as I found no logical explanation for it. After removal, problem was gone.

Signed-off-by: Hendrik Schreiber <hs@tagtraum.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-04-07 02:10:45 +02:00
Tobias Rapp
6325bd3717 swresample/rematrix: fix update of channel matrix if input or output layout is undefined
Prefer direct in/out channel count values over channel layout, when
available. Fixes a pan filter bug (ticket #6790).

Signed-off-by: Tobias Rapp <t.rapp@noa-archive.com>
2018-02-19 08:32:25 +01:00
Carl Eugen Hoyos
ff994c2aaa lswr/rematrix: Support s32p.
Fixes ticket #6785.
2017-11-01 01:04:43 +01:00
Carl Eugen Hoyos
8518294558 lswr/swresample: Mention the actually supported formats when erroring out.
Fixes ticket #6779.
2017-10-28 15:11:18 +02:00
James Almer
69b5ce64d2 Merge commit '07a2b155949eb267cdfc7805f42c7b3375f9c7c5'
* commit '07a2b155949eb267cdfc7805f42c7b3375f9c7c5':
  Bump major versions of all libraries

A few API deprecated ~2 years ago or more are also postponed here for
varying reasons.

FF_API_LOWRES:
Since this functionality depends on AVStream->codec, i figure the two can
be removed at the same time in the next bump or so.

FF_API_AVCTX_TIMEBASE:
Couldn't get this one to work. Not just libavcodec but apparently also
libavformat and ffmpeg.c expect AVCodecContext->time_base to be set for
decoding. Upon removal some tests report a different generic stream time
base (like 1/25), and others lose packet duration values. I guess it's
somehow tied to the AVStream->codec clusterfuck.
It can be dealt with alongside FF_API_LAVF_AVCTX in the next bump.

FF_API_OLD_FILTER_OPTS_ERROR:
This one is meant to remain after FF_API_OLD_FILTER_OPTS is removed.
Its purpose is displaying the corrected command line using the new syntax
as a suggestion as part of the error message.

Merged-by: James Almer <jamrial@gmail.com>
2017-10-21 14:57:53 -03:00
Michael Niedermayer
80154b1b3a Bump version for master after 3.4 branchpoint
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-10-11 02:45:37 +02:00
Michael Niedermayer
e1de9eab3a Bump minor versions for branching 3.4
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-10-11 01:23:47 +02:00
Michael Niedermayer
0ac8fce267 swresample/resample: Fix flush refelction length
Reviewed-by: atomnuker
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-08-16 00:54:17 +02:00
hexpointer
3fa8f263ab libswresample: check input to swr_convert_frame for NULL
When 'out' is an AVFrame that does not have buffers preallocated,
swr_convert_frame tries to allocate buffers of the right size. However
in calculating this size it failed to check for whether 'in' is NULL
(requesting that swr's internal buffers are to be flushed).

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-07-08 18:13:43 +02:00
Michael Niedermayer
c578c9c229 libswresample/swresample: remove obsolete code
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-06-27 23:21:53 +02:00
Diego Biurrun
fd502f4f5f build: Generalize yasm/nasm-related variable names
None of them are specific to the YASM assembler.

(Cherry-picked from libav commit 39e208f4d4)

Signed-off-by: James Almer <jamrial@gmail.com>
2017-06-21 17:00:29 -03:00
James Almer
6fdd35a312 Merge commit '92db5083077a8b0f8e1050507671b456fd155125'
* commit '92db5083077a8b0f8e1050507671b456fd155125':
  build: Generate pkg-config files from Make and not from configure
  build: Store library version numbers in .version files

Includes cherry-picked commits 8a34f36593 and
ee164727dd to fix issues.

Changes were also made to retain support for raise_major and build_suffix.

