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: Cirruslvr who wrote (95764)2/29/2000 1:05:00 AM
From: Elmer  Read Replies (2) of 1573439
 
Re: "I don't know too much about the technicals about this, but from what I have read on the net the Athlon fsb runs at 100MHz, but data is sent on the rising and falling parts of the path (whatever that means ;) ) or something like that and is therefore not double pumped and it can be called 200MHz."

Cringe, what you just described is EXACTLY what double pumped means.

The problem here is in the definition of the term MHz (or GHz). It's an outdated term when we are talking about double pumping. The term describes rising edge to rising edge because by it's definition that's the active edge. When both edges are active as in double pumping, the old terms are non descriptive because by definition they don't apply to this reference signal. A double pumped reference signal is not a clock in the traditional sense because each edge is active, not just the rising edge. Therefore MHz by it's old definition is the wrong measure because a 1.5GHz clock (as used by Willamette) really has 3.0 Billion active edges as far as double pumped logic is concerned. So it behaves exactly like a 3GHz clock for logic that only runs off the leading edge, except that the weenies who can't drop their old clock oriented mindset keep misleading everyone by pointing out that it is only 1.5Ghz buy their obsolete definition.

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