Re: OOPS in 2.0.24

Linus Torvalds (torvalds@cs.helsinki.fi)
Thu, 14 Nov 1996 09:53:57 +0200 (EET)


On Wed, 13 Nov 1996, Taner Halicioglu wrote:
>
> On Thu, 14 Nov 1996, Linus Torvalds wrote:
>
> > What CPU do you have? This _looks_ like the panic that some people saw
> > with Cyrix 486 clone chips.
> [...]
> > >
> > > Machine is an i486 DX4/100, 36M RAM.
> > >
> > Is that "i486" really an _i_ 486? The only cases of the above kind of
> > behaviour that I've seen has been for Cyrix chips.
>
> Ok, I lied about the i486ness... it's an IBM 486DX4/100 CPU.
>
> Forgot that that can make a difference ;-) Now, the interesting thing is,
> the Motherboard calls it: (from the BIOS screen)
>
> Main Processor : Cx486DX4
>
> The settings on the motherboard (jumprs, etc) are the same for the Cyrix
> and IBM chips.

The Cyrix and IBM chips are exactly the same as far as I know. The only
difference is the name they put on the chip itself, I think.

> Time to go get a new computer, anyway -- quake is too slow ;-)

I forget who saw this behaviour originally, but it doesn't seem to happen on
_every_ Cyrix chip, so it may be a case of just a bad batch that is fixed in
later revisions. As such, if you can find a new CPU cheaply, maybe it might
make sense to try to just exchange the CPU. There are bound to be lots of
people with Cyrix chips, and yet these kinds of problem reports are certainly
not very common.

I also forget what the exact circumstances were last time somebody had this
problem, but you might just do the "obvious things" first: make sure the chip
isn't overheating, make sure all the cache chips and RAM SIMMs are well
seated etc etc. Especially overheating of the CPU might just make the
whole thing worse, and any other problem with the caches or similar might
just confuse the CPU enough that it does these bogus things..

Linus