- 27 11月, 2015 6 次提交
-
-
由 Ganesh Ajjanagadde 提交于
This speeds up aac_tablegen to a ludicruous degree (~97%), i.e to the point where it can be argued that runtime initialization can always be done instead of hard-coded tables. The only cost is essentially a trivial increase in the stack size. Even if one does not care about this, the patch also improves accuracy as detailed below. Performance: Benchmark obtained by looping 10^4 times over ff_aac_tableinit. Sample benchmark (x86-64, Haswell, GNU/Linux): old: 1295292 decicycles in ff_aac_tableinit, 512 runs, 0 skips 1275981 decicycles in ff_aac_tableinit, 1024 runs, 0 skips 1272932 decicycles in ff_aac_tableinit, 2048 runs, 0 skips 1262164 decicycles in ff_aac_tableinit, 4096 runs, 0 skips 1256720 decicycles in ff_aac_tableinit, 8192 runs, 0 skips new: 21112 decicycles in ff_aac_tableinit, 511 runs, 1 skips 21269 decicycles in ff_aac_tableinit, 1023 runs, 1 skips 21352 decicycles in ff_aac_tableinit, 2043 runs, 5 skips 21386 decicycles in ff_aac_tableinit, 4080 runs, 16 skips 21299 decicycles in ff_aac_tableinit, 8173 runs, 19 skips Accuracy: The previous code was resulting in needless loss of accuracy due to the pow being called in succession. As an illustration of this: ff_aac_pow34sf_tab[3] old : 0.000000000007598092294225 new : 0.000000000007598091426864 real: 0.000000000007598091778545 truncated to float old : 0.000000000007598092294225 new : 0.000000000007598091426864 real: 0.000000000007598091426864 showing that the old value was not correctly rounded. This affects a large number of elements of the array. Patch tested with FATE. Reviewed-by: NRostislav Pehlivanov <atomnuker@gmail.com> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Matthieu Bouron 提交于
Avoid decoding a frame to get the codec parameters while the codec supports FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM. This is particulary useful to avoid decoding twice images (once in avformat_find_stream_info and once when the actual decode is made).
-
由 Rostislav Pehlivanov 提交于
This hugely reduces the echo which was introduced with the previous commit (though likely because previously everything was broken). Makes LTP actually worthwhile now. Signed-off-by: NRostislav Pehlivanov <atomnuker@gmail.com>
-
由 Rostislav Pehlivanov 提交于
This commit attempts to mirror what the decoder does more closely in addition to fixing some shortcomings.
-
由 Ganesh Ajjanagadde 提交于
Should fix issues with ppc, tested by bug reporter. Reported-by: NJohn Warburton <john@johnwarburton.net> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Matthieu Bouron 提交于
-
- 26 11月, 2015 16 次提交
-
-
由 Ganesh Ajjanagadde 提交于
Reviewed-by: NMichael Niedermayer <michael@niedermayer.cc> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
This removes wasteful pow(x, 2.0) that although not terribly important for speed, is still useless. Reviewed-by: NPaul B Mahol <onemda@gmail.com> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
Gain computation for various curves was being done in a needlessly inaccurate fashion. Of course these are all subjective curves, but when a curve is advertised to the user, it should be matched as closely as possible within the limitations of libm. In particular, the constants kept here were pretty inaccurate for double precision. Speed improvements are mainly due to the avoidance of pow, the most notorious of the libm functions in terms of performance. To be fair, it is the GNU libm that is among the worst, but it is not really GNU libm's fault since others simply yield a higher error as measured in ULP. "Magic" constants are also accordingly documented, since they take at least a minute of thought for a casual reader. Reviewed-by: NPaul B Mahol <onemda@gmail.com> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
