I am currently using a Cyrix 686MX200 and so far it works great by
setting the config option in the kernel build to 686. What Linus is
talking about doing is making optimizations that would only work if you
had a 686 chip that supported rdtsc, otherwise you would have say you
had a 486 in the config option, which would cause you lose some of the
advantages that your Cyrix 686 has.
My point is I don't wish to see Linux favor one particular chip over
another, the way Microsoft Web publisher uses by default certain
capabilities that only exist in Internet Explorer.
steve
menion wrote:
>
> > > Not all Cyrix chips are that way. I can say that the Cyrix MII 300s
> > > have a working rdtsc (minus the rest to 0 problems that are already
> > > known and handled). I have one acting as an email server (running
> > > several other internal services... some of which are "high load") and a
> > > development machine, which for the time being has an even higher load.
> > > If you kill the rdtsc in the MediaGX or some of the other early Cyrix
> > > 6z86 please don't go overboard and kill it for all Cyrix.
> > >
> > > Trever
> > >
> >
> > I agree with Trever - Some web pages say "Works Best with IE 4.0"
> >
> > Linux will have to say "Works Best with Intel Inside!".
> >
>
> I beg to differ. I have had wonderful success with the K6 chips.
>
> ----
> Joshua Schmidlkofer
> [ -- Linux Evangelist -- ]
> D+11 Since Changing to Dvorak [Keyboard]
> Speed: 20 words/minute
-
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/