From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation

Ahmed H. El Zein; Alistair P. Rendell

doi:10.1109/CCGRID.2010.81

From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation

Ahmed H. El Zein, Alistair P. Rendell

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

8 Citations (Scopus)

Abstract

The CUDA model for GPUs presents the programmer with a plethora of different programming options. These includes different memory types, different memory access methods, and different data types. Identifying which options to use and when is a non-trivial exercise. This paper explores the effect of these different options on the performance of a routine that evaluates sparse matrix vector products. A process for analysing performance and selecting the subset of implementations that perform best is proposed. The potential for mapping sparse matrix attributes to optimal CUDA sparse matrix vector product implementation is discussed.

Original language	English
Title of host publication	CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing
Pages	808-813
Number of pages	6
DOIs	https://doi.org/10.1109/CCGRID.2010.81
Publication status	Published - 30 Jul 2010
Externally published	Yes
Event	10th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2010 - Melbourne, VIC, Australia Duration: 17 May 2010 → 20 May 2010

Publication series

Name	CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing

Conference

Conference	10th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2010
Country/Territory	Australia
City	Melbourne, VIC
Period	17/05/10 → 20/05/10

Access to Document

10.1109/CCGRID.2010.81Licence: In Copyright

Cite this

El Zein, A. H., & Rendell, A. P. (2010). From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation. In CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing (pp. 808-813). [5493382] (CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing). https://doi.org/10.1109/CCGRID.2010.81

@inproceedings{b34cf823b9804e7e813c2c922784f18b,

title = "From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation",

abstract = "The CUDA model for GPUs presents the programmer with a plethora of different programming options. These includes different memory types, different memory access methods, and different data types. Identifying which options to use and when is a non-trivial exercise. This paper explores the effect of these different options on the performance of a routine that evaluates sparse matrix vector products. A process for analysing performance and selecting the subset of implementations that perform best is proposed. The potential for mapping sparse matrix attributes to optimal CUDA sparse matrix vector product implementation is discussed.",

author = "{El Zein}, {Ahmed H.} and Rendell, {Alistair P.}",

year = "2010",

month = jul,

day = "30",

doi = "10.1109/CCGRID.2010.81",

language = "English",

isbn = "9781424469871",

series = "CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing",

pages = "808--813",

booktitle = "CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing",

note = "10th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2010 ; Conference date: 17-05-2010 Through 20-05-2010",

}

El Zein, AH & Rendell, AP 2010, From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation. in CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing., 5493382, CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing, pp. 808-813, 10th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2010, Melbourne, VIC, Australia, 17/05/10. https://doi.org/10.1109/CCGRID.2010.81

From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation. / El Zein, Ahmed H.; Rendell, Alistair P.

CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing. 2010. p. 808-813 5493382 (CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing).

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

TY - GEN

T1 - From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation

AU - El Zein, Ahmed H.

AU - Rendell, Alistair P.

PY - 2010/7/30

Y1 - 2010/7/30

N2 - The CUDA model for GPUs presents the programmer with a plethora of different programming options. These includes different memory types, different memory access methods, and different data types. Identifying which options to use and when is a non-trivial exercise. This paper explores the effect of these different options on the performance of a routine that evaluates sparse matrix vector products. A process for analysing performance and selecting the subset of implementations that perform best is proposed. The potential for mapping sparse matrix attributes to optimal CUDA sparse matrix vector product implementation is discussed.

AB - The CUDA model for GPUs presents the programmer with a plethora of different programming options. These includes different memory types, different memory access methods, and different data types. Identifying which options to use and when is a non-trivial exercise. This paper explores the effect of these different options on the performance of a routine that evaluates sparse matrix vector products. A process for analysing performance and selecting the subset of implementations that perform best is proposed. The potential for mapping sparse matrix attributes to optimal CUDA sparse matrix vector product implementation is discussed.

UR - http://www.scopus.com/inward/record.url?scp=77954926909&partnerID=8YFLogxK

UR - http://purl.org/au-research/grants/ARC/DP0987773

U2 - 10.1109/CCGRID.2010.81

DO - 10.1109/CCGRID.2010.81

M3 - Conference contribution

AN - SCOPUS:77954926909

SN - 9781424469871

T3 - CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing

SP - 808

EP - 813

BT - CCGrid 2010 - 10th IEEE/ACM International Conference on Cluster, Cloud, and Grid Computing

T2 - 10th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2010

Y2 - 17 May 2010 through 20 May 2010

ER -

From sparse matrix to optimal GPU CUDA sparse matrix vector product implementation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this