Total Exchange Performance Modelling under Network Contention

Luiz Angelo Barchet Steffenel 1 Grégory Mounié 1
1 ID-IMAG - Informatique et Distribution
Abstract : One of the most important collective communication patterns for scientific applications is the many to many, also called complete exchange. Although efficient All-to-All algorithms have been studied for specific networks, general solutions like those found in well known MPI distributions are strongly influenced by the congestion of network resources. In this paper we present our approach to model the performance of the All-to-All collective operation. Our approach consists in identifying a contention factor that characterises the network environment, and using it to augment a contention-free communication model. This approach allows an accurate prediction of the performance of the All-to-All operation over different network environments with a small cost. Indeed, we demonstrate the accuracy of our approach by presenting our experiments with three different network environments, Fast Ethernet, Giga Ethernet and Myrinet.
Type de document :
Communication dans un congrès
Springer Verlag. international conference on Parallel Processing and Applied Mathematics, 2006, France. Springer Verlag, pp.100-107, 2006, number. 3911, ISSN 0302-9743. 〈10.1007/11752578_13〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-00022007
Contributeur : Luiz Angelo Steffenel <>
Soumis le : vendredi 31 mars 2006 - 00:22:19
Dernière modification le : mardi 24 avril 2018 - 13:35:19
Document(s) archivé(s) le : samedi 3 avril 2010 - 21:36:50

Fichier

PPAM05-Published.pdf

Identifiants

Collections

INRIA | IMAG | GRID5000 | UGA

Citation

Luiz Angelo Barchet Steffenel, Grégory Mounié. Total Exchange Performance Modelling under Network Contention. Springer Verlag. international conference on Parallel Processing and Applied Mathematics, 2006, France. Springer Verlag, pp.100-107, 2006, number. 3911, ISSN 0302-9743. 〈10.1007/11752578_13〉. 〈hal-00022007〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

258

Téléchargements de fichiers

123

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD