SI
SI
discoversearch

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: dougSF30 who wrote (219301)12/6/2006 3:56:59 PM
From: plantlifeRead Replies (2) | Respond to of 275872
 
I can see why people lose patience with you. That comment should be followed by IMO, but you state it as fact.



To: dougSF30 who wrote (219301)12/6/2006 4:23:54 PM
From: RinkRead Replies (3) | Respond to of 275872
 
Doug, FYI: AMD shrunk the logic part of their 65nm chip much less than expected (see also below pic from Hans). L2 cache shrink was fine. We don't know why AMD shrunk the logic part (the cores, xbar) much less. It's a design trade off of some kind.

Even with this bad logic scaling AMD's cores are still smaller than Intel's (the logic part that is, even when adding in a quarter of the die size for xbar + mem contr). Or in other words Intel's L2 is still smaller than AMD's L2/L3 cache.

Also Intel 'QC' is 2*143=286mm2. That is for 2*2MB L2 variant. Boy that's close to Barcelona.

BTW, Hans'adjusted estimate of Barcelona is 283mm2. Someone else mentioned 286mm^2 from another estimate. What's the error margin in your 300mm2 estimate?

Regards,

Rink