Advanced Micro Devices - Moderated (AMD) Message Board

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)

AMD 214.35

-0.4%

9:47 AM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Rink who wrote (210806)	9/13/2006 11:14:38 AM
From: jspeed	Read Replies (1) of 275872

Rink, I've been trying to guess how much power savings will be realized in the 65nm process (and thus what we can expect to see in the next few quarters in the 65nm rev F chips). Here's what we know: 60% perf/watt increase in mid 2007 (slide 58) epscontest.com performance increases of 10-50% per core (slide 60 - assuming that additional cores are about 80% efficient workload-wise) epscontest.com So I'm going to split the difference and say that the new process/design is going to be good for about a 30% power improvement. So as brushwud points out, there will probably be some time before the process gets fined tuned to produce in quantity AND get all of that performance/watt improvement on the 65nm rev F chips. As you point out, some of that will be relized through transistor design modifications (which will probably not be done for rev F.) But if production really started in June, I'd be prepared to guess that they will get to 15% or so by the end of this year. Thus, both the 90nm and 65nm lines should be able to produce chips that are 15% more efficient at the January crossover. This should be sufficient to compete with C2D in 1H07.

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next