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: Scumbria who wrote (91675)	2/5/2000 1:45:00 AM
From: Process Boy	Read Replies (1) \| Respond to of 1575624

Scumbria - <The (rumored) deep pipeline in Willamette would likely scale to very high MHz.> But Intel isn't using Cu yet! Can't go above 1GHz without Cu! Just kidding, and not directed at you Scumbria. Just kind of throwing this out there, as food for thought. PB

To: Scumbria who wrote (91675)	2/5/2000 10:50:00 AM
From: Dan3	Respond to of 1575624

Re: The (rumored) deep pipeline in Willamette would likely scale to very high MHz. And be devastated by cache misses. AMD is addressing this issue by moving to 8 and 16-way set associative caches and low latency DDR266. What have you heard about Willamette's cache? Are they still sticking with with 40+ns device latency Rambus? Dan

To: Scumbria who wrote (91675)	2/5/2000 11:16:00 AM
From: Jim McMannis	Read Replies (1) \| Respond to of 1575624

Scumbria, Is is possible for different functions on a single chip to run at different Mhz? ie. integer, FPU, MMX? Jim

To: Scumbria who wrote (91675)	2/5/2000 12:20:00 PM
From: Charles R	Respond to of 1575624

Scumbria, <The (rumored) deep pipeline in Willamette would likely scale to very high MHz.> From all indications Wilamette core is rated higher in MHz than current Athlon. How it compares to Mustang is not entirely clear but it is conceivable that Wilamette could still have a theoritical MHz edge. The factors other than pipelines that determine the MHz leadership on a quarterly basis are: - Process (not at all clear to me Intel has a lead here anymore - we are trading off notches against Cu and the advantage of having just one fab to upgrade) - Die size (edge to Thunderbird/Mustang) - Power (could be a pretty large edge to Thunderbird/Mustang) And of course execution risk. Intel is working with a huge amount of time pressure. So, Intel may have a theoritically faster core but needs to execute extremely well in other areas to turn that into to a reality this year. Chuck