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: d[-_-]b who wrote (69101)	8/17/1999 10:10:00 PM
From: Dan3	Respond to of 1585883

Re: The chipset is probably part of the problem NT is very responsive to drivers, in terms of performance and particularly in terms of stability. If you've followed any of the NT vs SCO vs Linux vs etc. battles, you'll have seen variations much greater than those described by Anand as drivers are changed. The Athlon performance that we have seen so far is on version 1.0 drivers running Intel optimized code (the only code out there right now). Without any changes from AMD (other than device drivers) there will most likely be meaningful performance increasese from Athlon systems over the coming months. The stability of the Athlons has been incredible. I never would have expected these 1.0 systems to have done as well as they have. There was a comparison review where the Xeon system couldn't finish one of the benchmark suites, and there has been considerable time to work out the bugs on the Xeon drivers. This in no way signifies any problem with the Xeon, it's just typical that the benchmark programs bang up against a device driver somewhere. And the 1.0 Athlon on a 1.0 motherboard with a 1.0 chipset and 1.0 device drivers hasn't had any widescale problems yet (something's got to turn up sooner or later, a lot of these issues are software problems beyond the control of AMD or Intel) So I'd say those tests are pretty encouraging, so far, and there is additional performance waiting to be brought out. Dan

To: d[-_-]b who wrote (69101)	8/18/1999 1:20:00 PM
From: tejek	Read Replies (1) \| Respond to of 1585883

Eric RE: <<<The chipset is probably part of the problem, but hasn't Paul and others pointed out the fact PIII's run at cpu clock for L2 cache and Athlon runs at half. From past readings here, I thought this was a hot topic - Intel choose speed with smaller cache and AMD choose larger cache slower cache access speed. Cache is what makes a Xeon a Xeon instead of a PII, and why people pay big money....>>> Thanks. There may well have been postings on this issue; however, I am learning as I go along and initially may not have caught the significance of those first postings. When you say cache is what makes the Xeon a Xeon, I take that to mean that the Xeon's cache is larger than the PII. Is that correct? BTW the article in "Toms Hardware" seems to have findings opposed to Anand's as re Athlon chipset stability. ted