DENIS, Alexandre

Métadonnées

Licence d’utilisation du document

DENIS, Alexandre
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]

Langue

Communication dans un congrès

Ce document a été publié dans

Euro-Par 2011, 2011-08-29, Bordeaux. 2011-08-29, vol. 6853, p. 276-287

Springer

Résumé en anglais

InfiniBand high performance networks require that the buffers used for sending or receiving data are registered. Since memory registration is an expensive operation, some communication libraries use caching (rcache) to amortize its cost, and copy data into pre-registered buffers for small messages. In this paper, we present a software protocol for InfiniBand that always uses a memory copy, and amortizes the cost of this copy with a superpipeline to overlap the memory copy and the RDMA. We propose a performance model of our protocol to study its behavior and optimize its parameters. We have implemented our protocol in the NewMadeleine communication library. The results of MPI benchmarks show a significant improvement in cache-unfriendly applications that do not reuse the same memory blocks all over the time, without degradation for cache-friendly applications.< Réduire

Mots clés en anglais

NewMadeleine

InfiniBand

MadMPI

MPI

CORBA

URI

https://oskar-bordeaux.fr/handle/20.500.12278/198108

Project ANR

Gestion de ressources coopérative multi niveaux - ANR-09-COSI-0001

Origine

Importé de hal

Unités de recherche

Laboratoire Bordelais de Recherche en Informatique (LaBRI) - UMR 5800