A scheduling selection process for energy-efficient task execution on DVFS processors

摘要

The efficient execution of parallel programs with respect to execution time and energy consumption is a major concern, and often, scheduling methods are used to achieve a good performance. In this article, we consider the problem of scheduling a set of independent tasks on a parallel system with homogeneous execution units providing frequency scaling. The set of tasks has the property that the tasks exhibit a task-specific inhomogeneous and non-linear behavior of their specific time-energy relation. In addition, it is assumed that execution time and energy consumption behave in a non-linearmannerwith respect to frequency scaling. For the assignment of these tasks to execution units, we propose a scheduling selection process combining scheduling algorithms, which determine a task assignment, with a subsequent selection of frequency scaling, whichwe call schedule executionmodes. This process builds a rich set of alternative schedule executionmodes from which efficient (or Pareto-optimal) schedule executionmodes can be selected. Experiments are done for the SPEC CPU benchmarks. Experimental results illustrate that the enriched scheduling process leads to task assignments resulting in an efficient execution onDVFS processors.