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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: stak who wrote (169558)	8/17/2002 8:41:03 PM
From: Dan3	Read Replies (1) \| Respond to of 186894

Re: $70 3.0 GHz chips are just a year away. Not much time to capitalize on the laptop market either perhaps. High power 2.0 GHz will be low end very soon. Need high ASPs to come from somewhere. But where?? Intel will be pushing hyperthreading chips as a reason to spend a little more, while AMD will be pushing 64-bit chips as a reason to spend a little more. Whether either strategy can keep CPU's from becoming sub $100 commodities remains to be seen. PS - it's interesting that AMD's architecture, with 9 available pipelines and a 20-way cache, would probably benefit more from hyperthreading than the P4, which has 6 pipelines and an 8-way cache. And, IIRC, some of P4's pipelines are actually siamesed 16-bit pipes, meaning that the resource difference is greater than 3 to 2. The basic concept of hyperthreading is to run multiple, concurrent threads on the chip so that there is something to keep the pipelines busy even when one thread is stalled waiting for data from main memory, or the results of a previous instruction. With 9 pipelines, Athlon is more likely to have some unused, at any given time, than the 6 pipeline P4. Dirk Meyer was working on hyperthreading at DEC before he moved to AMD, and there has been speculation that the follow-on to Hammer will support hyperthreading.