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.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Process Boy who wrote (93527)	2/16/2000 9:26:00 AM
From: DRBES	Read Replies (1) \| Respond to of 1571068

WILLY=pee-2000; Any bets on inteL's nomenclature for the newest set of chips. My best guess is pentiuM-2000. Regards, DARBES

To: Process Boy who wrote (93527)	2/16/2000 11:17:00 PM
From: Dan3	Respond to of 1571068

Re: Did you have time to look at it?... Hi PB, I looked at it briefly (and, I should add, I'm not particularly knowledgeable in this area, so I could easily have missed something) and it seemed as if what was posted was only a part of the documentation that focused on SIMD instructions pretty much exclusively. There was some discussion of the relative clock costs of the SIMD instructions, but not of whether or not some of the simpler instructions would be affected by a pipeline stall. There don't appear to be a lot of final clock counts yet. For example "shifts are relatively much more expensive in Willamette family processors, while multiplies are somewhat more expensive." (2x vs. 4x? 1.5x vs. 6x?, beats me :-) It does say that "register partial stalls are no longer an issue in Willamette family processors", so maybe that is an indication that not everything is lost if that long pipeline stalls. Thanks for the link, I may try to puzzle through some more of it later. Willamette - and Athlon - are amazing, wonderful devices. Regards, Dan