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)
AMD 215.00+0.7%Dec 22 3:59 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Tenchusatsu who wrote (57175)10/4/2001 5:46:09 PM
From: fyodor_Read Replies (2) of 275872
 
Tench: The trouble with the processor performance game is that there is no de facto standard of measurement besides clock speed. Obviously this is not a problem that Intel is very willing to fix, but AMD's arbitrary "quantispeed" rating is no solution, either.

Why are you so certain that AMD's rating scheme is "arbitrary"? They haven't announced any details so far and while it may wind up being (seemingly) arbitrary, it might not.

What would you say if AMD announced that their scheme is based on SPECint performance compared to Thunderbird? Or P4?

If you take a look at spec.org, both appear theoretical possibilities, since the 1.4GHz Tbird matches the (inexistant) 1.6GHz P4 (score derived by averaging 1.5GHz and 1.7GHz scores) - and that's using one of the slower motherboards out there. It's unclear to me exactly how much the Palomino will increase SPECint scores, but it could well be enough that the rating is relative to AMD's own Tbird core. If Palomino only increases scores none to slightly, that's still enough for the rating to apply to the P4 core.

An average of SPECint and SPECfp might also be the basis.

Then again, it might also be fairly arbitrary&#133 the point is, we just don't know yet and I think it's too early to condemn it.

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