Re: How to compile a Pentium II

Joel Jaeggli (
Fri, 15 May 1998 10:06:08 -0700 (PDT)

On Fri, 15 May 1998, Alex Buell wrote:

> H. Peter Anvin wrote:
> > Actually, the PII has an external L2 cache running at 2:1 clock
> > vs. the core; the PPro has an internal L2 cache at 1:1 (faster).
> So the PII is a marketing con-trick then? I've been told the PPro is far
> better. <g>

You have a couple of different issues at play here...

cpu clock speed
l2 cache size and clock speed
main memory clock speed size and bus width and timing (depends on chipset)

If you take my pentium pro linux box:
200 mhz ppro
256k l2 cache at 200mhz
440fx chipset and 64mb of edo running at 66mhz

versus my windows box:
233mhz pii
512k l2 cache at 120mhz
440fx and 64mb of edo running at 66mhz

versus the machine I just built for someone:
400mhz pii
512k l2 cache at 200mhz
440bx motherboard with 128mb of 7ns samsung sdram at 100mhz

The 233mhz pii is almost always just slightly faster that the ppro.
the 400mhz pii will outpeform the ppro and has about double the
usable memory bandwidth as a result of moving the memory timing from 60ns
to less than 10 and increasing the bus speed by 1/2. In most things it's
at least half again as fast, although in quake it's about double.

Until the pii xeon ships and the 450nx chipset is available you can't have
more than 2 pii's in an smp machine. this is an issue because with the
450gx chipset you can have 4-6 ppro's on a board (see: alr revolution
6x6), but again the memory bandwidth is limited compared to the of lx and
bx based boards, so there are some inherent trade-offs.

Off hand, for your personal workstation I'd say a pii would be better, at
least I enjoy it more, mostly it comes down to whatever has the right mix
of performance and cost for your application and pii's are pretty cheap...


> --
> Cheers,
> Alex.
> Watch out, the NSA are everywhere. Your computer must be watched!
> /\_/\ Legalise cannabis now!
> ( o.o ) Smoke some cannabis today!
> > ^ < Peace, Love, Unity and Respect to all.
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to

Joel Jaeggli
Academic User Services
PGP Key Fingerprint: 1DE9 8FCA 51FB 4195 B42A 9C32 A30D 121E
It is clear that the arm of criticism cannot replace the criticism of
arms. Karl Marx -- Introduction to the critique of Hegel's Philosophy of
the right, 1843.

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to