Re: MP on P5 vs P6

> I've had zero trouble with the Tyan S1668 ATX 2xPPRO board running
> everything from FreeBSD-3.0-SNAP (SMP) to WinNT4. The SuperMicro
> boards are supposedly pretty stable too (except yours, Andy? :< )

I have a SuperMicro P6DOF and it works fine. The main thing to remember
is the 450GX chipset has a few bugs, and there are a few options you
shouldn't turn on.

If you have a P6DNF, it should work fine, since it's a 440FX chipset.

> >>Of course these are all the bargan basement boards and CPUs, and I would
> >>guess there would be significant gains to using 512k L2 instead of 256k L2
> >>P6 chips.
> >Yes, but a coherent L2 cache at 256k is still usable.
>
> I've found some vendors who didn't know how to tell externally
> between a PPRO200-256k and PPRO200-512k. Needless to say they'll never
> be seeing my business again... one has to be careful about these guys.
> I'm sure there are numbers on the chip somewhere, but I'm still not
> absolutely sure. AFAIK the 150s were only built with -256k L1s.

Nope, there were some buit with 512k cache. Intel was offering a choice of
512k L2 cache only on PP150s initially, then some mags benched all the
PPros and found that the PP150-512k was as fast as the PP180 in most
applications, which was a bit embarassing, so Intel started offering 512k
cache on the PP200 as well (if I remember correctly).

> >My recommendation would be to go PPro for sure. If you want to economize,
> >getting the 256k cache configuration is a better compromise than going to
> >P5's. Shared L2 cache with write-through L1 is going to make it hard to
> >scale to any extent at all.
>
> I think 'disappointing' was the word used when the FreeBSD crowed surveyed
> P5-SMP performance :) Their caches just aren't big enough I guess.

I had a dual P120 for a while. It was about 10-15% faster when runnning
dual CPUS than when running a single CPU. The dual PP180 I have now is
something like 70% faster when running with both CPUs.

Toshi
Received on Wed Sep 10 08:19:02 1997