Power consumption is hard to predict even with a reasonable amount of architectural information and that is underlined in a paper that appeared at the Architectural Support for Programming Languages and Operating Systems (ASPLOS) conference last April. but recently picked up by LinuxDevices. In the paper, the researchers argue that processor maker need to make power information for their products more readily available to software developers.
Kathryn McKinley of the University of Texas at Austin and Stephen Blackburn of the Australian National University with several graduate students instrumented a range of PCs made from 2003 to 2010 for their paper "Looking Back on the Language and Hardware Revolutions: Measured Power, Performance and Scaling".
Naturally, later processors do better on power consumption: "A die shrink is remarkably effective at reducing energy consumption, even when controlling for clock frequency." And simultaneous multithreading results in big energy savings for the Core i5 and Atom processors.
However, things are not necessarily straightforward:
"Halving the clock rate of the Core i5 (32nm) increases its energy consumption around 4 per cent, whereas it decreases the energy consumption of the Core i7 (45nm) and Core 2 Duo (45nm) by around 60 per cent...Running the i5 (32nm) at its peak clock rate is as energy-efficient as running it at its lowest, whereas running the i7 and Core 2 Duo at their lowest clock rate is substantially more energy efficient than their peak."
The 2012 ASPLOS is coming up at the start of March and will be held in London and has a number of power-related papers that I'll be covering later on.
Leave a comment