Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: kash johal who wrote (61141)	6/9/1999 4:45:00 PM
From: kapkan4u	Read Replies (2) \| Respond to of 1572777

<Kash - re: That will likely tell us the upside on Coppermine performance. I would doubt that Coppermine with integrated 256K cache will exceed the performance of a Xeon with full speed 512 cache.> Kash, A good point about the Coppermine's performance being close to Xeon at one tenth the price. If you think that Intel is hurting because the Celeron sales are cannibalizing Pee-III, wait until Coppermine takes a byte out of the Xeon workstation sales. Kap.

To: kash johal who wrote (61141)	6/9/1999 5:05:00 PM
From: Elmer	Read Replies (1) \| Respond to of 1572777

Re: "Can you tell us the improvement from going from a PIII to a Xeon in an identical system." There are no identical systems because Xeon uses Slot2, but I'm nitpicking, they are close enough. spec.org spec.org Dell Xeon Workstations compare as follows to a Dell PIII Workstation @500MHz: SpecInt95: Xeon 512K + 5.8% Xeon 1Meg + 8.3% SpecFP95: Xeon 512K + 8.4% Xeon 1Meg + 13.3% So I know this is somewhat preliminary, but at first glance it looks as though a Coppermine may very well outperform a 1Meg Xeon. It would seem that if the data holds, the reduced latency of the L2 is a big deal. The on-die data path may also be wider than the 64 bits to the off-die L2 which would help also. Note to Ali: before you make another dumb post we all know that the Xeon is not intended for the desktop but the SMP environment where the large cache cuts down on bus traffic rather than providing a dramatic performance boost for a single processor system. That's the only way to justify the cost. EP