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: fyodor_ who wrote (72464)	2/26/2002 11:34:03 AM
From: combjelly	Respond to of 275872

"There have been some indications that Intel would be doubling much of the front end for HyperThreading." I would think that everything to the trace cache would have to be doubled for hyperthreading to work. What I was referring to was computational resources. The P4 resources were optimized a lot for the expected instruction stream, and, except maybe for floating point, there just isn't a whole lot left over to extract a huge amount of performance with hyperthreading. At a guess, for STREAM-like programs that mainly move stuff around without a lot of computation, hyperthreading may show good performance increases. But for extremely computational intensive tasks, there may not be enough resources for hyperthreading to show much, if any, performance increase.

To: fyodor_ who wrote (72464)	2/26/2002 12:09:32 PM
From: Joe NYC	Read Replies (2) \| Respond to of 275872

Fyo, There have been some indications that Intel would be doubling much of the front end for HyperThreading. This would not only explain the high benchmark increases, but also the abnormally large amount of "dark" transistors reported in the P4 (Willamette). I am not sure if you are talking about past tense or future? I am confused. I doubt that the front end was doubled (decoder / trace cache) from Willy to NW. Intel is reporting strong benchmark gains from hyperthreading, but no one else is, and the CPU in question was introduced yesterday. Joe