[MPlayer-dev-eng] [PATCH] autoq support for control()

[D Richard Felker III]

On Mon, Feb 11, 2002 at 12:16:49AM +0100, Michael Niedermayer wrote:
> Hi
> 
> On Sunday 10 February 2002 23:56, D Richard Felker III wrote:
> [...]
> > > > as Juanjo alerady did with MC slices, we could do the same to
> > > > quant/DCT, i mean doing DCT for whole slice/frame first, and then doing
> > > > quantization.
> > >
> > > are u sure this will be faster?
> > > 512 pixels width
> > > slice height of 16
> > > [16*512 (luma) + 8*256*2 (chroma)]*sizeof(short) = 24kb
> > > and the p3 has 16kb L1 data cache
> > > the p4 has 8kb L1 data cache ...
> >
> > the idea isn't that the whole slice fit in the cache -- although iirc
> > with an amd rather than those crappy p3s and p4s, it would :) -- the
> droping support for p3/p4 isnt an option ...

i never said anything about dropping support. i said it might make a
significant performance boost on athlons even if it doesn't help much
on p3s and p4s. in reality it should help a lot on both.

> > idea is to keep both the dct and quant steps from repeatedly ruining
> > cache coherency for one another. i've done optimizations like this
> cache coherency? hmm, iirc offtopic ... see SMP systems 

huh?


rich