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: Dan3 who wrote (130562)3/21/2001 11:36:58 AM
From: fingolfen  Read Replies (1) | Respond to of 186894
 
Funny how P4 looks awful on anything that doesn't have both code and data hand tweaked for P4. P4 is unsuited to running the entire installed base of code, and runs even "fixed" executables well only if the data are predetermined - it doesn't do as well with real data.

So what you're saying is the Pentium 4 is a processor that runs today's code very slowly... even more slowly than it's predecessor. You're saying that code has to be optimized to run on the processor, and so it doesn't run well on the installed base of software. You're also saying that the Pentium 4 won't perform well until the next generation of software is released (given SSE2 is being adopted by AMD as well, the software WILL be out there)...

... those aren't new criticisms. Those are exactly the same criticisms which were leveled at another Intel processor. You might remember it... it was called the Pentium... I seem to remember it doing quite well in the market for many, many years...



To: Dan3 who wrote (130562)3/21/2001 11:39:53 AM
From: fingolfen  Respond to of 186894
 
Yes, I think you are correct. The new Intel/Bapco benchmark is "fixed".

Funny how any time AMD does well on a new benchmark it's "proof of AMD's technical superiority and manifest destiny to defeat the evil Satanic sham of an empire that is Intel and benevolently bring high-speed computing to the repressed masses," but any time Intel does well on a new benchmark, it's "fixed."

I'll leave it at that...