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: hammerfall_prophet who wrote (201354)6/9/2006 10:23:24 AM
From: eracerRead Replies (1) | Respond to of 275872
 
Re: One detail I don't see mentioned in this discussion is die sizes.
Intel's larger L2 cache doesn't come for free. The degradation of parts yields is proportional to the square of the die size. The whole concept of Intel "squeezing" AMD with Core 2 parts pricing seems like an Intellitubbie pipe dream, when Intel's cost of Core 2 production parts must be significantly higher than AMD's cost of production of competitive parts at same clock.

It probably doesn't get discussed much here because AMD's current 90-nm core sizes are larger than Intel's 4MB Woodcrest/Conroe/Merom. The 512KBx2 AM2 and S1 CPUs are 183 mm^2 and the 1MBx2 versions are 230 mm^2 while 4MB NGA is only ~150 mm^2.



To: hammerfall_prophet who wrote (201354)6/9/2006 10:45:53 AM
From: Sarmad Y. HermizRead Replies (1) | Respond to of 275872
 
>> Intel's larger L2 cache doesn't come for free. The degradation of parts yields is proportional to the square of the die size.
<<

My understanding is that cache memory does not degrade yield because the designs incorporate redundancy (along with ability to bypass defective areas).


HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News