A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoC

With forecasted hundreds of processing elements (PEs), future embedded systems will be able to handle multiple applications with very diverse running constraints. Systems will integrate distributed decision capabilities. In order to control the power and temperature, dynamic voltage frequency scalin...

Full description

Saved in:
Bibliographic Details
Main Authors: Diego Puschini, Fabien Clermidy, Pascal Benoit, Gilles Sassatelli, Lionel Torres
Format: Article
Language:English
Published: Wiley 2008-01-01
Series:International Journal of Reconfigurable Computing
Online Access:http://dx.doi.org/10.1155/2008/403086
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832563233098039296
author Diego Puschini
Fabien Clermidy
Pascal Benoit
Gilles Sassatelli
Lionel Torres
author_facet Diego Puschini
Fabien Clermidy
Pascal Benoit
Gilles Sassatelli
Lionel Torres
author_sort Diego Puschini
collection DOAJ
description With forecasted hundreds of processing elements (PEs), future embedded systems will be able to handle multiple applications with very diverse running constraints. Systems will integrate distributed decision capabilities. In order to control the power and temperature, dynamic voltage frequency scalings (DVFSs) are applied at PE level. At system level, it implies to dynamically manage the different voltage/frequency couples of each tile to obtain a global optimization. This paper introduces a scalable multiobjective approach based on game theory, which adjusts at run-time the frequency of each PE. It aims at reducing the tile temperature while maintaining the synchronization between application tasks. Results show that the proposed run-time algorithm requires an average of 20 calculation cycles to find the solution for a 100-processor platform and reaches equivalent performances when comparing with an offline method. Temperature reductions of about 23% were achieved on a demonstrative test-case.
format Article
id doaj-art-9957f8cecf82422da61fd853bcff66db
institution Kabale University
issn 1687-7195
1687-7209
language English
publishDate 2008-01-01
publisher Wiley
record_format Article
series International Journal of Reconfigurable Computing
spelling doaj-art-9957f8cecf82422da61fd853bcff66db2025-02-03T01:20:39ZengWileyInternational Journal of Reconfigurable Computing1687-71951687-72092008-01-01200810.1155/2008/403086403086A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoCDiego Puschini0Fabien Clermidy1Pascal Benoit2Gilles Sassatelli3Lionel Torres4CEA /Leti-Minatec, 17 rue des Martyrs, 38054 Grenoble Cedex 9, FranceCEA /Leti-Minatec, 17 rue des Martyrs, 38054 Grenoble Cedex 9, FranceLIRMM, University of Montpellier 2/CNRS UMR 5506, 161 rue Ada, 34392 Montpellier Cedex 5, FranceLIRMM, University of Montpellier 2/CNRS UMR 5506, 161 rue Ada, 34392 Montpellier Cedex 5, FranceLIRMM, University of Montpellier 2/CNRS UMR 5506, 161 rue Ada, 34392 Montpellier Cedex 5, FranceWith forecasted hundreds of processing elements (PEs), future embedded systems will be able to handle multiple applications with very diverse running constraints. Systems will integrate distributed decision capabilities. In order to control the power and temperature, dynamic voltage frequency scalings (DVFSs) are applied at PE level. At system level, it implies to dynamically manage the different voltage/frequency couples of each tile to obtain a global optimization. This paper introduces a scalable multiobjective approach based on game theory, which adjusts at run-time the frequency of each PE. It aims at reducing the tile temperature while maintaining the synchronization between application tasks. Results show that the proposed run-time algorithm requires an average of 20 calculation cycles to find the solution for a 100-processor platform and reaches equivalent performances when comparing with an offline method. Temperature reductions of about 23% were achieved on a demonstrative test-case.http://dx.doi.org/10.1155/2008/403086
spellingShingle Diego Puschini
Fabien Clermidy
Pascal Benoit
Gilles Sassatelli
Lionel Torres
A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoC
International Journal of Reconfigurable Computing
title A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoC
title_full A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoC
title_fullStr A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoC
title_full_unstemmed A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoC
title_short A Game-Theoretic Approach for Run-Time Distributed Optimization on MP-SoC
title_sort game theoretic approach for run time distributed optimization on mp soc
url http://dx.doi.org/10.1155/2008/403086
work_keys_str_mv AT diegopuschini agametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT fabienclermidy agametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT pascalbenoit agametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT gillessassatelli agametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT lioneltorres agametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT diegopuschini gametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT fabienclermidy gametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT pascalbenoit gametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT gillessassatelli gametheoreticapproachforruntimedistributedoptimizationonmpsoc
AT lioneltorres gametheoreticapproachforruntimedistributedoptimizationonmpsoc