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: Scumbria who wrote (120363)7/16/2000 3:30:25 PM
From: porn_start878  Respond to of 1571808
 
Edit : Sorry scumbria the message is for Elmer

Wow you managed to contradict yourself in less than 200 words, that's hard :

First you say
what I consider to be 6th or 7th generation processors is unimportant

And a few word after, we can read :

Now we have a situation where AMD's 7th generation processor runs 7th generation code no faster than Intel's 6th generation processor runs 6th generation code. In which case I submit that there is no generation gap and claims of such are now exposed. I just wish Intel would offer a 512K L2 CuMine or a 64K L1 version because clearly the 6th generation would blow away the 7th. And what if Intel offered a 200MHz FSB?

The coppermine is 8-9 months old remember that and has a state-of-the-art cache subsystem. The cache incorporation in the TBIRD is simply, by far, inferior, missing a wider datapath and a lower latency. With equivalent caches, then you can compare the cores. To compare the cores themselves, you must compare them with a similar L2 cache subsystem; or compare the Athlon Calssic with the Katmai. Then you can observe a 17 to 30 % lead for the new core designed with less than a tenth of the intel's budget. And also, the K7 core has a clear binsplit advantage given that the intel's .18 Mu process is known to be the best in town (again think to how many times intel's process budget exceeds AMD's).

Max