Heterogeneous Implementation of Preconditioners Based on Gauss–Seidel Method for Sparse Block Matrices

In this paper we present a parallel preconditioner algorithm for the Krylov-type iterative method based on the multicolor Gauss–Seidel method and its transferable heterogeneous software implementation using the OpenCL computational standard. A special feature is its application to block sparse matri...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computational mathematics and modeling Ročník 33; číslo 4; s. 438 - 442
Hlavní autoři: Magomedov, A. R., Gorobets, A. V.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.10.2022
Springer Nature B.V
Témata:
Algorithms
Applications of Mathematics
Compressibility
Computational Mathematics and Numerical Analysis
Gauss-Seidel method
Hybrid systems
II. Numerical Methods
Iterative methods
Mathematical Modeling and Industrial Mathematics
Mathematics
Mathematics and Statistics
Optimization
Sparse matrices
Gauss–Seidel method
hybrid computing systems
preconditioner
sparse matrices
ISSN:1046-283X, 1573-837X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper we present a parallel preconditioner algorithm for the Krylov-type iterative method based on the multicolor Gauss–Seidel method and its transferable heterogeneous software implementation using the OpenCL computational standard. A special feature is its application to block sparse matrices as part of a numerical technique for modeling compressible turbulent flows. Optimization techniques are described that allow obtaining multiple speedups on graphics processors. Results of performance testing on a hybrid computing system are presented.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1046-283X
1573-837X
DOI:10.1007/s10598-023-09585-2