Abstract
Energy efficiency has been a growing concern for the embedded computing community for more than a decade. As a result, sophisticated methods for energy efficient processing have been developed leading to significant savings in hardware. The embedded computing community has recently turned its attention to software, where experts predict energy savings that far outweigh what can be achieved in hardware alone. We will present the state of the art in energy efficient software in embedded computing, describe the latest research at the University of Bristol in software energy efficiency modelling and introduce the audience to the Energy Aware COmputing (EACO) Initiative at Bristol. We will then look at how the concepts and techniques used to make software more energy efficient on embedded platforms are transferable to HPC.
Translated title of the contribution | Energy Efficient HPC Software: Learning from Embedded Systems Development |
---|---|
Original language | English |
Title of host publication | SIAM Conference on Parallel Processing for Scientific Computing |
Publisher | Society for Industrial and Applied Mathematics |
Number of pages | 30 |
Publication status | Published - 16 Feb 2012 |
Bibliographical note
Medium/genre: PresentationConference Organiser: SIAM