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: Dan3 who wrote (69076)	1/27/2002 9:12:34 AM
From: fyodor_	Read Replies (1) \| Respond to of 275872

Dan: There are new results at the site, reflecting that the benchmarks have been "fixed." Note that the "unusual results" were that hyperthreading enabled chips were slower on some software than chips w/o hyperthreading. ROFL ROFL ROFL!!! The benchmark used is SiSoft SANDRA!!! The FPU / ALU tests there are the most moronic ones ever devised. For example, the FPU test is specifically designed not to take advantage of pipelining. I can easily imagine that a HyperThreading enabled processor would score lower on it, but calling it "real world" in any sense is just plain nonsense. Even as a "synthetic" benchmark it absolutely sucks. Cross-architecture comparisons using the FPU / ALU results in Sandra are meaningless and same-architecture comparisons scale linearly with frequency. In other words, SiSoft Sandra provides, at best, a poor measure of processor clock frequency. Sandra sucks. Period. (I don't know enough about the bandwidth tests in Sandra to know if they are any good - my comments are targeted only at the FPU / ALU portion). -fyo