Exposing Fine-Grained Parallelism in Algebraic Multigrid Methods

Algebraic multigrid methods for large, sparse linear systems are a necessity in many computational simulations, yet parallel algorithms for such solvers are generally decomposed into coarse-grained tasks suitable for distributed computers with traditional processing cores. However, accelerating mult...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:SIAM journal on scientific computing Jg. 34; H. 4; S. C123 - C152
Hauptverfasser: Bell, Nathan, Dalton, Steven, Olson, Luke N.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Philadelphia Society for Industrial and Applied Mathematics 01.01.2012
Schlagworte:
Aggregates
Algebra
Algorithms
Computation
Computer simulation
Cycles
Explicit knowledge
Exposure
Heuristic
High performance computing
Methods
Multigrid methods
Solvers
Sparsity
ISSN:1064-8275, 1095-7197
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Algebraic multigrid methods for large, sparse linear systems are a necessity in many computational simulations, yet parallel algorithms for such solvers are generally decomposed into coarse-grained tasks suitable for distributed computers with traditional processing cores. However, accelerating multigrid methods on massively parallel throughput-oriented processors, such as graphics processing units, demands algorithms with abundant fine-grained parallelism. In this paper, we develop a parallel algebraic multigrid method which exposes substantial fine-grained parallelism in both the construction of the multigrid hierarchy as well as the cycling or solve stage. Our algorithms are expressed in terms of scalable parallel primitives that are efficiently implemented on the GPU. The resulting solver achieves an average speedup of $1.8\times$ in the setup phase and $5.7\times$ in the cycling phase when compared to a representative CPU implementation. [PUBLICATION ABSTRACT]
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:1064-8275
1095-7197
DOI:10.1137/110838844