Kernel Assisted Collective Intra-node MPI Communication Among Multi-core and Many-core CPUs

Abstract : Shared memory is among the most common approaches to implementing message passing within multi-core nodes. However, current shared memory techniques do not scale with increasing numbers of cores and expanding memory hierarchies -- most notably when handling large data transfers and collective communication. Neglecting the underlying hardware topology, using copy-in/copy-out memory transfer operations, and overloading the memory subsystem using one-to-many types of operations are some of the most common mistakes in today's shared memory implementations. Unfortunately, they all negatively impact the performance and scalability of MPI libraries -- and therefore applications. In this paper, we present several kernel-assisted intra-node collective communication techniques that address these three issues on many-core systems. We also present a new Open MPI collective communication component that uses the KNEM Linux module for direct inter-process memory copying. Our Open MPI component implements several novel strategies to decrease the number of intermediate memory copies and improve data locality in order to diminish both cache pollution and memory pressure. Experimental results show that our KNEM-enabled Open\,MPI collective component can outperform state-of-art MPI libraries (Open\,MPI and MPICH2) on synthetic benchmarks, resulting in a significant improvement for a typical graph application.
Type de document :
Communication dans un congrès
IEEE. 40th International Conference on Parallel Processing (ICPP-2011), Sep 2011, Taipei, Taiwan. 2011, 〈10.1109/ICPP.2011.29〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00602877
Contributeur : Brice Goglin <>
Soumis le : jeudi 23 juin 2011 - 15:48:50
Dernière modification le : jeudi 11 janvier 2018 - 06:22:12
Document(s) archivé(s) le : vendredi 9 novembre 2012 - 16:52:00

Fichier

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

Identifiants

Collections

Citation

Teng Ma, George Bosilca, Aurélien Bouteiller, Brice Goglin, Jeffrey Squyres, et al.. Kernel Assisted Collective Intra-node MPI Communication Among Multi-core and Many-core CPUs. IEEE. 40th International Conference on Parallel Processing (ICPP-2011), Sep 2011, Taipei, Taiwan. 2011, 〈10.1109/ICPP.2011.29〉. 〈inria-00602877〉

Partager

Métriques

Consultations de la notice

486

Téléchargements de fichiers

258