Re: RasterMan on linux and threads
michael_schulz@public.uni-hamburg.de
Sat, 18 Dec 1999 15:33:47 +0100
Rik van Riel:
> If the bursts are short enough, it will be more work to
> load the data into cache on another CPU than to do the
> calculations 'locally'.
>
> When it doesn't make sense to move the work to another
> CPU, it won't make sense to force it there. OTOH, when
> the amount of work is big enough, it _will_ get run on
> multiple CPUs in parrallel.
But i could think of a situation in a boss/worker setup (keeping
workers in a pool), where some workers got scheduled on different cpus
and then stay assigned to their cpus during several requests.
--
-- Michael Schulz, Uni Hamburg
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/