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: fyodor_ who wrote (51119)	8/15/2001 2:49:14 AM
From: Tenchusatsu	Read Replies (1) \| Respond to of 275872

Fyo, <NVIDIA's chipset features a prefetch cache of some sort (DASP or some such acronym). For Palominos, there is also a separate, complementary prefetching unit.> Another counterexample: The 840 dual-RDRAM chipset for Pentium III had a built-in prefetcher. Ideally that prefetcher was supposed to soak up the excess memory bandwidth, given that it was 3.2 GB/sec and three times as much as the 1.06 GB/sec of the FSB. In reality, I doubt it helped much. The performance of 840 was better than 820 (single-RDRAM), but not much better than 815 w/ PC133. And 840 was even slower than 815 in a few benchmarks. (BTW, the 850 and 860 chipsets have similar prefetchers.) For nForce, any CPU benefit from prefetching will have already been realized by Palomino. The prefetching done by nForce is likely beneficial only to the integrated graphics, just like the extra DDR channel. Tenchusatsu