Recherche avancée

Sur d’autres sites (10545)

• imdct15 : replace the FFT with a faster PFA FFT algorithm

  4 janvier 2017, par Rostislav Pehlivanov

  imdct15 : replace the FFT with a faster PFA FFT algorithm
  This commit replaces the current inefficient non-power-of-two FFT with a
  
  much faster FFT based on the Prime Factor Algorithm.
  
  Although it is already much faster than the old algorithm without SIMD,
  
  the new algorithm makes use of the already very throughouly SIMD’d power
  
  of two FFT, which improves performance even more across all platforms
  
  which we have SIMD support for.
  Most of the work was done by Peter Barfuss, who passed the code to me to
  
  implement into the iMDCT and the current codebase. The code for a
  
  5-point and 15-point FFT was derived from the previous implementation,
  
  although it was optimized and simplified, which will make its future
  
  SIMD easier. The 15-point FFT is currently using 6% of the current
  
  overall decoder overhead.
  The FFT can now easily be used as a forward transform by simply not
  
  multiplying the 5-point FFT’s imaginary component by -1 (which comes
  
  from the fact that changing the complex exponential’s angle by -1 also
  
  changes the output by that) and by multiplying the "theta" angle of the
  
  main exptab by -1. Hence the deliberately left multiplication by -1 at
  
  the end.
  FATE passes, and performance reports on other platforms/CPUs are
  
  welcome.
  Performance comparisons :
  iMDCT, PFA :
  
  101127 decicycles in speed,   32765 runs,      3 skips
  
  iMDCT, Old :
  
  211022 decicycles in speed,   32768 runs,      0 skips
  Standalone FFT, 300000 transforms of size 960 :
  
      PFA        Old FFT     kiss_fft    libfftw3f
  
      3.659695s, 15.726912s, 13.300789s, 1.182222s
  Being only 3x slower than libfftw3f is a big achievement by itself.
  There appears to be something capping the performance in the iMDCT side
  
  of things, possibly during the pre-stage reindexing. However, it is
  
  certainly fast enough for now.
  Signed-off-by : Rostislav Pehlivanov <atomnuker@gmail.com>
  

  • [DH] libavcodec/imdct15.c
  • [DH] libavcodec/imdct15.h

• lavfi : make window_func an inline function

  23 septembre 2017, par Rostislav Pehlivanov

  lavfi : make window_func an inline function
  Eliminate lavc->lavfi dependency. The function isn't big and doesn't
  
  deserve its own file.
  Signed-off-by : Rostislav Pehlivanov <atomnuker@gmail.com>
  

  • [DH] libavcodec/opusenc_psy.c
  • [DH] libavfilter/Makefile
  • [DH] libavfilter/af_afftfilt.c
  • [DH] libavfilter/avf_showfreqs.c
  • [DH] libavfilter/avf_showspectrum.c
  • [DH] libavfilter/vaf_spectrumsynth.c
  • [DH] libavfilter/window_func.c
  • [DH] libavfilter/window_func.h

• aacenc_tns : implement temporal noise shaping

  21 août 2015, par Rostislav Pehlivanov

  aacenc_tns : implement temporal noise shaping
  This commit implements temporal noise shaping support in the
  
  encoder, along with an -aac_tns option to toggle it on or off
  
  (off by default for now). TNS will increase audio quality
  
  and reduce quantization noise by applying a multitap FIR filter
  
  across allowed coefficients and transmit side information to the
  
  decoder so it could create an inverse filter.
  Users are encouraged to test the new functionality by enabling
  
   aac_tns 1 during encoding.
  No major bugs are observable at this time so after a while if no
  
  new problems appear and if the current implementation is deemed
  
  of high enough quality and stability it will be enabled by default,
  
  possibly at the same time the encoder has its experimental flag
  
  removed and becomes the standard aac encoder in ffmpeg.
  Signed-off-by : Rostislav Pehlivanov <atomnuker@gmail.com>
  

  • [DH] libavcodec/Makefile
  • [DH] libavcodec/aac.h
  • [DH] libavcodec/aaccoder.c
  • [DH] libavcodec/aacenc.c
  • [DH] libavcodec/aacenc.h
  • [DH] libavcodec/aacenc_tns.c
  • [DH] libavcodec/aacenc_tns.h