[FFmpeg-devel] [PATCH 0/6] x86 SIMD for dirac 10-bit wavelet transforms

Rostislav Pehlivanov atomnuker at gmail.com
Thu Jul 19 19:07:47 EEST 2018


On 19 July 2018 at 16:29, James Darnley <jdarnley at obe.tv> wrote:

> On 2018-07-19 17:23, Rostislav Pehlivanov wrote:
> >
> > Could you provide standard overall transform results using
> START/STOP_TIMER
> > rather than overall decoding speed?
> > Coefficients sizes and therefore golomb unpacking speed changes with
> > respect to the transform so potentially there could be somewhat of a
> > bottleneck on decoding before the inverse transform.
>
> Ah, you are right about that.  Should I limit the depth to 1 so that the
> functions operate on the same width all the time?  Anyway, I will get
> the timers in there.
>
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel at ffmpeg.org
> http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
>

Yep, use depth 1 for all transforms and use the biggest slices possible.


More information about the ffmpeg-devel mailing list