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: Paul Engel who wrote (84714)1/3/2000 3:19:00 AM
From: Petz  Read Replies (1) | Respond to of 1573088
 
engel: AMD ATHLON - the fastest x86 processor in the world!

"The only system that came close to earning the score recorded in the CRN Test Center by the 800MHz Athlon unit was a 733MHz Pentium III reference system using an early-design Intel motherboard and Rambus memory. That Intel system scored 645, 6.5 percent behind the 800MHz Athlon"

Engel: Looks like the Spry Coppy may still be the winner !
Given a 9.1% SPEED handicap, it was only 6.5% slower than the not-yet-available 800 MHz AthWipey !

NICE TRY, but did you notice that those early-design Intel motherboard and Rambus memory systems are the ones that DIDN'T WORK! When Intel "fixed" this problem, they did it by SLOWING DOWN THE CHIPSET by 5-10%. Check out this quote from tomshardware.com
Quite a while ago and still prior to i820's final release we received i820-motherboards from Intel that came with the initial three RIMM-slots. For some reason the performance of those nowadays obsolete platforms was significantly better than the new crop of the official i820-boards with only 2 RIMM-slots. As a matter of fact the new i820-motherboards score worse than BX in several NT-benchmarks, as you will see later. This is not an issue with the Asus P3C alone, all the other i820-boards we tested scored just as bad...

RE: Given a 9.1% SPEED handicap, it was only 6.5% slower than the not-yet-available 800 MHz AthWipey !

Do you really think that increasing the clock speed by 9.1% will increase business application performance by anything close to 6.5%? (BAPCO Sysmark for Windows NT) (hint: try 4.5%)

Petz