Reviewed-by: ubitux
Merged-by: James Almer <jamrial@gmail.com>
2017-05-04 19:59:30 -03:00
Clément Bœsch
3f17751eeb Merge commit '11a9320de54759340531177c9f2b1e31e6112cc2'
* commit '11a9320de54759340531177c9f2b1e31e6112cc2':
  build: Move build-system-related helper files to a separate subdirectory

"ffbuild" directory name is used instead of "avbuild".

Merged-by: Clément Bœsch <u@pkh.me>
2017-05-03 16:49:12 +02:00
Michael Niedermayer
22b0daa1b3 Bump versions for master after 3.3
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-04-02 19:54:12 +02:00
Michael Niedermayer
e1cc7f83df Bump minor for 3.3
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-04-02 19:49:45 +02:00
Michael Niedermayer
58b867a7cf Bump minor versions for master after release/3.3 branchpoint
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-03-31 13:21:06 +02:00
Michael Niedermayer
fc332f3e29 Bump minor versions for staring release/3.3 branch
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-03-31 13:21:06 +02:00
James Almer
db7a05dab0 swresample/resample: free existing ResampleContext on reinit
Fixes memleak.

Reviewed-by: wm4 <nfxjfg@googlemail.com>
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>
2017-03-21 12:03:44 -03:00
James Almer
2a8a8a2e98 swresample/resample: move resample_free() higher in the file
Also make it more readable while at it.

Signed-off-by: James Almer <jamrial@gmail.com>
2017-03-21 12:02:52 -03:00
Muhammad Faiz
de1308429a swresample/x86/resample: extend resample_double to support avx and fma3
benchmark:
sse2 10.670s
avx   8.763s
fma3  8.380s

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2017-03-19 12:24:41 +07:00
Muhammad Faiz
c52638cca2 swresample/swresample: do not use s32p internally by default when resampling
use fltp when doing s32 -> s32 resampling
because s32p has no simd optimization

benchmark:
old 17.913s
new  7.584s (use fma3)

Reviewed-by: wm4 <nfxjfg@googlemail.com>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2017-03-18 13:57:03 +07:00
Muhammad Faiz
3ba7b47d5c swresample/resample: do not assert compensation_distance on rebuild_filter
when set_compensation is called with zero sample_delta,
compensation does not happen (because dst_incr == ideal_dst_incr)
but compensation_distance is set

regression since 01ebb57c03

Found-by: wm4 <nfxjfg@googlemail.com>
Reviewed-by: wm4 <nfxjfg@googlemail.com>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2017-03-17 09:59:44 +07:00
Muhammad Faiz
1f7eb216b0 swresample/options: enable linear_interp and exact_rational by default
better quality without speedloss

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2017-03-17 00:08:03 +07:00
Muhammad Faiz
6c7a0876fe swresample/swresample: do not reset tsf on swr_alloc_set_opts
so tsf option in aresample will have effect
previously tsf/internal_sample_format had no effect

fate is updated
s32p previously used fltp internally
dblp previously used fltp/dblp internally

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2017-03-13 02:45:36 +07:00
Muhammad Faiz
53a5cea478 swresample/resample: do not allow odd filter_length
except filter_length == 1

odd filter_length gives worse frequency response,
even when compared with shorter filter_length

also makes build_filter simpler

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2017-03-09 13:09:14 +07:00
Muhammad Faiz
61926b6c3e swresample/resample: use uniform normalization
this gives better frequency response

update swresample fate and other fates
that depend on resampling

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2017-03-08 16:09:38 +07:00
Carl Eugen Hoyos
353f509ee3 lswr/rematrix: Remove an aggressive loop optimization.
Fixes undefined behaviour and a gcc warning:
libswresample/rematrix.c:376:47: warning: iteration 64 invokes undefined behavior
2017-02-25 18:53:34 +01:00
Matthieu Bouron
5ef2f4f394 swr/aarch64: add missing ret to ff_resample_common_apply_filter_x8_float_neon 2017-02-16 11:52:32 +01:00
Matthieu Bouron
e109c54a69 swresample/arm: cosmetic fixes 2017-01-13 21:24:25 +01:00
Matthieu Bouron
0265aec565 swresample/aarch64: add ff_resample_common_apply_filter_{x4,x8}_{float,s16}_neon 2017-01-13 21:24:19 +01:00
Muhammad Faiz
2b0112d42d swresample/resample: remove swri_resample function
integrate it inside multiple_resample
allow some calculations to be performed outside loop

