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: TechieGuy-alt who wrote (15156)	10/19/2000 10:40:27 PM
From: dougSF30	Respond to of 275872

Kernel interrupts for scheduling aren't so bad-- they tend to have a very small memory footprint. It's more trouble when you have memory intensive benchmarks. You know how certain benchmarks take a huge hit when the 'problem size' exceeds the L2 cache capacity? Imagine 2 folks running that benchmark simultaneously on the same CPU, both at 75% of the critical size. Result? Crappy time, totally misleading. I'm not sure the extent to which you could get one CPU entirely devoted to your process, and whether that would completely remove the problem for benchmarks that fit in the cache. But you could still compete for main memory. In general, to be safe, be the sole user process when benchmarking. Doug