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.

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

To: Tony Viola who wrote (61999)	11/3/2001 12:16:24 PM
From: Ali Chen	Read Replies (1) \| Respond to of 275872

Tony, "The quanti-speed thing is unprecedented in computer history. " How soon you forgot about iCOMP index for Intel Pentiums? Colorful iCOMP charts used to be stuck on every retail box. "All other computers have been sold based on brand name (IBM, Sun, Dell), or benchmarks or clock speed, or, of course, a combination of these." You just have justified the AMD approach as a combination "of these", just replace "or" for "and": AMD Athlon-XP 1800+ is a brand with benchmark rating close to actual clock rating. Feel better now? "If you cut it in half, but double clock speed and all else remains equal, and you end up with the same throughput, who cares?" Nobody, except Intel zealots like yourself and John Fowler. In case you have ignored couple of early posts on the subject, let me remind you of one example: Intel Itanic running at 800MHz, spec.org. posted performance score of 701 (SPECfp2000). At the same time, a Pentium-4 processor running at 1900 MHz, spec.org. scores on the same benchmark at 696. Why are you not complaining about inflated clock speed rating for the P4, or different "standards" of measuring frequency, or something else, just for the sake of complaining? For John and you, I suggest to drop the nonsense. - Ali

To: Tony Viola who wrote (61999)	11/3/2001 12:27:42 PM
From: dale_laroy	Read Replies (1) \| Respond to of 275872

>The quanti-speed thing is unprecedented in computer history.< How soon we forget about the PR rating system. Or are you referring to the fact that Quantispeed is not a rating, but a part of the processor name?

To: Tony Viola who wrote (61999)	11/3/2001 12:40:29 PM
From: aburner	Read Replies (2) \| Respond to of 275872

Tony, re: there is no standard for IPC. If you cut it in half, but double clock speed and all else remains equal, and you end up with the same throughput, who cares? OK, let me try to separate apples from oranges in this discussion: - What you're talking about - and what I agree with in general - is performance (IPCclock speed) according to AMD.() - John however was talking about MHz being an industry standard, or at least that's how I understood it. Someone correct me please if I'm wrong. - What I tried to say was: If you underclock a P4 to 1,1 GHz and compare it to a PIII 1GHz the PIII will win in most benchmarks, i.e. has the better performance than the P4. So while the P4 would be faster in MHz than the PIII it's performance would not. That's why I think that with the introduction of the P4 MHz became meaningless or at least a lot less meaningful as an indicator for performance (as I already wrote it's not a good idea anyway), whereas earlier you could always count on processors from one generation having better performance than processors from the generation before (e.g. PIII better than PII, Pentium better than 486) at the same clock speed. MHz is a measure for clock speed not for performance. ABurner (*)There's a discussion about why this is not a good definition initiated by Paul DeMone over at realworldtech.com