Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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 vs Intel (AMD / INTC) -- Ignore unavailable to you. Want to Upgrade?

To: mas_ who wrote (2051)	8/26/2007 8:37:27 PM
From: Elmer Phud	Read Replies (1) \| Respond to of 2596

mas The difference in FB-Dimm latency off and on die is 10ns if you look at Woodcrest (117ns) vs Niagara (107ns) and still leaves you well behind direct-connect and even traditional northbridges. Look again at that Anand test link to check the numbers. I assume the 117ns vrs 107ns means from the beginning of the FB-Dimm cycle, right? With the IMC the cycle starts much sooner than it would if the memory request had to cross the FSB and go through the NB MC. So it's not really 117ns vrs 107ns at all but the overall memory transaction latency which isn't reflected in the numbers you quote. Are you sure you guys are arguing the same thing?