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 (86799)	1/13/2000 1:17:00 PM
From: Greater Fool	Respond to of 1576162

>>the processes themselves (w/ on-die), not as expensive as you may think When the die is expanded to include cache, the extra die space costs exactly the same per square millimeter that the existing logic components do. Actually, it costs more per square millimeter, because it increases the likelihood a functioning core will be scrapped because of unrecoverable faults in the cache. With redundancy, of course, that likelihood isn't all that high, but still it's non zero. I realize the margins on high speed SRAM aren't bad, but I believe they're worse than AMD hopes for in microprocessor cores. I also understand that there's no choice but to go to attached L2, as the performance is significantly better, even when compared to full speed unattached L2. It seems this will have to impact AMD's and Intel's margins.