summaryrefslogtreecommitdiffstats
path: root/libswresample/resample.c
Commit message (Collapse)AuthorAgeFilesLines
* swresample/resample: speed up build_filter for Blackman-Nuttall filterGanesh Ajjanagadde2015-11-051-2/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
* swresample/resample: speed up build_filter by 50%Ganesh Ajjanagadde2015-11-041-4/+40
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
* swresample/resample: manually unroll the main loop in bessel()Michael Niedermayer2015-10-071-3/+5
| | | | | | About 10% faster Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
* swresample/resample: merge first iteration into init in bessel()Michael Niedermayer2015-10-071-3/+4
| | | | | | speedup of about 1% Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
* swresample/resample: fix typosMichael Niedermayer2015-06-041-2/+2
| | | | | Found-by: wm4 <nfxjfg@googlemail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample: Add swr_get_out_samples()Michael Niedermayer2015-06-041-0/+20
| | | | | | Previous version reviewed-by: Pavel Koshevoy <pkoshevoy@gmail.com> Previous version reviewed-by: wm4 <nfxjfg@googlemail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample/resample: Fix undefined shiftsMichael Niedermayer2015-03-141-1/+1
| | | | | | Found-by: Clang -fsanitize=shift Reported-by: Thierry Foucu <tfoucu@google.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample/resample: fix invert_initial_buffer() after flushMichael Niedermayer2014-10-161-3/+3
| | | | | | | Fixes: asan_heap-uaf_2071250_7_139.ogg Fixes: assertion failure Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: initialize only the necessary resample dsp functionsJames Almer2014-07-041-8/+2
| | | | | Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: rename swresample_dsp init functions to swri_resample_dspJames Almer2014-07-021-1/+1
| | | | | | | The swresample_ prefix is not for internal functions Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: move dst_size == 0 handling outside DSP function.Ronald S. Bultje2014-06-281-3/+7
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: remove div/mod from DSP functions.Ronald S. Bultje2014-06-181-8/+15
| | | | | | Also fix a bug with resample_compensation resetting dst_incr. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: split out DSP functions.Ronald S. Bultje2014-06-141-100/+49
| | | | | | | | | | DSP bits of swri_resample go into their own mini-DSP functions; DSP init goes from a per-call branch in multiple_resample to a proper DSP init routine; x86 bits go into x86/; swri_resample() moves out of resample_template.c into resample.c because it's independent of DSP code or sample type; multiple_resample() is simplified. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample/resample: replace assert by av_assertMichael Niedermayer2014-06-141-1/+1
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: handle initial negative sample index outside DSP function.Ronald S. Bultje2014-06-141-0/+46
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: handle 64bit overflow check in multiple_resample().Ronald S. Bultje2014-06-091-0/+2
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: move compensation_distance handling to swri_resample caller.Ronald S. Bultje2014-06-021-0/+10
| | | | | | | | | | | I think there's an off-by-one in terms of the switchpoint where we switch from dst_incr to ideal_dst_incr, I don't think that's a massive issue, but just be aware of that. It's probably trivial to prevent but I don't care. Signed-off-by: Michael Niedermayer <michaelni@gmx.at> I could not reproduce any off by 1 error, results are bit exact (michael)
* swresample: add swri_resample_float_avxJames Almer2014-05-161-0/+10
| | | | | Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample: add swri_resample_double_sse2James Almer2014-04-251-0/+8
| | | | | Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample/resample: use av_malloc_array() where appropriateMichael Niedermayer2014-04-081-1/+1
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample/resample: Limit filter lengthMichael Niedermayer2014-04-081-0/+5
| | | | | | | | | Related to CID1197063 The limit choosen is arbitrary and much larger than what makes sense. It avoids the need for checking arithmetic operations with the length for overflow Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample: add swri_resample_float_sseJames Almer2014-03-201-0/+10
| | | | | | | At least two times faster than the C version. Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample: change COMMON_CORE_INT16 asm from SSSE3 to SSE2James Almer2014-03-181-5/+5
| | | | | | | | | pshuf+paddd is slightly faster than phaddd. The real gain is in pre-ssse3 processors like AMD K8 and K10, which get a big boost in performance compared to the mmxext version Signed-off-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swresample: replace 2 av_free() by av_freep()Michael Niedermayer2013-09-161-1/+1
