New algorithm for computing eigenvectors of the symmetric eigenvalue problem

Azzam Haidar; Piotr Luszczek; Jack Dongarra

doi:10.1109/IPDPSW.2014.130

New algorithm for computing eigenvectors of the symmetric eigenvalue problem

Azzam Haidar, Piotr Luszczek, Jack Dongarra

Computer Science and Mathematics Div

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

We describe a design and implementation of a multi-stage algorithm for computing eigenvectors of a dense symmetric matrix. We show that reformulating the existing algorithms is beneficial in terms of performance even if that doubles the computational complexity. Through detailed analysis, we show that the effect of the increase in the asymptotic operation count may be compensated by a much improved performance rate. Our performance results indicate that using our approach achieves very good speedup and scalability even when directly compared with the existing state-of-the-art software.

Original language	English
Title of host publication	Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014
Publisher	IEEE Computer Society
Pages	1150-1159
Number of pages	10
ISBN (Electronic)	9780769552088
DOIs	https://doi.org/10.1109/IPDPSW.2014.130
State	Published - Nov 27 2014
Event	28th IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014 - Phoenix, United States Duration: May 19 2014 → May 23 2014

Publication series

Name	Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014

Conference

Conference	28th IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014
Country/Territory	United States
City	Phoenix
Period	05/19/14 → 05/23/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

Dynamic runtime scheduling
Eigenvectors
Symmetric eigenvalue problem

Access to Document

10.1109/IPDPSW.2014.130

Cite this

Haidar, A., Luszczek, P., & Dongarra, J. (2014). New algorithm for computing eigenvectors of the symmetric eigenvalue problem. In Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014 (pp. 1150-1159). Article 6969512 (Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014). IEEE Computer Society. https://doi.org/10.1109/IPDPSW.2014.130

Haidar, Azzam ; Luszczek, Piotr ; Dongarra, Jack. / New algorithm for computing eigenvectors of the symmetric eigenvalue problem. Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014. IEEE Computer Society, 2014. pp. 1150-1159 (Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014).

@inproceedings{4fa60c3d829249e79298585df4a035da,

title = "New algorithm for computing eigenvectors of the symmetric eigenvalue problem",

abstract = "We describe a design and implementation of a multi-stage algorithm for computing eigenvectors of a dense symmetric matrix. We show that reformulating the existing algorithms is beneficial in terms of performance even if that doubles the computational complexity. Through detailed analysis, we show that the effect of the increase in the asymptotic operation count may be compensated by a much improved performance rate. Our performance results indicate that using our approach achieves very good speedup and scalability even when directly compared with the existing state-of-the-art software.",

keywords = "Dynamic runtime scheduling, Eigenvectors, Symmetric eigenvalue problem",

author = "Azzam Haidar and Piotr Luszczek and Jack Dongarra",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 28th IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014 ; Conference date: 19-05-2014 Through 23-05-2014",

year = "2014",

month = nov,

day = "27",

doi = "10.1109/IPDPSW.2014.130",

language = "English",

series = "Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014",

publisher = "IEEE Computer Society",

pages = "1150--1159",

booktitle = "Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014",

}

Haidar, A, Luszczek, P & Dongarra, J 2014, New algorithm for computing eigenvectors of the symmetric eigenvalue problem. in Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014., 6969512, Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014, IEEE Computer Society, pp. 1150-1159, 28th IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014, Phoenix, United States, 05/19/14. https://doi.org/10.1109/IPDPSW.2014.130

New algorithm for computing eigenvectors of the symmetric eigenvalue problem. / Haidar, Azzam; Luszczek, Piotr; Dongarra, Jack.
Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014. IEEE Computer Society, 2014. p. 1150-1159 6969512 (Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - New algorithm for computing eigenvectors of the symmetric eigenvalue problem

AU - Haidar, Azzam

AU - Luszczek, Piotr

AU - Dongarra, Jack

PY - 2014/11/27

Y1 - 2014/11/27

N2 - We describe a design and implementation of a multi-stage algorithm for computing eigenvectors of a dense symmetric matrix. We show that reformulating the existing algorithms is beneficial in terms of performance even if that doubles the computational complexity. Through detailed analysis, we show that the effect of the increase in the asymptotic operation count may be compensated by a much improved performance rate. Our performance results indicate that using our approach achieves very good speedup and scalability even when directly compared with the existing state-of-the-art software.

AB - We describe a design and implementation of a multi-stage algorithm for computing eigenvectors of a dense symmetric matrix. We show that reformulating the existing algorithms is beneficial in terms of performance even if that doubles the computational complexity. Through detailed analysis, we show that the effect of the increase in the asymptotic operation count may be compensated by a much improved performance rate. Our performance results indicate that using our approach achieves very good speedup and scalability even when directly compared with the existing state-of-the-art software.

KW - Dynamic runtime scheduling

KW - Eigenvectors

KW - Symmetric eigenvalue problem

UR - http://www.scopus.com/inward/record.url?scp=84918777379&partnerID=8YFLogxK

U2 - 10.1109/IPDPSW.2014.130

DO - 10.1109/IPDPSW.2014.130

M3 - Conference contribution

AN - SCOPUS:84918777379

T3 - Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014

SP - 1150

EP - 1159

BT - Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014

PB - IEEE Computer Society

T2 - 28th IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014

Y2 - 19 May 2014 through 23 May 2014

ER -

Haidar A, Luszczek P, Dongarra J. New algorithm for computing eigenvectors of the symmetric eigenvalue problem. In Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014. IEEE Computer Society. 2014. p. 1150-1159. 6969512. (Proceedings - IEEE 28th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2014). doi: 10.1109/IPDPSW.2014.130

New algorithm for computing eigenvectors of the symmetric eigenvalue problem

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this