SI
SI
discoversearch

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.
Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?


To: Petz who wrote (188926)3/7/2006 7:30:41 PM
From: near_or_farRespond to of 275872
 
Petz,

Quite hypocritical of Anand to allow an Intel-supplied ATI driver to be used, when he refused to use an AMD-supplied PATCH that allowed Windows Media Encoder to use SSE2 instructions. This was a couple years ago, I think I am remembering the details right.

yes, he also swore never to use drivers unreleased to the public after nvidia supplied him with drivers unreleased to the public a while ago (forget which driver revision that was, I believe it was durring the geforce 3 days).

The thing I find interesting about these benchmarks is the complete lack of integer based tests. I'm sure Intel hand picked the benchmarks that ran the best for them, anyone hear any rumors on the INT performance of NGA? I'm getting the feeling that AMD is going to remain quite firmly in the lead in the server space(thanks to the integrated mem controller of course).



To: Petz who wrote (188926)3/7/2006 7:36:17 PM
From: pgerassiRespond to of 275872
 
Dear Petz:

I think you are remembering the incident correctly. If the shoe was on the other foot, think of how Intel would howl, if a benchmark used a program that checked for "AuthenticAMD" and if it was missing, used unoptimal 386/387 code, instead of highly tweaked 3DNow/SSE/SSE2/AMD64 code.

Pete