Re: [FFmpeg-devel] [PATCH 4/4] lavc/fft-test: update benchmark code

2016-03-25 Thread Reimar Döffinger
On Fri, Mar 25, 2016 at 09:11:10AM -0700, Ganesh Ajjanagadde wrote: > On Fri, Mar 25, 2016 at 7:53 AM, Michael Niedermayer > wrote: > > On Thu, Mar 24, 2016 at 05:50:52PM -0700, Ganesh Ajjanagadde wrote: > >> 1. The most important change is the addition of a permute call to ensure > >> that the co

Re: [FFmpeg-devel] [PATCH 4/4] lavc/fft-test: update benchmark code

2016-03-25 Thread Ganesh Ajjanagadde
On Fri, Mar 25, 2016 at 7:53 AM, Michael Niedermayer wrote: > On Thu, Mar 24, 2016 at 05:50:52PM -0700, Ganesh Ajjanagadde wrote: >> 1. The most important change is the addition of a permute call to ensure >> that the comparison between fftw and avfft is fair, since fftw does not >> require the ca

Re: [FFmpeg-devel] [PATCH 4/4] lavc/fft-test: update benchmark code

2016-03-25 Thread Michael Niedermayer
On Fri, Mar 25, 2016 at 03:53:29PM +0100, Michael Niedermayer wrote: > On Thu, Mar 24, 2016 at 05:50:52PM -0700, Ganesh Ajjanagadde wrote: > > 1. The most important change is the addition of a permute call to ensure > > that the comparison between fftw and avfft is fair, since fftw does not > > req

Re: [FFmpeg-devel] [PATCH 4/4] lavc/fft-test: update benchmark code

2016-03-25 Thread Michael Niedermayer
On Thu, Mar 24, 2016 at 05:50:52PM -0700, Ganesh Ajjanagadde wrote: > 1. The most important change is the addition of a permute call to ensure > that the comparison between fftw and avfft is fair, since fftw does not > require the call. This is evident from the test code additions in the > previous

[FFmpeg-devel] [PATCH 4/4] lavc/fft-test: update benchmark code

2016-03-24 Thread Ganesh Ajjanagadde
1. The most important change is the addition of a permute call to ensure that the comparison between fftw and avfft is fair, since fftw does not require the call. This is evident from the test code additions in the previous commit, and also from http://www.fftw.org/benchfft/. 2. Added in a memcpy f