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: Joe NYC who wrote (76006)	3/31/2002 11:11:33 PM
From: Elmer	Read Replies (2) \| Respond to of 275872

The results with hyperthreading enabled are devastating. Performance drop across the board, except in 3d rendering software. No wonder Intel is postponing Hyperthreading for desktop until the next core revision. If you notice the server application results, these are from their tests. The source is "Intel Mircoprocessor Software Labs", not their own, "hands on" tests. You must have missed the review infoworld did on hyperthreading. It showed some very impressive performance improvements and it was essentially free. True, it's not ready for desktop like you said but it will eventually be. infoworld.com

To: Joe NYC who wrote (76006)	3/31/2002 11:35:31 PM
From: Dan3	Read Replies (1) \| Respond to of 275872

Re: The results with hyperthreading enabled are devastating. Performance drop across the board It was pretty ugly, wasn't it? Theoretically, SMT should be a very nice technology, that should provide a moderate improvement in IPC under almost any circumstances. An SMT chip should have two sets of registers, stacks, etc. so that there is almost no penalty for its use. Maybe P4 just has really poor implementation and they'll fix it at some point (or AMD will come out with an SMT implementation that works).