Optimizing MPI Communication within large Multicore nodes with Kernel assistance
MOREAUD, Stéphanie
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
GOGLIN, Brice
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
See more >
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
MOREAUD, Stéphanie
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
GOGLIN, Brice
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
NAMYST, Raymond
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
< Reduce
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Language
en
Communication dans un congrès
This item was published in
Workshop on Communication Architecture for Clusters, held in conjunction with IPDPS 2010, 2010-04-19, Atlanta. 2010-04p. 7 p.
English Abstract
As the number of cores per node increases in modern clusters, intra-node communication efficiency becomes critical to application performance. We present a study of the traditional double-copy model in MPICH2 and a ...Read more >
As the number of cores per node increases in modern clusters, intra-node communication efficiency becomes critical to application performance. We present a study of the traditional double-copy model in MPICH2 and a kernel-assisted single-copy strategy with KNEM on different shared-memory hosts with up to 96 cores. We show that KNEM suffers less from process placement on these complex architectures. It improves throughput up to a factor of 2 for large messages for both point-to-point and collective operations, and significantly improves NPB execution time. We detail when to switch from one strategy to the other depending on the communication pattern and we show that \ioat copy offload only appears to be an interesting solution for older architectures.Read less <
Origin
Hal imported