Energy efficient task scheduling on a multi-core platform using real-time energy measurements

Abstract

This paper presents a large advance in energy-efficient operating system multiprocessor task scheduling with experimentally proven benefits for standard Linux multi-core computing platforms. This Energy Aware Scheduler (EAS) introduces micro-Operations executed Per Joule (OPJ) as a metric representing run-time task energy efficiency. A novel platform architecture permits eventresolved real-time energy measurements. EAS uses OPJ values for scheduling tasks to reduce resource contention. Compared to the Linux task scheduler (Completely Fair Scheduler), EAS improves energy efficiency by over 30% and execution time by over 24%.