A Bottleneck-centric Tuning Policy for Optimizing Energy in Parallel Programs

Endrei, M, Jin, C, Dinh, M, Abramson, D, Poxon, H, DeRose, L and de Supinski, B 2018, 'A Bottleneck-centric Tuning Policy for Optimizing Energy in Parallel Programs', in Sanzio Bassini, Marco Danelutto, Patrizio Dazzi, Gerhard R. Joubert, and Frans Peters. (ed.) Proceedings of the International Conference on Parallel Computing (ParCo2017), Bologna, Italy, 12-15 September 2017, pp. 265-276.


Document type: Conference Paper
Collection: Conference Papers

Title A Bottleneck-centric Tuning Policy for Optimizing Energy in Parallel Programs
Author(s) Endrei, M
Jin, C
Dinh, M
Abramson, D
Poxon, H
DeRose, L
de Supinski, B
Year 2018
Conference name ParCo2017: Volume 32
Conference location Bologna, Italy
Conference dates 12-15 September 2017
Proceedings title Proceedings of the International Conference on Parallel Computing (ParCo2017)
Editor(s) Sanzio Bassini, Marco Danelutto, Patrizio Dazzi, Gerhard R. Joubert, and Frans Peters.
Publisher IOS Press
Place of publication Amsterdam, Netherlands
Start page 265
End page 276
Total pages 12
Abstract In order to operate within power supply constraints, the next generation of supercomputers must be energy efficient. Both the capacities of the target HPC system architecture and workload features impact the energy efficiency of parallel applications. These system and workload factors form a complicated optimization search space. Further, a typical workload may consist of multiple algorithmic kernels each with different power consumption patterns. Using the Parallel Research Kernels as a case study, we identify key bottlenecks that change the energy usage pattern and develop strategies that improve energy efficiency by optimizing both workload and system parameters in an automated manner. The method provides significant insights to identify repeatable, statistically significant energy saving opportunities for parallel applications at various scales.
Subjects Artificial Intelligence and Image Processing not elsewhere classified
Distributed Computing not elsewhere classified
Keyword(s) High Performance Computing
Energy Efficiency
Power Usage
DOI - identifier 10.3233/978-1-61499-843-3-265
Copyright notice © 2018 The all/hors a11d !OS Press. A II rights reserved.
ISBN 9781614998426
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 19 Abstract Views  -  Detailed Statistics
Created: Wed, 23 Oct 2019, 08:59:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us