Suggested-by: Michael Niedermayer <michael@niedermayer.cc>
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-12-14 06:48:34 +07:00
Muhammad Faiz
6a8c0d8357 swresample/resample: do not allow negative dst_size return value
This should fix Ticket6012

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-12-14 00:43:44 +07:00
Michael Niedermayer
65e33d8e23 swresample/resample_template: Add filter values in parallel
This is faster 2871 -> 2189  cycles for int16 matrixbench -> 23456hz
Fixes a integer overflow in a artificial corner case
Fixes part of 668007-media

Found-by: Matt Wolenetz <wolenetz@google.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-12-10 02:44:21 +01:00
Michael Niedermayer
34db650784 swresample/resample_template: Reorder operations to avoid one addition
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-12-10 02:05:17 +01:00
Michael Niedermayer
b3928a1cc6 swresample/swresample: Check count before memcpy()
Fixes undefined operation
Fixes part of 668007-media

Found-by: Matt Wolenetz <wolenetz@google.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-12-10 02:05:17 +01:00
Muhammad Faiz
01ebb57c03 swresample/resample: do not rebuild filter when sample_delta is zero
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-12-04 01:32:26 +07:00
Muhammad Faiz
da34e4e132 swresample/soxr: fix invalid use of linear_interp
give very bad quality for soxr resampler.
linear_interp is intended for  using linear interpolation
between filter bank so quality will be better.

i guess this is misunderstood as 'do not use filter bank,
but directly interpolate linearly between samples'.

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-11-26 05:52:24 +07:00
Muhammad Faiz
06f94149c6 swresample/resample: optimize exact_rational=on:linear_interp=on case
separate dsp.resample to dsp.resample_common and dsp.resample_linear
and choose to call faster resample_common even when linear_interp=on
when c->frac and c->dst_incr_mod are both zero

speed up resampling when exact_rational and linear_interp are both
enabled because exact_rational force c->frac and c->dst_incr_mod to
be zero when soft compensation does not happen

benchmark on exact_rational=on:linear_interp=on
        old     new
real    8.432s  5.097s
user    7.679s  4.989s
sys     0.125s  0.107s

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-11-25 03:22:04 +07:00
Michael Niedermayer
1609935b6c Bump minor versions after 3.2 branchpoint to seperate release
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-10-26 20:52:42 +02:00
Michael Niedermayer
3f3025205f Bump minor versions for 3.2
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-10-26 20:52:42 +02:00
Vodyannikov Aleksandr
9445e7e6d5 swresample/rematrix: Fix float part of swr_set_matrix()
Fixes Ticket #5897.

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-10-26 19:27:22 +02:00
Muhammad Faiz
acd74f9200 swresample/resample: fix return value of build_filter
return AVERROR code on error

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-10-18 22:36:01 +07:00
Michael Niedermayer
fd902510ac swr: Update version & APIChanges for swr_build_matrix()
Found-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-09-27 15:26:13 +02:00
Michael Niedermayer
23c0779cda swresample: Add swr_build_matrix()
API and Doxy documentation is taken from avresample_build_matrix()
Fixes: Ticket5780

