Re: 4MB pages and framebuffer access, x11perf results, 2.1.125

Linus Torvalds (torvalds@transmeta.com)
29 Oct 1998 21:14:11 GMT

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: LJP: "286 & Linux"
Previous message: Alan Cox: "Re: UMSDOS support in 2.1.125 doesn't compile"
Maybe in reply to: MOLNAR Ingo: "4MB pages and framebuffer access, x11perf results, 2.1.125"

In article <Pine.LNX.3.96.981029185304.421A-100000@dragon.bogus>,
Andrea Arcangeli <andrea@e-mind.com> wrote:
>On Thu, 29 Oct 1998, MOLNAR Ingo wrote:
>
>>it's incorrect. It didnt make a stability difference though because i used
>
>So it would be nice to know the x11perf report without the GLOBAL flag set
>(I can' t do the test myself because I have not a P6 CPU :-().

Good point. X11perf showed an almost 15% improvement, but considering
that some of what happened was definitely completely illegal, the
numbers are very suspect indeed.

Note that you don't need a P6 to test this: Pentiums will also support
the 4M page (not the global thing, but you can run your own tests with
that bug fixed).

Linus

-
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/

Next message: LJP: "286 & Linux"
Previous message: Alan Cox: "Re: UMSDOS support in 2.1.125 doesn't compile"
Maybe in reply to: MOLNAR Ingo: "4MB pages and framebuffer access, x11perf results, 2.1.125"