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 (81335)	11/29/1999 12:57:00 AM
From: Elmer	Respond to of 1572686

Re: "And SPEC tests run without Intels "optimized prefetch" compiler also show dramatically lower scores. " How about backing these claims up with a link Krash. Be careful now, those benchmarks might actually show Intel still beating the Athlon in integer performance, even without prefetch. If that's the case you'll look like an idiot again. Show us the link. EP

To: kash johal who wrote (81335)	11/29/1999 12:59:00 AM
From: Process Boy	Read Replies (1) \| Respond to of 1572686

kash - <Independent Benchmarkers seem to consistently show that on an equivalent clock basis the Athlon is superior to Cumine.> This is debatable. My take is that the aggregate results of 3rd party Cumine vs. Athlon benchmarks are about a wash. <And SPEC tests run without Intels "optimized prefetch" compiler also show dramatically lower scores.> From what I can glean from industry rags (since I am no where near an expert on the subject, but this controversy has got me asking questions), compiler optimizations are a perfectly legal way to improve benchmarking performance. AMD had and has the same opportunity. Intel expended the resources on 4.5. AMD did not perform an equivalent program. spec.org will post the 4.5 scores, as well as whatever AMD has at the moment. I also anticipate AMD will perform some prefetch optimizations. Hopefully, from my point of view, Intel has an answer at that point in time. Intel surprised everybody once already with the low latency on die cache. PB