[FFmpeg-devel] [PATCH 0/4] fftw exploration (WIP)

Nicolas George george at nsup.org
Fri Mar 25 17:36:10 CET 2016


Le sextidi 6 germinal, an CCXXIV, Ganesh Ajjanagadde a écrit :
> Depends on if it is small or not. Yes, in many codecs, FFT's are short
> length ones, e.g 512. However, on long lengths, e.g 8192+, as seen
> from the benches, there are sometimes 2x variations at the moment.

And how much of the actual total decoding is spent in the FFT? Even a ×50
speedup would be useless if it is for a function that never amounts to more
than 0,01% of the actual time. The FFT is probably not that negligible, but
this is not a ×50 speedup either, and I have no idea how frequent are long
lengths.

You often do your benchmark like that, please try to be more careful and
benchmark spans of code that are actually relevant for FFmpeg's tasks.

Regards,

-- 
  Nicolas George
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: Digital signature
URL: <http://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20160325/8337b548/attachment.sig>


More information about the ffmpeg-devel mailing list