[FFmpeg-devel] [PATCH] ffvorbis, better L1 cache use and simplification of code

Benoit Fouet ml_benoitfouet
Tue Sep 30 10:21:53 CEST 2008


Hi,

Siarhei Siamashka wrote:
> Hi,
>
> Interleaved forward/backward channels processing in order to increase chances
> of stepping on already cached data for the cores with extremely small data
> cache. Ensure that IMDCT per-rotation does not introduce cache write misses
> (write misses on random memory accesses are bad for ARM cores with no
> write-allocate cache as they prevent combining data in the write buffer).
>
> ARM11 with 32K of L1 data cache (no L2) shows performance improvement in the
> range 0.5-1% which is not so bad considering that IMDCT/IFFT and also many
> other important dsputil functions are not assembly optimized for it yet.
>
> According to cachegrind simulation, there might be also some improvement for
> x86 cores with 16K of L1 data cache (decrease of the number of cache misses
> is most visible in this configuration).
>
>   

does this patch depend on another one I missed ?
it doesn't apply as is...

-- 
Benoit Fouet
Purple Labs S.A.
www.purplelabs.com





More information about the ffmpeg-devel mailing list