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: Ali Chen who wrote (78751)	4/29/2002 9:48:21 PM
From: pgerassi	Read Replies (1) \| Respond to of 275872

Dear Ali: AC skin effect does not come into play as the skin is already to thin to have a core. DC resistance varies by the inverse of the process size assuming that the wires are shrunk vertically as well. However the capacitance varies by the process size again assuming the distance between the traces are about the same. Thus the RC time constant of a cubic wire element is about the same over the processes. However the big variable which is neglected in these researches is quantum effects which by most accounts appear in significant amounts at 100nm which is just the next process size. I do not remember at which process size the quantum effects begin to dominate over the EM effects. Strange effects begin to be felt. All of this has accelerants since the amount of extra performance for each new transistor is beginning to shrink dramatically for a typical GP CPU. It is already known that a number of cheap low cost CPUs outperforms any single CPU for most problems. This trend is likely to accelerate. There are many DSP systems where multiple simple DSPs are used to outperform a single far more expensive fast DSP. The wait for something similar to happen with desktop GP CPU is not long. That is why CMP may be an idea whose time has come to the x86 world. Pete