Supercomputer Environment for Recursive Matrix Algorithms

A new runtime environment for the execution of recursive matrix algorithms on a supercomputer with distributed memory is proposed. It is designed both for dense and sparse matrices. The environment ensures decentralized control of the computation process. As an example of a block recursive algorithm...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Programming and computer software Jg. 48; H. 2; S. 90 - 101
Hauptverfasser: Malaschonok, G. I., Sidko, A. A.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Moscow Pleiades Publishing 01.04.2022
Springer Nature B.V
Schlagworte:
Algorithms
Artificial Intelligence
Cholesky factorization
Computer Science
Decentralized control
Distributed memory
Experiments
Mathematical analysis
Operating Systems
Software Engineering
Software Engineering/Programming and Operating Systems
Sparse matrices
Supercomputers
Workloads
ISSN:0361-7688, 1608-3261
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A new runtime environment for the execution of recursive matrix algorithms on a supercomputer with distributed memory is proposed. It is designed both for dense and sparse matrices. The environment ensures decentralized control of the computation process. As an example of a block recursive algorithm, the Cholesky factorization of a symmetric positive definite matrix in the form of a block dichotomous algorithm is described. The results of experiments with different numbers of cores are presented, demonstrating good scalability of the proposed solution.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0361-7688
1608-3261
DOI:10.1134/S0361768822020086