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: tcmay who wrote (136859)	6/7/2001 12:39:46 AM
From: muzosi	Read Replies (1) \| Respond to of 186894

And yet where are the super-fast PPCs? it is possible that they don't exist for the same reason 1.13 ghz p3 doesn't exist but a p4 can run at 1.7 ghz at the same process. it is possible to design the micro-architecture to do more in a cycle instead of frequency scaleability.

To: tcmay who wrote (136859)	6/7/2001 12:44:28 AM
From: Dan3	Read Replies (1) \| Respond to of 186894

Re: Ask yourself why IBM is using Xeons and Pentium 4s and so on instead of using their own SOI process for their own PPCs. Well, they are using their SOI process for PPCs (the RS6000s). As far as Xeons are concerned, the X86 installed base of code is pretty compelling - which will provide something of a challenge for Itanium / McKinley (and less of a challenge for the Hammers). The most compelling thing to me is the fact that AMD, which obviously could very easily have gone, like Intel, with plain copper & .13, instead decided to build a major extension at their Dresden FAB in order to add SOI to their process. This isn't a case of building a plant aimed at SOI/copper/.13 years before the technology was ready, when you don't yet know for sure that it's needed. They actually had to go back and retrofit the SOI capability to their existing copper/.13 facility. By the time they started the SOI addition, they had well over a years of high volume production experience with copper, and plenty of time to experiment with SOI and non-SOI implementations. And AMD went through the hassle and risk of bolting a mini-FAB on top of their crown Jewel at Dresden, that adds no additional unit capacity, pretty much at the last minute, in order to add SOI. You might want to consider that, without SOI, the roadmap for coppermine goes from 1GHZ to 1.26GHZ when moving to Intel's super-small gate, high aspect ratio .13 and copper process from .18 and aluminum. AMD expects the move to .13 to take the Athlon core from 1.5 or 1.7GHZ on .18 to 3GHZ on .13. Without SOI, P4 may only go from 2GHZ on .18 to 3GHZ on .13 - and even the larger L2 on Northwood isn't gong to bring P4's IPC anywhere near Athlon's. Intel made a big deal about copper not really adding much until you got to .13 - and they seem to have been largely correct. AMD has been making a big deal about .13 and copper not really adding much unless you go to SOI - and they may be just as correct. They've certainly been willing to risk their only money making FAB for it. Dan