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: AK2004 who wrote (200903)	6/8/2006 12:12:39 AM
From: brushwud	Read Replies (1) \| Respond to of 275872

with current frequency of transitions from one process to another the cost benefit maybe negative. It makes sense to move to larger wafers for cost reduction Process transitions are still happening about every two years as they have for fifty years according to Moore's Law. Processes are getting more complex, but the number of transistors per mm^2 is still going up exponentially, so they are getting cheaper. Yes, moving to larger wafers is always for cost reduction, but subject to Rock's Law: en.wikipedia.org I think lower geometry implys less power but, and I maybe completely wrong here, less power does not imply higher frequency Electronics has always had a speed-power tradeoff. Sometimes the power-delay product is used as a figure of merit for a given level of process technology. Delay is the reciprocal of speed and powerdelay is a measure of how much energy it takes to make a state transition. That's what a designer gets to work with and you can decrease power only by increasing delay and vice versa. Now as process technology improves (but not necessarily smaller), powerdelay decreases, so if a designer is trying to fit into a constant thermal envelope like 65 W, he does get to increase frequency.