In EDS ansehen

TProf: An energy profiler for task-parallel programs.

Gespeichert in:
Bibliographische Detailangaben
Titel: TProf: An energy profiler for task-parallel programs.
Autoren: Manousakis, Ioannis1 im159@cs.rutgers.edu, Zakkak, Foivos S.2 zakkak@ics.forth.gr, Pratikakis, Polyvios2 polyvios@ics.forth.gr, Nikolopoulos, Dimitrios S.3 d.nikolopoulos@qub.ac.uk
Quelle: Sustainable Computing: Informatics & Systems. Mar2015, Vol. 5, p1-13. 13p.
Schlagwörter: Parallel programs (Computer programs), Energy consumption, Mathematical models, Analysis of variance, Parameter estimation
Abstract: We present TProf , an energy profiling tool for OpenMP-like task-parallel programs. To compute the energy consumed by each task in a parallel application, TProf dynamically traces the parallel execution and uses a novel technique to estimate the per-task energy consumption. To achieve this estimation, TProf apportions the total processor energy among cores and overcomes the limitation of current works which would otherwise make parallel accounting impossible to achieve. We demonstrate the value of TProf by characterizing a set of task parallel programs, where we find that data locality, memory access patterns and task working sets are responsible for significant variance in energy consumption between seemingly homogeneous tasks. In addition, we identify opportunities for fine-grain energy optimization by applying per-task Dynamic Voltage and Frequency Scaling (DVFS). [ABSTRACT FROM AUTHOR]
Datenbank: Supplemental Index
Beschreibung
Abstract:We present TProf , an energy profiling tool for OpenMP-like task-parallel programs. To compute the energy consumed by each task in a parallel application, TProf dynamically traces the parallel execution and uses a novel technique to estimate the per-task energy consumption. To achieve this estimation, TProf apportions the total processor energy among cores and overcomes the limitation of current works which would otherwise make parallel accounting impossible to achieve. We demonstrate the value of TProf by characterizing a set of task parallel programs, where we find that data locality, memory access patterns and task working sets are responsible for significant variance in energy consumption between seemingly homogeneous tasks. In addition, we identify opportunities for fine-grain energy optimization by applying per-task Dynamic Voltage and Frequency Scaling (DVFS). [ABSTRACT FROM AUTHOR]
ISSN:22105379
DOI:10.1016/j.suscom.2014.07.004