HOEFLER, Torsten; JEANNOT, Emmanuel; MERCIER, Guillaume

Métadonnées

Licence d’utilisation du document

HOEFLER, Torsten
Department of Computer Science [ETH Zürich] [D-INFK]

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

MERCIER, Guillaume
Institut Polytechnique de Bordeaux
Efficient runtime systems for parallel architectures [RUNTIME]
Laboratoire Bordelais de Recherche en Informatique [LaBRI]

Langue

Chapitre d'ouvrage

Ce document a été publié dans

High Performance Computing on Complex Environments, High Performance Computing on Complex Environments. 2014-06p. 75-94

Wiley

Résumé en anglais

Due to the advent of modern hardware architectures of high-performance comput- ers, the way the parallel applications are laid out is of paramount importance for performance. This chapter surveys several techniques and algorithms that efficiently address this issue: the mapping of the application's virtual topology (for instance its communication pattern) onto the physical topology. Using such strategy enables to improve the application overall execution time significantly. The chapter concludes by listing a series of open issues and problems.< Réduire

Métadonnées

Partager cette publication !

Licence d’utilisation du document

An Overview of Process Mapping Techniques and Algorithms in High-Performance Computing

Langue

Ce document a été publié dans

Résumé en anglais

URI

Origine

Unités de recherche