A Note on the Performance of Sparse Matrix-vector Multiplication with Column Reordering

We revisit ordering techniques as a preprocessing step for improving the performance of sparse matrix-vector multiplication (SpM x V) on modern hierarchical memory computers. In computing SpM x V the main purpose of ordering of columns (or rows) is to improve the performance by enhancing data reuse....

Full description

Saved in:
Bibliographic Details
Published inInternational Conference of Computing in Engineering, Science and Information pp. 23 - 26
Main Authors Haque, S.A., Hossain, S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2009
Subjects
Bandwidth
Computer science
Data structures
Drives
Mathematics
Performance gain
Reflective binary codes
Sparse matrices
Testing
Vectors
Online AccessGet full text
ISBN9780769535388
0769535380
DOI10.1109/ICC.2009.40

Cover

More Information
Summary:We revisit ordering techniques as a preprocessing step for improving the performance of sparse matrix-vector multiplication (SpM x V) on modern hierarchical memory computers. In computing SpM x V the main purpose of ordering of columns (or rows) is to improve the performance by enhancing data reuse. We present a new ordering technique based on the binary reflected gray codes and experimentally evaluate and compare it with other column ordering techniques from the literature. The results from numerical experiments with very large test matrices clearly demonstrates the performance gains rendered by our proposed technique.
ISBN:9780769535388
0769535380
DOI:10.1109/ICC.2009.40