[Ffmpeg-devel] Fixed point arithmetic RealAudio G2 (cook) decoder
Thu Mar 8 22:29:51 CET 2007
Guillaume Poirier wrote:
> Since when does vectorization only works on fixed point arithmetic?
some instructions are fixed point only some float only ^^
So you may find simpler/more to vectorize one implementatio or the
other. Usually fixed point is nicer.
> BTW, BLAS-type computation is probably the easiest and most
> straightforward candidate for vectorization (since you don't need to
> Or maybe I missed smth in your reasoning?
I was too much cryptic ^^
More information about the ffmpeg-devel