From x86inc:
> On AMD cpus <=K10, an ordinary ret is slow if it immediately follows either
> a branch or a branch target. So switch to a 2-byte form of ret in that case.
> We can automatically detect "follows a branch", but not a branch target.
> (SSSE3 is a sufficient condition to know that your cpu doesn't have this problem.)
x86inc can automatically determine whether to use REP_RET rather than
REP in most of these cases, so impact is minimal. Additionally, a few
REP_RETs were used unnecessary, despite the return being nowhere near a
branch.
The only CPUs affected were AMD K10s, made between 2007 and 2011, 16
years ago and 12 years ago, respectively.
In the future, everyone involved with x86inc should consider dropping
REP_RETs altogether.
x64 always has MMX, MMXEXT, SSE and SSE2 and this means
that some functions for MMX, MMXEXT, SSE and 3dnow are always
overridden by other functions (unless one e.g. explicitly
disables SSE2). So given that the only systems which benefit
from the MMXEXT resamplers (which are overridden by SSE2)
are truely ancient 32bit x86s they are removed.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
x64 always has MMX, MMXEXT, SSE and SSE2 and this means
that some functions for MMX, MMXEXT and 3dnow are always
overridden by other functions (unless one e.g. explicitly
disables SSE2) for x64. So given that the only systems that
benefit from these functions are truely ancient 32bit x86s
they are removed.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
x64 always has MMX, MMXEXT, SSE and SSE2 and this means
that some functions for MMX, MMXEXT and 3dnow are always
overridden by other functions (unless one e.g. explicitly
disables SSE2) for x64. So given that the only systems that
benefit from these functions are truely ancient 32bit x86s
they are removed.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
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>
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>
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>
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>
Only two functions that use xop multiply-accumulate instructions where the
first operand is the same as the fourth actually took advantage of the macros.
This further reduces differences with x264's x86inc.
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
There's no benefit from using blendps here except on CPUs with AVX, where
it's faster than shufps according to Intel's documentation.
As such, rename the sse4 functions to sse/sse2 and use shufps instead.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
The swresample_ prefix is not for internal functions
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Linear interpolation goes from 63 (llvm) or 58 (gcc) to 48 (yasm)
cycles/sample on 64bit, or from 66 (llvm/gcc) to 52 (yasm) cycles/
sample on 32bit. Bon-linear goes from 43 (llvm) or 38 (gcc) to
32 (yasm) cycles/sample on 64bit, or from 46 (llvm) or 44 (gcc) to
38 (yasm) cycles/sample on 32bit (all testing on OSX 10.9.2, llvm
5.1 and gcc 4.8/9).
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Should fix compilation failures with MSVC and any other compiler
without inline asm support.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
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>
James Almer
Lynne
Andreas Rheinhardt
Marcin Gorzel
Diego Biurrun
Muhammad Faiz
Michael Niedermayer
Ronald S. Bultje
Matt Oliver