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-09-27 12:54:00 +02:00
Michael Niedermayer
740f5105d5 swresample: Use double and float for matrixes for best quality and speed
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-09-27 12:53:25 +02:00
Paul B Mahol
9876d8fc6d swresample: add int64 sample format 2016-08-18 15:30:05 +02:00
Michael Niedermayer
30b2611ed3 swresample: Skip over dither steps if dithering scale is 0
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-08-18 11:52:11 +02:00
Michael Niedermayer
946acacdcd swresample: move dither init up
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-08-18 11:50:14 +02:00
Timothy Gu
58c7bf789f doxygen: Standardize root-level modules 2016-08-02 22:15:25 -07:00
Matthieu Bouron
0acc170aad Merge commit '535a742c2695a9e0c586b50d7fa76e318232ff24'
* commit '535a742c2695a9e0c586b50d7fa76e318232ff24':
  build: Change structure of the linker version script templates

Merged-by: Matthieu Bouron <matthieu.bouron@stupeflix.com>
2016-06-27 17:56:47 +02:00
Clément Bœsch
a9eda4b260 swr: fix time.h include 2016-06-22 14:00:08 +02:00
Clément Bœsch
5d48e4eafa Merge commit 'a6a750c7ef240b72ce01e9653343a0ddf247d196'
* commit 'a6a750c7ef240b72ce01e9653343a0ddf247d196':
  tests: Move all test programs to a subdirectory

Merged-by: Clément Bœsch <clement@stupeflix.com>
2016-06-22 13:44:34 +02:00
Muhammad Faiz
6031e5d1af swresample/x86: add support for exact_rational
phase_shift and phase_mask is removed
generally exact_rational=on is faster than exact_rational=off

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-06-21 05:18:21 +07:00
Muhammad Faiz
7f1b503ec2 swresample/resample: do not increase phase_count on exact_rational
high phase_count is only useful when dst_incr_mod is non zero
in other word, it is only useful on soft compensation

on init, it will build filter with low phase_count
but when soft compensation is enabled, rebuild filter
with high phase_count

this approach saves lots of memory

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-06-17 16:02:49 +07:00
Muhammad Faiz
ee575acb8c swresample/resample: add support for odd phase_count
because exact_rational does not guarantee
that phase_count is even

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-06-17 16:00:13 +07:00
Muhammad Faiz
b8c6e5a661 swresample: add exact_rational option
give high quality resampling
as good as with linear_interp=on
as fast as without linear_interp=on
tested visually with ffplay
ffplay -f lavfi "aevalsrc='sin(10000*t*t)', aresample=osr=48000, showcqt=gamma=5"
ffplay -f lavfi "aevalsrc='sin(10000*t*t)', aresample=osr=48000:linear_interp=on, showcqt=gamma=5"
ffplay -f lavfi "aevalsrc='sin(10000*t*t)', aresample=osr=48000:exact_rational=on, showcqt=gamma=5"

slightly speed improvement
for fair comparison with -cpuflags 0
audio.wav is ~ 1 hour 44100 stereo 16bit wav file
ffmpeg -i audio.wav -af aresample=osr=48000 -f null -
        old         new
real    13.498s     13.121s
user    13.364s     12.987s
sys      0.131s      0.129s

linear_interp=on
        old         new
real    23.035s     23.050s
user    22.907s     22.917s
sys      0.119s     0.125s

exact_rational=on
real    12.418s
user    12.298s
sys      0.114s

possibility to decrease memory usage if soft compensation is ignored

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
2016-06-13 12:36:01 +07:00
Michael Niedermayer
feeb3a9261 swresample/resample: Fix division by 0 with tap_count=1
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-05-16 05:10:21 +02:00
Michael Niedermayer
2f76157eb0 swresample/rematrix: Use clipping s16 rematrixing if overflows are possible
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-05-15 22:25:34 +02:00
Michael Niedermayer
7fe81bc4f8 swresample/rematrix: Use error diffusion to avoid error in the DC component of the matrix
This fixes the sum of the integer coefficients ending up summing to a value
larger than the value representing unity.

