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: Rink who wrote (210915)	9/14/2006 6:14:20 PM
From: ChrisBBo	Read Replies (1) \| Respond to of 275872

Can you provide any insight if and how relevant the reduction in power is as a result of wire scaling? Switched power consumption - that is power excluding leakage - is proportional to frequency and capacitance in wires and transistors. Further, it is inversely proportinal to voltage squared. So, wire capacitance has a first order effect on power consumption. Specifically, Power=Constant*WireCapacitance+OtherPower. "OtherPower" is made up of leakage and capacitance contributions from transistors. I have no clue about the relative weighting between wiring and "OtherPower" of a 90nm K8, 65nm K8 or 65nm K8L. Maybe "OtherPower" is 50%, maybe it's less, maybe much less. A better way to look at the subject of power consumption and multi cores, is to look at the fact that, currently, a ~15% frequency reduction typically allows for a 50% power reduction. This will probably be no different for 65nm. Using this rule of thumb, a 4GHz single core and a 2.8GHz quad core should consume about the same amount of power.