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 : AMD:News, Press Releases and Information Only! -- Ignore unavailable to you. Want to Upgrade?

To: StockMan who wrote (4829)	3/8/1998 4:33:00 PM
From: Maxwell	Read Replies (2) \| Respond to of 6843

Stockman: <<Those benchmarks don't say a darn thing. It measures individual timing. Real world applications will provide entirely different results.>> I definitely agree. So what is your suggestion on how to gauge different CPUs? Each CPU has its strength and weakness and each application will require more of certain executions than other. <<You contradict yourself in the same statement. An architecture is not how well you do in memory to memory transfer instructions, but in different application mix.>> No I didn't. When I argued with Yousef we assume a CPU only and nothing of the peripheral components. If you want to talk about memory to memory transfer than you need to include the memory, the L2 cache, the chipset, and the bus. <<Thus Cyrix architecture is actually INFERIOR because they optimized for the wrong thing.>> It depends on what application you want to run. See Dr. Engel's message above. <<BTW "deep branches" are not neccessarily a good thing. Remember Madwell tradeoffs.>> I never said a good thing. The tradeoff is the speed. Reread my previous post. Maxwell