ON two-dimensional sparse matrix partitioning: models, methods, and a recipe
Author
Çatalyürek, U. V.
Aykanat, Cevdet
Uçar, A.
Date
2010Source Title
SIAM Journal on Scientific Computing
Print ISSN
1064-8275
Publisher
Society for Industrial and Applied Mathematics
Volume
32
Issue
2
Pages
656 - 683
Language
English
Type
ArticleItem Usage Stats
132
views
views
215
downloads
downloads
Abstract
We consider two-dimensional partitioning of general sparse matrices for parallel sparse matrix-vector multiply operation. We present three hypergraph-partitioning-based methods, each having unique advantages. The first one treats the nonzeros of the matrix individually and hence produces fine-grain partitions. The other two produce coarser partitions, where one of them imposes a limit on the number of messages sent and received by a single processor, and the other trades that limit for a lower communication volume. We also present a thorough experimental evaluation of the proposed two-dimensional partitioning methods together with the hypergraph-based one-dimensional partitioning methods, using an extensive set of public domain matrices. Furthermore, for the users of these partitioning methods, we present a partitioning recipe that chooses one of the partitioning methods according to some matrix characteristics. © 2010 Society for Industrial and Applied Mathematics.
Keywords
Combinatorial scientific computingHypergraph partitioning
Parallel matrix-vector multiplication
Sparse matrix partitioning
Two-dimensional partitioning
Experimental evaluation
Hypergraph
Matrix vector multiplication
One-dimensional partitioning
Partitioning methods
Public domains
Scientific computing
Single processors
Sparse matrices
Matrix algebra
Permalink
http://hdl.handle.net/11693/22351Published Version (Please cite this version)
http://dx.doi.org/10.1137/080737770Collections
Related items
Showing items related by title, author, creator and subject.
-
Encapsulating multiple communication-cost metrics in partitioning sparse rectangular matrices for parallel matrix-vector multiplies
Uçar, B.; Aykanat, Cevdet (SIAM, 2004)This paper addresses the problem of one-dimensional partitioning of structurally unsymmetric square and rectangular sparse matrices for parallel matrix-vector and matrix-transpose-vector multiplies. The objective is to ... -
Improving performance of sparse matrix dense matrix multiplication on large-scale parallel systems
Acer, S.; Selvitopi, O.; Aykanat, Cevdet (Elsevier BV, 2016)We propose a comprehensive and generic framework to minimize multiple and different volume-based communication cost metrics for sparse matrix dense matrix multiplication (SpMM). SpMM is an important kernel that finds ... -
Fast optimal load balancing algorithms for 1D partitioning
Pınar, A.; Aykanat, Cevdet (Academic Press, 2004)The one-dimensional decomposition of nonuniform workload arrays with optimal load balancing is investigated. The problem has been studied in the literature as the "chains-on-chains partitioning" problem. Despite the rich ...