summaryrefslogtreecommitdiffstats
path: root/libswresample/resample.c
Commit message (Collapse)AuthorAgeFilesLines
* swr/resample: use av_clip_int16 instead of av_clipGanesh Ajjanagadde2015-12-241-2/+2
| | | | | Reviewed-by: Michael Niedermayer <michael@niedermayer.cc> Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
* swresample/resample: remove redundant L for floating literalGanesh Ajjanagadde2015-11-151-2/+2
| | | | | | | It is inherently double precision, and 1.0 is perfectly represented anyway. Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
* swresample/resample: increase precision for compensationMichael Niedermayer2015-11-111-0/+4
| | | | Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
* swresample/resample: speed up Blackman Nuttall filterGanesh Ajjanagadde2015-11-091-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
* swresample/resample: speed up upsampling by precomputing sinesGanesh Ajjanagadde2015-11-091-4/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
* swresample/resample: improve bessel function accuracy and speedGanesh Ajjanagadde2015-11-081-27/+98
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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>
* swresample: allow double precision beta value for the Kaiser windowGanesh Ajjanagadde2015-11-081-2/+2
| | | | | | | | | | | | | 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>
* 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>
OpenPOWER on IntegriCloud