Dodging Non-Uniform I/O Access in Hierarchical Collective Operations for Multicore Clusters

Brice Goglin 1, 2 Stéphanie Moreaud 1, 2
2 RUNTIME - Efficient runtime systems for parallel architectures
Inria Bordeaux - Sud-Ouest, UB - Université de Bordeaux, CNRS - Centre National de la Recherche Scientifique : UMR5800
Abstract : The increasing number of cores led to scalability issues in modern servers that were addressed by using non-uniform memory interconnects such as HyperTransport and QPI. These technologies reintroduced Non-Uniform Memory Access (NUMA) architectures. They are also responsible for Non-Uniform Input/Output Access (NUIOA), as I/O devices may be directly connected to a single processor, thus getting faster access to some cores and memory banks than to the others. In this paper, we propose to adapt MPI collective operations to NUIOA constraints. These operations are now often based on the combination of multiple strategies depending on the underlying cluster topology, with local leader processes being used as intermediate. Our strategy focuses on electing these leaders according to the locality of processes and network interfaces so as to give them privileged network access. We validate our approach on a hierarchical Broadcast operation which brings up to 25% throughput improvement between 64 processes.
Type de document :
Communication dans un congrès
IEEE. CASS 2011: The 1st Workshop on Communication Architecture for Scalable Systems, held in conjunction with IPDPS 2011, May 2011, Anchorage, United States. 7p, 2011, <10.1109/IPDPS.2011.222>


https://hal.inria.fr/inria-00566246
Contributeur : Brice Goglin <>
Soumis le : mercredi 16 février 2011 - 15:01:36
Dernière modification le : jeudi 10 septembre 2015 - 01:06:43
Document(s) archivé(s) le : mardi 6 novembre 2012 - 14:01:33

Fichier

article.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Brice Goglin, Stéphanie Moreaud. Dodging Non-Uniform I/O Access in Hierarchical Collective Operations for Multicore Clusters. IEEE. CASS 2011: The 1st Workshop on Communication Architecture for Scalable Systems, held in conjunction with IPDPS 2011, May 2011, Anchorage, United States. 7p, 2011, <10.1109/IPDPS.2011.222>. <inria-00566246>

Exporter

Partager

Métriques

Consultations de
la notice

621

Téléchargements du document

259