This is a trivial rewrite of the loops that results in better prefetching and associated cache efficiency. Essentially, the problem is that modern prefetching logic is based on finite state Markov memory, a reasonable assumption that is used elsewhere in CPU's in for instance branch predictors. Surrounding loops all iterate forward through the array, making the predictor think of prefetching in the forward direction, but the intermediate loop is unnecessarily in the backward direction. Speedup is nontrivial. Benchmarks obtained by 10^6 iterations within solve_lls, with START/STOP_TIMER. File is tests/data/fate/flac-16-lpc-cholesky.err. Hardware: x86-64, Haswell, GNU/Linux. new: 17291 decicycles in solve_lls, 2096706 runs, 446 skips 17255 decicycles in solve_lls, 4193657 runs, 647 skips 17231 decicycles in solve_lls, 8384997 runs, 3611 skips 17189 decicycles in solve_lls,16771010 runs, 6206 skips 17132 decicycles in solve_lls,33544757 runs, 9675 skips 17092 decicycles in solve_lls,67092404 runs, 16460 skips 17058 decicycles in solve_lls,134188213 runs, 29515 skips old: 18009 decicycles in solve_lls, 2096665 runs, 487 skips 17805 decicycles in solve_lls, 4193320 runs, 984 skips 17779 decicycles in solve_lls, 8386855 runs, 1753 skips 18289 decicycles in solve_lls,16774280 runs, 2936 skips 18158 decicycles in solve_lls,33548104 runs, 6328 skips 18420 decicycles in solve_lls,67091793 runs, 17071 skips 18310 decicycles in solve_lls,134187219 runs, 30509 skips Reviewed-by: NMichael Niedermayer <michael@niedermayer.cc> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Paul B Mahol 提交于
Signed-off-by: NPaul B Mahol <onemda@gmail.com>
-
由 Timothy Gu 提交于
Silences warning when building without assertions Signed-off-by: NClaudio Freire <klaussfreire@gmail.com>
-
由 Claudio Freire 提交于
In some conditions, where the first band was being zeroed mainly, the wrong global gain scalefactor would be written to the stream since it's always taken from the first band regardless of whether it's been marked as zero or not. So, always make sure it contians something useful.
-
由 Claudio Freire 提交于
When both M/S coding and PNS are enabled, scalefactors and coding books would be mistakenly clobbered when setting the M/S flag on PNS'd bands. The flag needs to be set to signal the generation of correlated noise, but the scalefactors, coefficients and the coding books need to be kept intact.
-
由 Timothy Gu 提交于
-
由 Rodger Combs 提交于
-
由 Michael Niedermayer 提交于
It appears rets_count is redundant Signed-off-by: NMichael Niedermayer <michael@niedermayer.cc>
-
由 James Almer 提交于
-
由 Paul B Mahol 提交于
Signed-off-by: NPaul B Mahol <onemda@gmail.com>
-
由 Paul B Mahol 提交于
Signed-off-by: NPaul B Mahol <onemda@gmail.com>
-
由 Paul B Mahol 提交于
Signed-off-by: NPaul B Mahol <onemda@gmail.com>
-
由 Stefano Sabatini 提交于
-
- 25 11月, 2015 15 次提交
-
-
由 Paul B Mahol 提交于
Signed-off-by: NPaul B Mahol <onemda@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
Commit 14ea4151 had a bug in that the conversion of the uint64_t result to an int (the return signature) would lead to implementation defined behavior, and in this case simply returned 0 for NAN. A fix via AND'ing the result with 1 does the trick, simply by ensuring a 0 or 1 return value. Patch tested with FATE on x86-64, GNU/Linux by forcing the compatibility code via an ifdef hack suggested by Michael. Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Timothy Gu 提交于
-
由 Timothy Gu 提交于
-
由 Ganesh Ajjanagadde 提交于
