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 207.67+2.2%Jan 12 3:59 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: pgerassi who wrote (11170)10/2/2000 5:28:46 PM
From: combjellyRead Replies (1) of 275872
 
pgerassi, latencies and north bridges.

Good point, the impact of the latencies would depend on the packet size. And yes, considering the alternative is to page it off a disk, even a highly hierarchal NUMA system will be better than that, latency speaking. I would assume that code would get paged in from non-local resources, otherwise the performance hit would be terrible on smaller cache processors. Is this a settable parameter on at least some NUMA systems? I know that the latencies can get quite high with some of the systems with thousands of processors.

The specifications of LDT (regular and crispy) look real good. I can't wait to see actual hardware and how it works in the real world...
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext