Distibuted Dense Numerical Linear Algebra Algorithms on massively parallel architectures: DPLASMA - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Distibuted Dense Numerical Linear Algebra Algorithms on massively parallel architectures: DPLASMA

Abstract

We present DPLASMA, a new project related to PLASMA, that operates in the distributed memory regime. It uses a new generic distributed Direct Acyclic Graph engine for high performance computing (DAGuE). Our work also takes advantage of some of the features of DAGuE, such as DAG representation that is independent of problem-size, overlapping of communication and computa- tion, task prioritization, architecture-aware scheduling and management of micro-tasks on distributed architectures that feature heterogeneous many-core nodes. The originality of this engine is that it is capable of translating a sequential nested-loop code into a concise and synthetic format which it can be interpret and then execute in a distributed environment. We consider three common dense linear algebra algorithms, namely: Cholesky, LU and QR factorizations, to investigate their data driven expression and execution in a distributed system. We demonstrate from our preliminary results that our DAG-based approach has the potential to bridge the gap between the peak and the achieved performance that is characteristic in the state-of-the-art distributed numerical softwares on current and emerging architectures.
Fichier principal
Vignette du fichier
DPLASMA_technical_report.pdf (400.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00809680 , version 1 (09-04-2013)

Identifiers

  • HAL Id : hal-00809680 , version 1

Cite

George Bosilca, Aurélien Bouteiller, Anthony Danalis, Mathieu Faverge, Azzam Haidar, et al.. Distibuted Dense Numerical Linear Algebra Algorithms on massively parallel architectures: DPLASMA. Proceedings of the 25th IEEE International Symposium on Parallel \& Distributed Processing Workshops and Phd Forum (IPDPSW'11), PDSEC 2011, May 2011, Anchorage, United States. pp.1432--1441. ⟨hal-00809680⟩
156 View
201 Download

Share

Gmail Facebook Twitter LinkedIn More