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 : Intel Corporation (INTC)
INTC 35.75+3.6%3:59 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Rob Young who wrote (128518)2/28/2001 1:06:05 PM
From: Tenchusatsu  Read Replies (2) of 186894
 
Rob, <Are you saying it won't happen, PERIOD?>

Period. It's a wild fantasy to think that 256 CPUs can scale UMA-style. For a normal read transaction, the worst-case latency is 14 hops (seven hops for the request, seven hops for the returned data), meaning the average will be seven hops. No UMA system would require an average of seven hops, even if you get the best-case hop latency every time.

Besides, the infrastructure cost of a 256-CPU system is astronomical. UMA suggests SHV (Standard High Volume), which EV7 has absolutely no hope of reaching, even with 16-way systems. (Unless you think several gigabytes of RDRAM w/ ECC is going to be cheap, or processor packages w/ over 1,400 pins.)

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