On Sat, 5 Oct 2002 03:50:38 +0200
Dieter N�tzel <[EMAIL PROTECTED]> wrote:
> Am Mittwoch, 2. Oktober 2002 09:58 schrieb Keith Whitwell:
> > > I definitely running this on my dual Athlon with latest ACPI for 2.4.19
> > > and irq's routing enabled, I think.
> > >
> > > With "procinfo -f" I see ~980 irq/sec during "gears".
> > >
> > > Same with r200 code from yesterday. But it was much faster.
> >
> > I think I may have fixed your problem (thanks to Felix), can you try again?
>
> I think you have.
>
> 2.4.19-ck5 (O(1) + -AA + preemption)
>
> gears:
> ~2380 fps
> System load ~25-26%
>
> But Q3A get best (~136 fps) only with "setenv R200_NO_USLEEPS 1".
Stefan Lange reported that Quake3 gives him max 50FPS which sounds like
a usleep limit. I saw that usleep is used in several places in
r200_ioctl.c. I'm afraid that my change in r200Clear may be causing
trouble.
I could actually reproduce the 50FPS limit on my Radeon7500 by changing
radeonClear to behave like r200Clear (set RADEON_MAX_CLEAR to 1 and put
in a usleep instead of busy waiting). With RADEON_MAX_CLEAR == 2
everything seems fine. But maybe it wouldn't hurt increasing the limit a
bit further, just to be sure.
Felix
__\|/__ ___ ___ ___
__Tsch��_______\_6 6_/___/__ \___/__ \___/___\___You can do anything,___
_____Felix_______\�/\ \_____\ \_____\ \______U___just not everything____
[EMAIL PROTECTED] >o<__/ \___/ \___/ at the same time!
-------------------------------------------------------
This sf.net email is sponsored by:ThinkGeek
Welcome to geek heaven.
http://thinkgeek.com/sf
_______________________________________________
Dri-devel mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/dri-devel
