RE: 2.2.10 oops (buggy Cyrix CPUs)

Dale Amon (donthomp@luna.cs.unm.edu)
Thu, 1 Jul 1999 13:01:01 -0600 (MDT)


Well not exactly. Many models of Cyrix cpu's (6x86L and 6x86 pr200+)
ran at bus speeds of 75mhz, which is why cyrix claimed its chip running at
150 clock, outperformed a P1 200. I haven't seen a K5 or an original K6
that was intended to run at anything greater than 66mhz bus speed. On
motherboards intended for P1 cpu's, many manufacturers allowed for 75mhz
bus speed, but warned the configuration may be unstable. Cyrix 6x86 have
voltage settings of 3.5v and 3.3v. K6's can have voltage settings of 2.9v
or 3.3v.

The problem may very well have nothing to do with the cpu, or have
something to do with kernel code dealing with cyrix cpu's. However testing the
configuration with an intel P1 cpu will only help to isolate and track
down the problem. I have to say that my cyrix cpu didn't seem to become
really unstable until the 2.2 kernels arrived, but replacing the cpu with
a pentium appeared to fix the problem..and at the time I wasn't concerned
in isolating the source of the problems I was having, just stopping them.

-Donald Thompson

On Thu, 1 Jul 1999, Rafael Reilova wrote:

> Hi,
>
> AFAIK, Cyrixes and IBM 686(MX)'s are exactly the same chip down to the
> masks used for the lythographic process. The only difference being the
> packaging. This is mostly confirmed by the fact that equivalent
> model/stepping chips share the same bugs (ie. comma bug). IBM's also
> report "CyrixInstead" as their cpu vendor id.
>
> Cheers,
>
> -Rafael
>
>
> On Thu, 1 Jul 1999, Woodhouse Ian wrote:
>
> > On the subject of Cyrix Pxxx+ CPUs and bugs, I note that there are
> > twins running around bearing the IBM name rather than Cyrix.
> > Rumour suggests that these are more reliable that the Cyrix editions.
> >
> > I find this odd since I believe many Cyrix's were made at IBM plants.
> >
> > Does anyone else's experience demonstrate this?
> >
> >
> > -
> > 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/
> >
>
>
> -
> 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/
>

-
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/