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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?


To: porn_start878 who wrote (169858)8/23/2002 1:27:46 PM
From: Tenchusatsu  Read Replies (1) | Respond to of 186894
 
Max, <When the Hammer is out, they'll suddently get particularly interested in code that love larger cache and hyperthreading.>

When the Hammer is out, AMD will suddenly get particularly interested in code that is recompiled for x86-64 and its larger register file.

Let's admit the obvious before we go on: Benchmarks Are Bunk. Keith Diefendorff of MDR Online wrote an editorial entitled as such in Microprocessor Report. (Too bad it's not an editorial I can link to or copy.)

Get this: the date of the editorial was June 26, 2000. Two years later (40 in computer years), and what's changed? Absolutely nothing.

Tenchusatsu



To: porn_start878 who wrote (169858)8/23/2002 2:01:01 PM
From: wanna_bmw  Respond to of 186894
 
MAX, Re: "When the Hammer is out, they'll suddently get particularly interested in code that love larger cache and hyperthreading."

And why shouldn't they be? It's in their best interests, after all. The only thing I would insist is that actual applications take advantage of these enhancements before benchmarks are altered to favor them. I would also insist that AMD make sure their enhancements are also included in any independent benchmarking suites.

wbmw