This issue occurs with qN0.dts when converting to stereo

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-05-15 18:36:53 +02:00
Matthieu Bouron
f6265a5cbc swresample/arm: add ff_resample_common_apply_filter_{x4,x8}_{float,s16}_neon 2016-05-13 21:13:46 +02:00
Michael Niedermayer
914ad90edd swresample/swresample: Remove "less than" comparissions of enums
Found-by: wm4
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-03-22 14:20:12 +01:00
James Almer
70d685a77f x86: use the new helper macros where useful
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: James Almer <jamrial@gmail.com>
2016-02-14 20:00:21 -03:00
Timothy Gu
180f9a0958 all: Make header guard names consistent 2016-01-31 15:44:11 -08:00
Ganesh Ajjanagadde
26937fb416 swr/resample: use av_clip_int16 instead of av_clip
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-12-24 11:29:52 -08:00
Clément Bœsch
c1f114a8c4 swresample: use AV_OPT_TYPE_BOOL for linear_interp and cheby options 2015-12-04 15:43:33 +01:00
Ganesh Ajjanagadde
0bd0af6e68 swresample/resample: remove redundant L for floating literal
It is inherently double precision, and 1.0 is perfectly represented
anyway.

Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-11-15 10:26:43 -05:00
Michael Niedermayer
351e625d60 swresample/resample: increase precision for compensation
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2015-11-11 18:17:18 +01:00
Ganesh Ajjanagadde
cf491a925e swresample/resample: speed up Blackman Nuttall filter
This may be a slightly surprising optimization, but is actually based on
an understanding of how math libraries compute trigonometric functions.
Explanation is given here so that future development uses libm more effectively
across the codebase.

All libm's essentially compute transcendental functions via some kind of
polynomial approximation, be it Taylor-Maclaurin or Chebyshev.
Correction terms are added via polynomial correction factors when needed
to squeeze out the last bits of accuracy. Lookup tables are also
inserted strategically.

In the case of trigonometric functions, periodicity is exploited via
first doing a range reduction to an interval around zero, and then using
some polynomial approximation.

This range reduction is the most natural way of doing things - else one
would need polynomials for ranges in different periods which makes no
sense whatsoever.

To avoid the need for the range reduction, it is helpful to feed in
arguments as close to the origin as possible for the trigonometric
functions. In fact, this also makes sense from an accuracy point of view:
IEEE floating point has far more resolution for small numbers than big ones.

This patch does this for the Blackman-Nuttall filter, and yields a
non-negligible speedup.

Sample benchmark (x86-64, Haswell, GNU/Linux)
test: fate-swr-resample-dblp-2626-44100
old:
18893514 decicycles in build_filter (loop 1000),     256 runs,      0 skips
18599863 decicycles in build_filter (loop 1000),     512 runs,      0 skips
18445574 decicycles in build_filter (loop 1000),    1000 runs,     24 skips

new:
16290697 decicycles in build_filter (loop 1000),     256 runs,      0 skips
16267172 decicycles in build_filter (loop 1000),     512 runs,      0 skips
16251105 decicycles in build_filter (loop 1000),    1000 runs,     24 skips

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-11-09 18:41:32 -05:00
Ganesh Ajjanagadde
b87ca4bf25 swresample/resample: speed up upsampling by precomputing sines
When upsampling, factor is set to 1 and sines need to be evaluated only
once for each phase, and the complexity should not depend on the number
of filter taps. This does the desired precomputation, yielding
significant speedups. Hard guarantees on the gain are not possible, but gains
themselves are obvious and are illustrated below.

Sample benchmark (x86-64, Haswell, GNU/Linux)
test: fate-swr-resample-dblp-2626-44100
old:
29161085 decicycles in build_filter (loop 1000),     256 runs,      0 skips
28821467 decicycles in build_filter (loop 1000),     512 runs,      0 skips
28668201 decicycles in build_filter (loop 1000),    1000 runs,     24 skips

new:
14351936 decicycles in build_filter (loop 1000),     256 runs,      0 skips
14306652 decicycles in build_filter (loop 1000),     512 runs,      0 skips
14299923 decicycles in build_filter (loop 1000),    1000 runs,     24 skips

Note that this does not statically allocate the sin lookup table. This
may be done for the default 1024 phases, yielding a 512*8 = 4kB array
which should be small enough.
This should yield a small improvement. Nevertheless, this is separate from
this patch, is more ambiguous due to the binary increase, and requires a
lut to be generated offline.

