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 231.83+1.7%Jan 16 9:30 AM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: mas_ who wrote (253028)6/8/2008 1:15:17 PM
From: dougSF30Read Replies (1) of 275872
 
The reason I'm not 100% sure is that games are also susceptible to memory latency too

that is not the only reason. Given N's faster core, and much faster L2, and the fact that processors have latency-hiding prefetchers, the PATTERN OF ACCESSES matters greatly. It is not enough to consider "working set size".

It is as if you think the access pattern is completely and utterly random within various working set sizes. Only in that case would some of your conclusions be justified. Given that virtually no code behaves like this, your conclusions are not justified, and those that read "ANYTHING that fits in..." are flat out wrong, as I tried to explain in my previous post.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext