Interleaved parallel schemes : improving memory throughput on supercomputers - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 1992

Interleaved parallel schemes : improving memory throughput on supercomputers

André Seznec

Résumé

On many commercial supercomputers, several vector register processors share a global highly interleaved memory in a MIMD mode. When all the processors are working on a single verctor loop, a significant part of the potential memory throughput may be wasted due to the asynchronism of the processors. In order to limit loss of memory throughput, a SIMD synchronization mode for vector accesses to memory may be used. But an important part of the memory bandwith may be wasted when accessing vectors with an even stride. In this paper, we present IPS, an interleaved parallel scheme, which ensures an equitable distribution of elements on a highly interleaved memory for a wide range a vector strides. We show how to organize access to memory, such that unscrambling of vectors from memory to the vector register processors requires a minimum number of passes through the interconnection network.

Domaines

Autre [cs.OH]
Fichier principal
Vignette du fichier
RR-1656.pdf (803.77 Ko) Télécharger le fichier

Dates et versions

inria-00074901 , version 1 (24-05-2006)

Identifiants

  • HAL Id : inria-00074901 , version 1

Citer

André Seznec, Jacques Lenfant. Interleaved parallel schemes : improving memory throughput on supercomputers. [Research Report] RR-1656, INRIA. 1992. ⟨inria-00074901⟩
87 Consultations
137 Téléchargements

Partager

Gmail Facebook X LinkedIn More