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

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Paul Engel who wrote (44043)12/26/1998 4:15:00 PM
From: Maxwell  Read Replies (2) of 1572596
 
Priest:

<<Maxwell - Anand's Latest K6-3 Benchmarks attribute most of its gains from the 2 MegaByte L3 cache - apparently in a RINGER system provided by AMD.

Anand seems bright enough to have recognized this "stacked deck" provided by AMD and he re-did his benchmarks with differing amounts of external L3 cache.

With smaller L3 caches - or no cache at all - the K6-3 performance is severely degraded:>>

There is little improvement going from L3=1M to 2M. Most MB comes with 512K or 1M L2 (which will become L3 in K6-3 systems). The strength of the K6-3 is in the integrated 256K L2.

Winstone 98

K6-3-350 (512K L3)= 27.2
Pentium II 400 = 27.6
K6-3-350 (1M L3)= 28.0
K6-3-350 (2M L3)= 28.9
Pentium II 450 = 29.5
CeleronA 450= 29.5
K6-3-400 (1M L3/ 66MHz FSB) = 29.9

When AMD releases the K6-3 it will be the fastest period. It will also be cheaper than the PII. Look like Sharpteeth are out to bite PII.

Maxwell
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext