2013 International Green Computing Conference Proceedings (2013)
Arlington, VA, USA
June 27, 2013 to June 29, 2013
Guillaume Aupy , LIP - ENS Lyon, France
Anne Benoit , LIP - ENS Lyon, France
Rami Melhem , University of Pittsburgh, USA
Paul Renaud-Goud , LIP - ENS Lyon, France
Yves Robert , LIP - ENS Lyon, France
In this paper, we aim at minimizing the energy consumption when executing a divisible workload under a bound on the total execution time, while resilience is provided through checkpointing. We discuss several variants of this multi-criteria problem. Given the workload, we need to decide how many chunks to use, what are the sizes of these chunks, and at which speed each chunk is executed. Furthermore, since a failure may occur during the execution of a chunk, we also need to decide at which speed a chunk should be re-executed in the event of a failure. The goal is to minimize the expectation of the total energy consumption, while enforcing a deadline on the execution time, that should be met either in expectation (soft deadline), or in the worst case (hard deadline). For each problem instance, we propose either an exact solution, or a function that can be optimized numerically.
Energy consumption, Checkpointing, High definition video, Numerical models, Reliability, Computational modeling, Optimization
G. Aupy, A. Benoit, R. Melhem, P. Renaud-Goud and Y. Robert, "Energy-aware checkpointing of divisible tasks with soft or hard deadlines," 2013 International Green Computing Conference Proceedings(IGCC), Arlington, VA, USA USA, 2013, pp. 1-8.