| | | | | | avoids leaving stale pointers in memory Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr/resample: fix filter rounding and cliping for s32Michael Niedermayer2013-02-041-1/+1
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr/ build_filter: use av_calloc() fix buffer overflowMichael Niedermayer2013-01-271-1/+1
| | | | | | | Fixes integer & buffer overflow Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* lswr: Improve default resampler's default parametersAlexander Strasser2013-01-041-1/+1
| | | | | | | | | | | | | | After making some blind tests on a small collection of music samples for home usage. It turned out that the default cutoff was too low. The impact of filter_size was not clearly distinguishable (the results were on the edge) with the music samples but turned out to be clearly audible in some synthetic samples. Thanks to Daniel for helping out with the listening tests. Signed-off-by: Alexander Strasser <eclipse7@gmx.net>
* swr: Add SOX resampler supportRob Sykes2012-12-111-1/+2
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: add a lowpass default so that each Resampler can have its own default.Rob Sykes2012-12-111-1/+2
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: move flush into ResamplerMichael Niedermayer2012-12-111-0/+17
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: Add API to make resample engine selectable.Rob Sykes2012-12-111-30/+19
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr/resample: fix SSSE3 included unconditionally.Clément Bœsch2012-11-151-0/+2
| | | | 10l Regression since 8ea88339.
* swr/resample: move templating parameters to template itself.Clément Bœsch2012-11-151-112/+15
| | | | | | | | | It has various benefits such as allowing some refactoring, clarifying the code in the inclusion part, and making the template understandable in standalone. This commit is based on the templating method used by Justin Ruggles for libavresample.
* swri_resample_init: unsupported sample formats are an internal error.Michael Niedermayer2012-10-111-1/+1
| | | | | | | This condition cannot happen. Fixes CID733802 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr/resample: mark mm_flags as potentially unusedMichael Niedermayer2012-09-131-1/+1
| | | | | | They are unused when asm is disabled Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* libswr: remove redundant ARCH_X86, MMX* implicates X86Michael Niedermayer2012-09-071-3/+3
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swsresample: Fix unprotected inline asmDerek Buitenhuis2012-09-071-2/+2
| | | | | Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr/resample: update SSSE3 flag to new nameMichael Niedermayer2012-09-011-2/+2
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* bessel: check that the function terminates as expected by av_assert2().Michael Niedermayer2012-08-091-0/+1
| | | | | | A clear abort is better than wrong output and a possible crash. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: resampling: add filter type and Kaiser window beta to AVOptionsJustin Ruggles2012-07-231-13/+20
|
* swr: fix MMX resample code, add emmsMichael Niedermayer2012-06-301-3/+7
| | | | | | Fixes Ticket1495 Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: fix compilation with ancient toolchain that doesnt support SSSE3Michael Niedermayer2012-06-281-1/+6
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: MMX2 & SSSE3 int16 resample coreMichael Niedermayer2012-06-281-4/+60
| | | | | | about 4 times faster Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: introduce filter_alloc in preparation of SIMD resample optimisationsMichael Niedermayer2012-06-191-9/+11
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: add swr_get_delay() to find the exact delay the swresampler introduces.Michael Niedermayer2012-05-181-0/+15
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: change sample format representation so as to maintain the planer/packed ↵Michael Niedermayer2012-04-281-12/+12
| | | | | | distinction. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: simplify code by using av_get_bytes_per_sample()Michael Niedermayer2012-04-111-6/+2
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* resample: support double precission resamplingMichael Niedermayer2012-04-101-0/+29
| | | | | | | This commit is dedicated to the audiophiles who can hear it when a needle is dropped on the moon. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* swr: support float & int32 in the resamplerMichael Niedermayer2012-04-101-126/+102
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* resample: update copyright years, they where incorrect.Michael Niedermayer2012-04-101-1/+1
| | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
OpenPOWER on IntegriCloud