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 Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: mas_ who wrote (253040)	6/8/2008 5:31:23 PM
From: dougSF30	Read Replies (2) \| Respond to of 275872

You are wrong as I have shown by the OFFICIAL SpecCPU/JBB submissions which explicitly disable prefetching. You are confused, mas. Certain benchmarks disable prefetching from main memory due to the bandwidth constraints of the old FSB connection. If you do aggressive speculative prefetching without enough bandwidth, and the prefetchers are pulling enough false positives in, it costs you performance, because the unneeded data is plugging the narrow pipe to main memory, slowing the real data flow. Nehalem has bandwidth in spades, so you won't see prefetching disabled for any benchmarks. unlike you who is claiming something that is not backed up by any evidence. I am providing you with examples that are backed up by what I thought was elementary arithmetic. If you understood them, you would not be making laughable claims like: "Any application with a working set of 1 to 6MB will perform worse on Nehalem."