Platform Calibration for Load Balancing of Large Simulations: TLM Case

Cristian Ruiz; Mihai Alexandru; Olivier Richard; Thierry Monteil; Hervé Aubert

doi:10.1109/CCGrid.2014.26

Platform Calibration for Load Balancing of Large Simulations: TLM Case

Cristian Ruiz ^{1, *} Mihai Alexandru ^{2, 3} Olivier Richard ¹ Thierry Monteil ^{3, 2} Hervé Aubert ^{2, 3}

* Corresponding author

1 MESCAL - Middleware efficiently scalable

Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble

2 LAAS-SARA - Équipe Services et Architectures pour Réseaux Avancés

LAAS - Laboratoire d'analyse et d'architecture des systèmes [Toulouse]

3 INSA Toulouse - Institut National des Sciences Appliquées - Toulouse

Abstract : The heterogeneous nature of distributed platforms such as computational Grids is one of the main barriers to effectively deploy tightly-coupled applications. For those applications , one common problem that appears due to the hardware heterogeneity is the load imbalance which slows down the application to the pace of the slower processor. One solution is to distribute the load adequately taking into account hardware capacities. To do so, an estimation of the hardware capacities for running the application has to be obtained. In this paper, we present a static load balancing for iterative tightly-coupled applications based on a profile prediction model. This technique is presented as a successful example of the interaction between experiment management tools and parallel applications. The experiment management tool Expo is used that enabled to: (1) provide a general, lightweight and descriptive way to capture the tuning and deployment of a parallel application in a computing infrastructure, (2) perform the tuning of the application efficiently in terms of human effort and resources needed. This paper reports the costs for carrying out the tuning of a large electromagnetic simulation based on TLM for the platform Grid'5000 and the improvements obtained on the total execution time of the application.

Keywords : Transmission-line matrix methods Load balancing Experiment methodology Large scale system Grid computing High performance computing

Document type :

Conference papers

Domain :

Computer Science [cs]

Liste complète des métadonnées

Cited literature [20 references] Display Hide Download

https://hal.archives-ouvertes.fr/hal-01228344
Contributor : Thierry Monteil <>
Submitted on : Thursday, November 12, 2015 - 10:45:31 PM
Last modification on : Saturday, April 13, 2019 - 9:44:02 AM
Document(s) archivé(s) le : Friday, April 28, 2017 - 4:49:51 AM

MI9_CCGRID.pdf

Files produced by the author(s)

Platform Calibration for Load Balancing of Large Simulations: TLM Case

File

Identifiers

Collections

Citation

Export

Metrics

851

117

Contact

Platform Calibration for Load Balancing of Large Simulations: TLM Case

File

Identifiers

Collections

Citation

Export

Share

Metrics

851

117

Contact