Hybrid parallel algorithm of general sparse matrix multiplication

Sparse matrix multiplication is widely used in scientific and engineering computations. It is a basic operation in scientific computation, but it faces many difficulties such as large data set, irregular distribution of non-zero values, load unbalancing and irregular distribution of column index of...

Full description

Saved in:
Bibliographic Details
Published in:Jisuanji Kexue yu Tansuo / Journal of Computer Science and Frontiers Vol. 7; no. 8; pp. 698 - 703
Main Authors: Luo, Haibiao, Wang, Ting, Zhang, Yunquan
Format: Journal Article
Language:Chinese
Published: 01.08.2013
Subjects:
Algorithms
Computation
Computer programs
Kernels
Libraries
Multiplication
Software
Stress concentration
ISSN:1673-9418
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sparse matrix multiplication is widely used in scientific and engineering computations. It is a basic operation in scientific computation, but it faces many difficulties such as large data set, irregular distribution of non-zero values, load unbalancing and irregular distribution of column index of the resulting matrix. This paper optimizes matrix partitioning, data communication, load balancing and parallel sort methods to tackle the above problems. The computing speed of the algorithm improves 56% in average at multithread over commercial software Intel MKL (Intel Math Kernel Library). This paper further develops MPI+OpenMP hybrid parallel algorithm for multiprocess that achieves similar efficiency on shared memory system.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1673-9418
DOI:10.3778/j.issn.1673-9418.1212018