lrintf is anyway used, suggesting we only care up to floating precision. Rurthermore, there is a compat hack in avutil/libm for this function, and it is used in avcodec/aacps_tablegen.h. This yields a non-negligible speedup. Sample benchmark: x86-64, Haswell, GNU/Linux: old (draw_mandelbrot): 274635709 decicycles in draw_mandelbrot, 256 runs, 0 skips 300287046 decicycles in draw_mandelbrot, 512 runs, 0 skips 371819935 decicycles in draw_mandelbrot, 1024 runs, 0 skips 336663765 decicycles in draw_mandelbrot, 2048 runs, 0 skips 581851016 decicycles in draw_mandelbrot, 4096 runs, 0 skips new (draw_mandelbrot): 269882717 decicycles in draw_mandelbrot, 256 runs, 0 skips 296359285 decicycles in draw_mandelbrot, 512 runs, 0 skips 370076599 decicycles in draw_mandelbrot, 1024 runs, 0 skips 331478354 decicycles in draw_mandelbrot, 2048 runs, 0 skips 571904318 decicycles in draw_mandelbrot, 4096 runs, 0 skips Reviewed-by: NMichael Niedermayer <michael@niedermayer.cc> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
This rewrites into a similar expression avoiding sqrt. Similarity is assured since sqrt(x^2 + y^2)/(x+y) lies in [1/sqrt(2), 1] for x, y > 0. Tested on x86-64, Haswell, GNU/Linux. Command: ffmpeg -f lavfi -i mandelbrot -f null - old (draw_mandelbrot): 277625266 decicycles in draw_mandelbrot, 256 runs, 0 skips 304527322 decicycles in draw_mandelbrot, 512 runs, 0 skips 377593582 decicycles in draw_mandelbrot, 1024 runs, 0 skips 338539499 decicycles in draw_mandelbrot, 2048 runs, 0 skips 583630357 decicycles in draw_mandelbrot, 4096 runs, 0 skips new (draw_mandelbrot): 274635709 decicycles in draw_mandelbrot, 256 runs, 0 skips 300287046 decicycles in draw_mandelbrot, 512 runs, 0 skips 371819935 decicycles in draw_mandelbrot, 1024 runs, 0 skips 336663765 decicycles in draw_mandelbrot, 2048 runs, 0 skips 581851016 decicycles in draw_mandelbrot, 4096 runs, 0 skips Reviewed-by: NMichael Niedermayer <michael@niedermayer.cc> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
Reviewed-by: NRostislav Pehlivanov <atomnuker@gmail.com> Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
See e.g https://stackoverflow.com/questions/1666353/are-typedef-and-define-the-same-in-c for rationale. Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Ganesh Ajjanagadde 提交于
See e.g https://stackoverflow.com/questions/1666353/are-typedef-and-define-the-same-in-c for rationale. Signed-off-by: NGanesh Ajjanagadde <gajjanagadde@gmail.com>
-
由 Timothy Gu 提交于
-
由 Marton Balint 提交于
This option can be used to select useful frames from an ffconcat file which is using inpoints and outpoints but where the source files are not intra frame only. Reviewed-by: NStefano Sabatini <stefasab@gmail.com> Signed-off-by: NMarton Balint <cus@passwd.hu>
-
由 Marton Balint 提交于
Reviewed-by: NNicolas George <george@nsup.org> Signed-off-by: NMarton Balint <cus@passwd.hu>
-
由 Marton Balint 提交于
If duration is still AV_NOPTS_VALUE when opening the next file, we can assume that outpoint is not set. Reviewed-by: NNicolas George <george@nsup.org> Signed-off-by: NMarton Balint <cus@passwd.hu>
-
由 Marton Balint 提交于
Reviewed-by: NNicolas George <george@nsup.org> Signed-off-by: NMarton Balint <cus@passwd.hu>
-
由 Michael Niedermayer 提交于
Fixes out of array access Fixes: 1430e9c43fae47a24c179c7c54f94918/signal_sigsegv_421427_2049_f2192b6829ab6e0eefcb035329c03c60.264 Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind Signed-off-by: NMichael Niedermayer <michael@niedermayer.cc>
-
- 24 11月, 2015 3 次提交
-
-
由 Derek Buitenhuis 提交于
* commit 'fb8753ad': qsvenc: factor out common options Merged-by: NDerek Buitenhuis <derek.buitenhuis@gmail.com>
-
由 Timothy Gu 提交于
Fixes a floating point exception when width and height are not supplied (and therefore are zero).
-
由 Timothy Gu 提交于
Calculate packet size only once, and propagate errors earlier in the chain. Also remove use of the deprecated av_image_get_buffer_size().
-