Publication Details

Fast Radix Sort for Sparse Linear Algebra on GPU

POLOK Lukáš, ILA Viorela S. and SMRŽ Pavel. Fast Radix Sort for Sparse Linear Algebra on GPU. In: Proceedings of the 22nd High Performance Computing Symposium (HPC'14). Tampa: Association for Computing Machinery, 2014, pp. 1-8. ISBN 1-56555-353-5. Available from: http://dl.acm.org/citation.cfm?id=2663521
Czech title
Rychlé radixové řazení pro řídkou lineární algebru na GPU
Type
conference paper
Language
english
Authors
Polok Lukáš, Ing. (DCGM FIT BUT)
Ila Viorela S., Ing., Ph.D. (DCGM FIT BUT)
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT)
URL
Keywords

Parallel sorting, radix sort, sparse matrix, matrix-matrix multiplication.

Abstract

Fast sorting is an important step in many parallel algorithms, which require data ranking, ordering or partitioning. Parallel sorting is a widely researched subject, and many algorithms were developed in the past. In this paper, the focus is on implementing highly efficient sorting routines for the sparse linear algebra operations, such as parallel sparse matrix - matrix multiplication, or factorization. We propose a fast and simple to implement variant of parallel radix sort algorithm, suitable for GPU architecture.

Published
2014
Pages
1-8
Proceedings
Proceedings of the 22nd High Performance Computing Symposium (HPC'14)
Conference
22nd High Performance Computing Symposium, Tampa, Florida, US
ISBN
1-56555-353-5
Publisher
Association for Computing Machinery
Place
Tampa, US
BibTeX 
@INPROCEEDINGS{FITPUB10598,
   author = "Luk\'{a}\v{s} Polok and S. Viorela Ila and Pavel Smr\v{z}",
   title = "Fast Radix Sort for Sparse Linear Algebra on GPU",
   pages = "1--8",
   booktitle = "Proceedings of the 22nd High Performance Computing Symposium (HPC'14)",
   year = 2014,
   location = "Tampa, US",
   publisher = "Association for Computing Machinery",
   ISBN = "1-56555-353-5",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10598"
}
Files
Back to top