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: Petz who wrote (85929)	7/28/2002 2:18:29 AM
From: wanna_bmw	Read Replies (3) \| Respond to of 275872

Petz, Re: "Absolutely not! It will have 21% higher clock speed. At best, it will be 10% faster, averaged over the 21 benchmarks in Tomshardware's suite." Earth to John. My post to pgerassi was not supposed to be 100% factual. In fact, it was a satire of pgerassi's own hyperbolic logic. And I decided on that piece of sarcasm because you and pgerassi are both going about proving the performance of Hammer in the wrong way. Pgerassi does it through sheer wishful thinking, and you do it by taking AMD's public performance claims (which time and again have proven to be optimistic), and applying them in calculations that are supposed to represent performance on a wide range of code. Hammer is not going to get 25% performance in every single application, and Pentium 4 is not going to scale 100% in every application. You obviously recognize the latter, yet you seem completely oblivious to the former. You must account for the limited scalability of the Pentium 4 in some applications, but you also must account for the limited benefits to the Hammer micro-architecture in some applications. Even though you recognize the need to account for limited scalability in the Pentium 4, you make the mistake of trying to determine a single "Pentium 4 scalability constant" by drawing a trend line given only 2 data points, and then averaging that across a number of applications whose bottlenecks aren't even in the CPU (3DMark, for example). For one thing, you need more than 2 data points, since errors in testing and proximity of scores can easily cause non-symmetric scaling across multiple speed grades. And for another thing, if an application is more affected by the video card than the CPU, then you can't use it with your averaged scalability constant, and then assume that Hammer will still get the full 25%. It's all horrible, horrible logic, John. If you think my post was bad, you should re-examine yours. Message 17794908 wbmw