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-11-09 18:41:03 -05:00
Ganesh Ajjanagadde
a5202bc968 swresample/resample: improve bessel function accuracy and speed
This improves accuracy for the bessel function at large arguments, and this in turn
should improve the quality of the Kaiser window. It also improves the
performance of the bessel function and hence build_filter by ~ 20%.
Details are given below.

Algorithm: taken from the Boost project, who have done a detailed
investigation of the accuracy of their method, as compared with e.g the
GNU Scientific Library (GSL):
http://www.boost.org/doc/libs/1_52_0/libs/math/doc/sf_and_dist/html/math_toolkit/special/bessel/mbessel.html.
Boost source code (also cited and licensed in the code):
https://searchcode.com/codesearch/view/14918379/.

Accuracy: sample values may be obtained as follows. i0 denotes the old bessel code,
i0_boost the approach here, and i0_real an arbitrary precision result (truncated) from Wolfram Alpha:
type "bessel i0(6.0)" to reproduce. These are evaluation points that occur for
the default kaiser_beta = 9.

Some illustrations:
bessel(8.0)
i0      (8.000000) = 427.564115721804739678191254
i0_boost(8.000000) = 427.564115721804796521610115
i0_real (8.000000) = 427.564115721804785177396791

bessel(6.0)
i0      (6.000000) = 67.234406976477956163762428
i0_boost(6.000000) = 67.234406976477970374617144
i0_real (6.000000) = 67.234406976477975326188025

Reason for accuracy: Main accuracy benefits come at larger bessel arguments, where the
Taylor-Maclaurin method is not that good: 23+ iterations
(at large arguments, since the series is about 0) can cause
significant floating point error accumulation.

Benchmarks: Obtained on x86-64, Haswell, GNU/Linux via a loop calling
build_filter 1000 times:
test: fate-swr-resample-dblp-44100-2626

new:
995894468 decicycles in build_filter(loop 1000),     256 runs,      0 skips
1029719302 decicycles in build_filter(loop 1000),     512 runs,      0 skips
984101131 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

old:
1250020763 decicycles in build_filter(loop 1000),     256 runs,      0 skips
1246353282 decicycles in build_filter(loop 1000),     512 runs,      0 skips
1220017565 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

A further ~ 5% may be squeezed by enabling -ftree-vectorize. However,
this is a separate issue from this patch.

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-11-08 21:18:16 -05:00
Ganesh Ajjanagadde
1bed09a30e swresample: allow double precision beta value for the Kaiser window
Kaiser windows inherently don't require beta to be an integer. This was
an arbitrary restriction. Moreover, soxr does not require it, and in
fact often estimates beta to a non-integral value.

Thus, this patch allows greater flexibility for swresample clients.
Micro version is updated.

Reviewed-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-11-08 21:11:07 -05:00
Ganesh Ajjanagadde
c8780822ba swresample/resample: speed up build_filter for Blackman-Nuttall filter
This uses the trigonometric double and triple angle formulae to avoid
repeated (expensive) evaluation of libc's cos().

