[FFmpeg-devel] [PATCH] 1D DCT for dsputil
Tue Jan 19 05:49:03 CET 2010
Vitor Sessak wrote:
> Loren Merritt wrote:
>> On Mon, 18 Jan 2010, Vitor Sessak wrote:
>>> + data[i ] = COS(s,n,i) * val1 + SIN(s,n,i) * val2;
>>> + data[i + 1] = SIN(s,n,i) * val1 - COS(s,n,i) * val2;
>> data aliases costab, so the SIN/COS loads will be duplicated.
>>> + float tmp1 = data[i ] * (1./n);
>>> + float tmp2 = data[n - i - 1] * (1./n);
>>> + float sin1 = 0.5/SIN(s,n,2*i+1);
> I don't see how it is avoidable, I've tried a LUT and it is slower.
I made a stupid mistake that was getting the benchmarks wrong. Actually
a LUT is faster. New patch attached.
> New version attached with the above changes, indentation nits and added
> myself to the copyright.
-------------- next part --------------
A non-text attachment was scrubbed...
Size: 9867 bytes
Desc: not available
More information about the ffmpeg-devel