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: Mary Cluney who wrote (57332)	10/5/2001 1:35:00 PM
From: fyodor_	Respond to of 275872

Mary: Physical IOCS has always been a limiting factor wrt performance from day one. Only today, the consumer is more knowledgeable and these issues now effect his effectiveness. Over the longer term however, frequency may, if anything become more important. It's more likely you could do away with Physical IOCS and rely entirely (or mostly) on Logical IOCS. I'm afraid you've misunderstood what I said. Certainly, frequency ramping is going to be extremely important - I did not mean to suggest that. The "problem" stems from a single chip no longer running at one single frequency, but different parts of the chip running at different frequencies. Examples of this include the Fireball core (ermm.. Netburst) of the P4 and the floating point unit of the C3. My claim was that, going forward, it is going to be harder and harder to come up with one meaningful frequency, which you can say that "the CPU" runs. Therefore, CPU performance is no longer well-characterized by a single frequency. This is partially true already, but will become increasingly so going forward. Individual sections of the device can still be attributed a frequency, of course, but describing the whole chip with one single frequency becomes meaningless and arbitrary. -fyo