Sample benchmark (x86-64, Haswell, GNU/Linux)
test: fate-swr-resample-dblp-44100-2626
old:
1104466600 decicycles in build_filter(loop 1000),     256 runs,      0 skips
1096765286 decicycles in build_filter(loop 1000),     512 runs,      0 skips
1070479590 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

new:
588861423 decicycles in build_filter(loop 1000),     256 runs,      0 skips
591262754 decicycles in build_filter(loop 1000),     512 runs,      0 skips
577355145 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

This results in small differences with the old expression:
difference (worst case on [0, 2*M_PI]), argmax 0.008:
max diff (relative): 0.000000000000157289807188
blackman_old(0.008): 0.000363951585488813192382
blackman_new(0.008): 0.000363951585488755946507

These are judged to be insignificant for the performance gain. PSNR to
reference file is unchanged up to second decimal point for instance.

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-11-05 21:52:40 -05:00
Ganesh Ajjanagadde
9bec6d71a2 swresample/resample: speed up build_filter by 50%
This speeds up build_filter by ~ 50%. This gain should be pretty
consistent across all architectures and platforms.

Essentially, this relies on a observation that the filters have some
even/odd symmetry that may be exploited during the construction of the
polyphase filter bank. In particular, phases (scaled to [0, 1]) in [0.5, 1] are
easily derived from [0, 0.5] and expensive reevaluation of function
points are unnecessary. This requires some rather annoying even/odd
bookkeeping as can be seen from the patch.

I vaguely recall from signal processing theory more general symmetries allowing even greater
optimization of the construction. At a high level, "even functions"
correspond to 2, and one can imagine variations. Nevertheless, for the sake
of some generality and because of existing filters, this is all that is
being exploited.

Currently, this patch relies on phase_count being even or (trivially) 1,
though this is not an inherent limitation to the approach. This
assumption is safe as phase_count is 1 << phase_bits, and is hence a
power of two. There is no way for user API to set it to a nontrivial odd
number. This assumption has been placed as an assert in the code.

To repeat, this assumes even symmetry of the filters, which is the most common
way to get generalized linear phase anyway and is true of all currently
supported filters.

As a side note, accuracy should be identical or perhaps slightly better
due to this "forcing" filter symmetries leading to a better phase
characteristic. As before, I can't test this claim easily, though it may
be of interest.

Patch tested with FATE.

Sample benchmark (x86-64, Haswell, GNU/Linux):

test: swr-resample-dblp-44100-2626

new:
527376779 decicycles in build_filter(loop 1000),     256 runs,      0 skips
524361765 decicycles in build_filter(loop 1000),     512 runs,      0 skips
516552574 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

old:
974178658 decicycles in build_filter(loop 1000),     256 runs,      0 skips
972794408 decicycles in build_filter(loop 1000),     512 runs,      0 skips
954350046 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

Note that lower level optimizations are entirely possible, I focussed on
getting the high level semantics correct. In any case, this should
provide a good foundation.

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-11-04 17:05:57 -05:00
wm4
80580bb240 swr: do not reject channel layouts that use channel 63
Channel layouts are essentially uint64_t, and every value is valid.
2015-10-28 19:25:49 +01:00
Ganesh Ajjanagadde
c7131762c0 all: add const-correctness to qsort comparators
This adds const-correctness when needed for the comparators.

Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-10-25 10:07:20 -04:00
Ganesh Ajjanagadde
8507b98c10 avfilter,swresample,swscale: use fabs, fabsf instead of FFABS
It is well known that fabs and fabsf are at least as fast and sometimes
faster than the FFABS macro, at least on the gcc+glibc combination.
For instance, see the reference:
http://patchwork.sourceware.org/patch/6735/.
This was a patch to glibc in order to remove their usages of a macro.

The reason essentially boils down to fabs using the __builtin_fabs of
the compiler, while FFABS needs to infer to not use a branch and to
simply change the sign bit. Usually the inference works, but sometimes
it does not. This may be easily checked by looking at the asm.

This also has the added benefit of reducing macro usage, which has
problems with side-effects.

Note that avcodec is not handled here, as it is huge and
most things there are integer arithmetic anyway.

Tested with FATE.

Reviewed-by: Clément Bœsch <u@pkh.me>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2015-10-22 16:13:26 -04:00