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: Dan3 who wrote (100100)3/26/2000 8:43:00 PM
From: Scumbria  Read Replies (2) of 1571928
 
Dan,

The Ace's post was interesting.

No matter how many pipe stages you have, the chip will run at the speed of the slowest bit of logic. One thing that really caught my attention at the Dirk Meyer dinner last year, was that he started the talk with a discussion of the up front effort that went into balancing the pipeline. That is why Athlon has scaled so well in MHz.

It does no good to have a 20 stage pipe, if one stage is much slower than the rest. Another reason why MHz doesn't scale well with pipe depth is that latch delays and clock jitter and skew eat up a fixed chunk of the clock period.

Nevertheless, as transistors speed up, increasingly deep pipes will be necessary to optimize performance.

Scumbria

BTW: Maybe someone could pass this comment from ACE's on to Elmer, so that he will stop babbling about the Willy demo:

Now Willy could go stably to 1.3 GHz, that 1.5GHz demo only booted up and ran application showing it's 1.5GHz - nothing more, thus CPU was probably severely (and unstably) overclocked.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext