Intel Corporation (INTC) Message Board

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 : Intel Corporation (INTC)

INTC 40.56

+10.2%

Nov 28 9:30 AM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Tenchusatsu who wrote (160369)	2/27/2002 11:07:03 PM
From: Dan3	Read Replies (1) of 186894

Re: Why not show some comparisons with an Athlon MP server I don't have a dual P4 platform to compare it to. What was interesting in the infoworld article was the collapse in the difference as the number of sessions went up. As the number of sessions goes up, that 8-way cache is more and more likely to be cleared with each transaction, and the long pipeline of P4 and high latency of RDRAM will become more of a problem. Meanwhile, the 1GHZ PIII system that the 2GHZ SMT P4s were compared to has a short pipeline and low latency SDRAM memory - which lets it catch up once P4's 8-way cache is being churned too much keep the long pipeline full. It may sound funny, but SMT (I think) would do better in a platform with a 20-way cache and a shorter pipeline like Athlon has. Too bad Athlon doesn't seem anywhere near to having SMT available. SMT is a cool technology that has got to be of some help to P4 - I just have my doubts that the tests presented in that article are representative of the general performance benefits that will be seen from SMT on P4.

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next