Re: [Offtopic] PIII -or- Xeon PIII ?

Joel Jaeggli (joelja@darkwing.uoregon.edu)
Thu, 18 Mar 1999 09:49:25 -0800 (PST)


The only significant design difference is l2 cache design. Your PIII has
512k of 1/2 processor speed l2 cache (ie. on the 500mhz part the l2 cache
runs at 250mhz). The XEON has 512k, 1024k or 2048k of L2 cache running at
the processor core speed (in the xeon's case 400 450, or now 500mhz). SRAM
that runs that fast is a really spendy part, alhough it certianly doesn't
justify the price premium that intel's charging on the 1MB+ items.

Recently I've been using celeron 333 and 400 cpu's in slot-1 boards for
server boxes. you can allways replace them with a pIII when you need more
horsepower and the price/performance ratio of what's essentially an $80
pII is pretty darn good as far as intel goes.

For me, the only reall motivation for jumping to xeon's would involve
either wanting more than 2 cpu's per box, or wanting some of the more
exotic features of the 450nx chipset like more dimm sockets so you can get
to 1gb+ using cheaper memory(256mb dimms instead if 512MB), having 4 64
bit pci slots. I2O developement for linux might eventually make these
boards much more interesting, but I'd reserve judgement until I've had the
opportunity to play with one. certain peoples applications will probably
run much better with a far larger/faster l2 cache, but you're mileage may
vary...

On Thu, 18 Mar 1999, Russell Leighton wrote:

> Could someone that understands the
> differences between PIII and Xeon PIII
> please outline the major *pragmatic*
> differences...in otherwords, for example,
> if you were buying a new computer for
> Linux why would you choose a PIII vs a
> Xeon PIII (what kinds of apps/services
> would benefit from one versus another)?
>
> My particular problem is to find a cost
> effective platform for a service that
> lives behind/within a http server...it
> must be as fast as it can...but price
> plays in too 'cause on deployment there
> may be alot of 'em. Advice?
>
> Thanks in advance.
>
> Russ
>
> --
> ------------------------------------------------------------
> Russell Leighton leighton@imake.com http://www.imake.com
> ------------------------------------------------------------
>
> -
> 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/
>

--------------------------------------------------------------------------
Joel Jaeggli joelja@darkwing.uoregon.edu
Academic User Services consult@gladstone.uoregon.edu
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 majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/