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: andreas_wonisch who wrote (5135)	8/16/2000 12:10:32 PM
From: Petz	Read Replies (1) \| Respond to of 275872

Andreas, thanks for the benchmarks from c't, exactly what I was looking for to guesstimate the improvement with DDR. If DDR-RAM scales linear we would have additional performance increase of ca. 10% (100 MHz DDR) or 13% (133 MHz DDR) via PC-100) -- assuming the latency stays the same. Latency does NOT get proportionally lower when you double peak bandwidth going from PC100 to DDR 100, or going from PC133 to DDR PC133. In fact it doesn't improve at all. Therefore I would expect only half of the above improvement, 5-6%, and that will occur only if the FSB is increased to 133 MHz x 2, which I think will happen with the Mustang CPU's. The results will be better than 5-6% for faster CPU's because the memory system becomes for of a bottleneck at faster CPU speeds. 800 MHz is now the slowest Athlon! But the really important thing about DDR is that a DDR system will excel on benchmarks designed to run fast on RDRAM, so I don't think there will be any place for Intel to hide with its Willy benchmarks, except for code optimized for SSE2.