Re: [PATCH] APM support doesn't compile with binutils 2.8.1.0.24

Michael L. Galbraith (mikeg@weiden.de)
Sat, 28 Mar 1998 05:34:56 +0100 (MET)


On Fri, 27 Mar 1998, Harald Koenig wrote:

> On Mar 25, MOLNAR Ingo wrote:
>
> > the testcode has to be run as root, it should produce something like this:
> >
> > [root@hell asm]# ./test2
> > best pushw latency: 19 cycles
> > best pushl latency: 20 cycles
>
> with a [true;] Pentium OverDrive PODP-83 I got
>
> best pushw latency: 30 cycles
> best pushl latency: 19 cycles
>
>
> remember that this weird CPU was the reason why I started that bogomips thread
> about alignment of the delay loop and (not) inlining it.
> looks like this is yet another example of weird differences between
> read Pentium and Pentium OverDrive...
>

MMX-Overdrive says..

best pushw latency: 20 cycles
best pushl latency: 20 cycles

-Mike

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu