Detail publikace

Fast Radix Sort for Sparse Linear Algebra on GPU

POLOK, L. ILA, V. SMRŽ, P.

Originální název

Fast Radix Sort for Sparse Linear Algebra on GPU

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

POLOK, L.; ILA, V.; SMRŽ, P.

Rok RIV

2014

Vydáno

16. 4. 2014

Nakladatel

Association for Computing Machinery

Místo

Tampa

ISBN

1-56555-353-5

Kniha

Proceedings of the 22nd High Performance Computing Symposium (HPC'14)

Strany od

1

Strany do

8

Strany počet

8

URL

BibTex

@inproceedings{BUT111565,
  author="Lukáš {Polok} and Viorela Simona {Ila} and Pavel {Smrž}",
  title="Fast Radix Sort for Sparse Linear Algebra on GPU",
  booktitle="Proceedings of the 22nd High Performance Computing Symposium (HPC'14)",
  year="2014",
  pages="1--8",
  publisher="Association for Computing Machinery",
  address="Tampa",
  isbn="1-56555-353-5",
  url="http://dl.acm.org/citation.cfm?id=2663521"
}