Re: Pentium II Math Bug

Dan Merillat (dan@merillat.org)
Tue, 13 May 1997 04:22:41 -0400

alan@lxorguk.ukuu.org.uk writes:
>
quoting someone else:
>
> > - and don't go see the page about comparison between Pentium-II and K6
> > (and others) because the guy has sufficiently little knowledge in
> processor > to think that processors have to be compared at similar
> frequencies,

What, asking that a PPro 200 not be compared with a P166? He was
specifically talking about processers of the _SAME FAMILY_

So yes, comparing a P100 with a 486/100 is valid. It shows the P100
is faster. Comparing the MMX 166 with a P100 to show the "new" pentium
is faster is NOT valid.

Comparing CISC chips to RISC chips is always going to be diffuclt.

> Well you can thank that paticular very good chip engineer for the fact
> Linux has the undocumented 4Mbyte page mode and the vm86 extensions that
> Intel put in Appendix H, as well as some of the bug info Intel tried to
> leak quietly out of the door.

Tell me about it.. that's a great site. Good information for subtle
code tricks, as well.

- --Dan

------- End of Forwarded Message