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.
Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Joe NYC who wrote (109083)5/2/2000 3:31:00 PM
From: Cirruslvr  Read Replies (1) | Respond to of 1579107
 
Joe - RE: "I think I read somewhere that in Merced, Intel call different levels of cache differently, that L2 is really L1, L3 is L2, and L1 is something else (I forgot what). Does Foster use the same terminology?"

I think in Foster L1 will be the trace cache, L2 will be the 256KB, and L3 will be the 1MB Sharky is talking about. So in a way, the L2 may be interpreted as a huge L1 and the L3 is a normal L2 like in Cascades. Foster will probably be quite a bit faster than Willy.

Does that sound right, Elmer?



To: Joe NYC who wrote (109083)5/2/2000 4:48:00 PM
From: pgerassi  Respond to of 1579107
 
Dear Joe:

I think Intel refers to the Williamette Trace Cache as L1, the typical instruction and data caches as L2 and the unified L2 as L3.

Pete



To: Joe NYC who wrote (109083)5/3/2000 2:46:00 AM
From: Elmer  Respond to of 1579107
 
Re: "I think I read somewhere that in Merced, Intel call different levels of cache differently, that L2 is really L1, L3 is L2, and L1 is something else (I forgot what). Does Foster use the same terminology?"

I think so.

EP


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