Performance Prediction and Analysis of Parallel Out-of-Core Matrix Factorization

Caron, Eddy; Lazure, Dominique; Utard, Gil

doi:10.1007/3-540-44467-x_15

Cited by 4 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This out-of-core function was also modified to allow the overlap of I/O by computation. Then, the performance is very close to the theoretical performance of the in-core algorithm on a (virtual) machine with no physical memory limit (see [9] for details). Unfortunately, only few out-of-core routines are provided in SCALAPACK.…”

Section: Out-of-core Extensionssupporting

confidence: 64%

Scilab to Scilab//: The Ouragan project

Caron¹,

Chaumette

Contassot-Vivier³

et al. 2001

Parallel Computing

View full text Add to dashboard Cite

Abstract:In this paper, we present the developments realized in the OURAGAN project around the parallelization of a MATLAB-like tool called SCILAB. These developments use high performance numerical libraries and different approaches based either on the duplication of SCILAB processes or on computational servers. This tool, SCILAB¢ £ ¢ , allows users to perform high level operations on distributed matrices in a metacomputing environment. We also present performance results on different architectures. De SCILAB à SCILAB -Le projet OURAGAN Résumé : Dans cet article, nous présentons la parallélisation d'un outil de type MATLAB appelé SCILAB qui utilise des bibliothèques à hautes performances et différentes approches basées soit sur la duplication de processus SCILAB ou l'utilisation de serveurs de calcul. Cet outil permet d'effectuer des opérations de haut niveau sur des matrices distribuées dans un environnement de métacomputing. Nous présentons également des résultats de performances sur différentes architectures. Key-words: Mots-clé : SCILAB¢ £ ¢, bibliothèques parallèles, serveurs de calcul, CORBA, redistribution de données.

show abstract

Section: Out-of-core Extensionssupporting

confidence: 64%

Scilab to Scilab//: The Ouragan project

Caron¹,

Chaumette

Contassot-Vivier³

et al. 2001

Parallel Computing

View full text Add to dashboard Cite

show abstract

Mixed parallel implementations of the top level step of Strassen and Winograd matrix multiplication algorithms

Desprez

Suter²

Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001

View full text Add to dashboard Cite

This paper presents parallel implementations of the top level of Strassen and Winograd algorithms for matrix multiplication that use mixed-parallelism, i.e., simultaneous exploitation of data-and task-parallelism. This paradigm allows a better task placement and reduces the communication costs. A comparison with the ScaLAPACK implementation of the matrix multiplication is given. We present a theoretical evaluation of the algorithms which is corroborated by experiments.

show abstract

Parallel out-of-core matrix inversion

Caron

Utard

2002

Proceedings 16th International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

Performance Prediction and Analysis of Parallel Out-of-Core Matrix Factorization

Cited by 4 publications

References 7 publications

Scilab to Scilab//: The Ouragan project

Scilab to Scilab//: The Ouragan project

Mixed parallel implementations of the top level step of Strassen and Winograd matrix multiplication algorithms

Parallel out-of-core matrix inversion

Contact Info

Product

Resources

About