Improving Reactivity and Communication Overlap in MPI using a Generic I/O Manager
TRAHAY, François
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
DENIS, Alexandre
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
AUMAGE, Olivier
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Voir plus >
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
TRAHAY, François
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
DENIS, Alexandre
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
AUMAGE, Olivier
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
NAMYST, Raymond
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
< Réduire
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Langue
en
Communication dans un congrès
Ce document a été publié dans
EuroPVM/MPI 2007, 2007-10, Paris. 2007, vol. 4757, p. 170-177
Springer
Résumé en anglais
MPI applications may waste thousands of CPU cycles if they do not efficiently overlap communications and computation. In this paper, we present a generic and portable I/O manager that is able to make communication progress ...Lire la suite >
MPI applications may waste thousands of CPU cycles if they do not efficiently overlap communications and computation. In this paper, we present a generic and portable I/O manager that is able to make communication progress asynchronously using tasklets. It chooses automatically the most appropriate communication method, depending on the context: multi-threaded application or not, SMP machine or not. We have implemented and evaluated our I/O manager with Mad-MPI, our own MPI implementation, and compared it to other existing MPI implementations regarding the ability to efficiently overlap communication and computation.< Réduire
Mots clés en anglais
Polling
Interrupt
Thread
Scheduler
High-Speed Network
Pioman
NewMadeleine
Origine
Importé de halUnités de recherche