Conference paper

POLOK Lukáš, ILA Viorela S. and SMRŽ Pavel. Fast Sparse Matrix Multiplication on GPU. In: Proceedings of the 23rd High Performance Computing Symposium (HPC'15). Alexandria, Virginia: Association for Computing Machinery, 2015, pp. 1-8. ISBN 1-56555-355-1. Available from: http://dl.acm.org/citation.cfm?id=2872604
Publication language:english
Original title:Fast Sparse Matrix Multiplication on GPU
Title (cs):Rychlé násobení řídkých matic na GPU
Pages:1-8
Proceedings:Proceedings of the 23rd High Performance Computing Symposium (HPC'15)
Conference:23rd High Performance Computing Symposium
Place:Alexandria, Virginia, US
Year:2015
URL:http://dl.acm.org/citation.cfm?id=2872604
ISBN:1-56555-355-1
Publisher:Association for Computing Machinery
Files: 
+Type Name Title Size Last modified
iconspringsim.pdf1,36 MB2015-03-11 15:41:42
^ Select all
With selected:
Keywords

parallel sparse matrix multiplication, parallel linear algebra, matrix-matrix multiplication, GPGPU

Annotation

Sparse matrix multiplication is an important algorithm in a wide variety of problems, including graph algorithms, simulations and linear solving to name a few. Yet, there are but a few works related to acceleration of sparse matrix multiplication on a GPU. We present a fast, novel algorithm for sparse matrix multiplication, outperforming the previous algorithm on GPU up to 3x and CPU up to 30x. The principal improvements include more efficient load balancing strategy, and a faster sorting algorithm. The main contribution is design and implementation of efficient sparse matrix multiplication algorithm and extending it to sparse block matrices, which is to our best knowledge the first implementation of this kind.

BibTeX:
@INPROCEEDINGS{
   author = {Luk{\'{a}}{\v{s}} Polok and S. Viorela Ila and
	Pavel Smr{\v{z}}},
   title = {Fast Sparse Matrix Multiplication on GPU},
   pages = {1--8},
   booktitle = {Proceedings of the 23rd High Performance Computing Symposium
	(HPC'15)},
   year = {2015},
   location = {Alexandria, Virginia, US},
   publisher = {Association for Computing Machinery},
   ISBN = {1-56555-355-1},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10835}
}

Your IPv4 address: 54.234.228.78
Switch to IPv6 connection

DNSSEC [dnssec]