Global and localized parallel preconditioning techniques for large scale solid Earth simulations

Kai Wang; Sangbae Kim; Jun Zhang; Kengo Nakajima; Hiroshi Okuda

doi:10.1109/IPDPS.2003.1213468

Global and localized parallel preconditioning techniques for large scale solid Earth simulations

Kai Wang, Sangbae Kim, Jun Zhang, Kengo Nakajima, Hiroshi Okuda

Computer Science

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

2 Scopus citations

Abstract

We investigate and compare a few parallel preconditioning techniques in the iterative solution of large sparse linear systems arising from solid Earth simulation with and without using contact information in the domain partitioning process. Previous studies are focused on using static or matrix pattern based incomplete LU (ILU) preconditioners in a localized preconditioner implementation. Our current studies are concerned with preconditioner performance for solving two different cases with and without known contact information. For the cases with contact information, we use localized threshold value based incomplete LU (ILUT) preconditioner to improve efficiency. For the cases without contact information, we use a global sparse approximate inverse preconditioner with a static sparsity pattern to achieve robustness. Numerical results from simulating ground motion on a parallel supercomputer are given to compare the effectiveness of these parallel preconditioning techniques.

Original language	English
Title of host publication	Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003
ISBN (Electronic)	0769519261, 9780769519265
DOIs	https://doi.org/10.1109/IPDPS.2003.1213468
State	Published - 2003
Event	International Parallel and Distributed Processing Symposium, IPDPS 2003 - Nice, France Duration: Apr 22 2003 → Apr 26 2003

Publication series

Name	Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003

Conference

Conference	International Parallel and Distributed Processing Symposium, IPDPS 2003
Country/Territory	France
City	Nice
Period	4/22/03 → 4/26/03

Bibliographical note

Publisher Copyright:
© 2003 IEEE.

Funding

This research work was supported in part by the Japanese Research Organization for Information Science and Technology (RIST), in part by the US National Science Foundation under grants CCR-9902022, CCR-9988165, CCR-0092532, and ACI-0202934, in part by the US Department of Energy under grant DE-FG02-02ER45961, and in part by the University of Kentucky Research Committee.

Funders	Funder number
Japanese Research Organization for Information Science and Technology
RIST
US Department of Energy	DE-FG02-02ER45961
US National Science Foundation	CCR-0092532, CCR-9902022, ACI-0202934, CCR-9988165
University of Kentucky Research Committee

Keywords

Fault contact problem
Preconditioning techniques
Solid Earth simulation
Sparse matrices

ASJC Scopus subject areas

Computational Theory and Mathematics
Theoretical Computer Science
Software

Access to Document

10.1109/IPDPS.2003.1213468

Cite this

Wang, K., Kim, S., Zhang, J., Nakajima, K., & Okuda, H. (2003). Global and localized parallel preconditioning techniques for large scale solid Earth simulations. In Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003 Article 1213468 (Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003). https://doi.org/10.1109/IPDPS.2003.1213468

@inproceedings{ee87e4c4dba8400d91d2447def62f130,

title = "Global and localized parallel preconditioning techniques for large scale solid Earth simulations",

abstract = "We investigate and compare a few parallel preconditioning techniques in the iterative solution of large sparse linear systems arising from solid Earth simulation with and without using contact information in the domain partitioning process. Previous studies are focused on using static or matrix pattern based incomplete LU (ILU) preconditioners in a localized preconditioner implementation. Our current studies are concerned with preconditioner performance for solving two different cases with and without known contact information. For the cases with contact information, we use localized threshold value based incomplete LU (ILUT) preconditioner to improve efficiency. For the cases without contact information, we use a global sparse approximate inverse preconditioner with a static sparsity pattern to achieve robustness. Numerical results from simulating ground motion on a parallel supercomputer are given to compare the effectiveness of these parallel preconditioning techniques.",

keywords = "Fault contact problem, Preconditioning techniques, Solid Earth simulation, Sparse matrices",

author = "Kai Wang and Sangbae Kim and Jun Zhang and Kengo Nakajima and Hiroshi Okuda",

note = "Publisher Copyright: {\textcopyright} 2003 IEEE.; International Parallel and Distributed Processing Symposium, IPDPS 2003 ; Conference date: 22-04-2003 Through 26-04-2003",

year = "2003",

doi = "10.1109/IPDPS.2003.1213468",

language = "English",

series = "Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003",

booktitle = "Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003",

}

Wang, K, Kim, S, Zhang, J, Nakajima, K & Okuda, H 2003, Global and localized parallel preconditioning techniques for large scale solid Earth simulations. in Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003., 1213468, Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003, International Parallel and Distributed Processing Symposium, IPDPS 2003, Nice, France, 4/22/03. https://doi.org/10.1109/IPDPS.2003.1213468

Global and localized parallel preconditioning techniques for large scale solid Earth simulations. / Wang, Kai; Kim, Sangbae; Zhang, Jun et al.
Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003. 2003. 1213468 (Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003).

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

TY - GEN

T1 - Global and localized parallel preconditioning techniques for large scale solid Earth simulations

AU - Wang, Kai

AU - Kim, Sangbae

AU - Zhang, Jun

AU - Nakajima, Kengo

AU - Okuda, Hiroshi

PY - 2003

Y1 - 2003

N2 - We investigate and compare a few parallel preconditioning techniques in the iterative solution of large sparse linear systems arising from solid Earth simulation with and without using contact information in the domain partitioning process. Previous studies are focused on using static or matrix pattern based incomplete LU (ILU) preconditioners in a localized preconditioner implementation. Our current studies are concerned with preconditioner performance for solving two different cases with and without known contact information. For the cases with contact information, we use localized threshold value based incomplete LU (ILUT) preconditioner to improve efficiency. For the cases without contact information, we use a global sparse approximate inverse preconditioner with a static sparsity pattern to achieve robustness. Numerical results from simulating ground motion on a parallel supercomputer are given to compare the effectiveness of these parallel preconditioning techniques.

AB - We investigate and compare a few parallel preconditioning techniques in the iterative solution of large sparse linear systems arising from solid Earth simulation with and without using contact information in the domain partitioning process. Previous studies are focused on using static or matrix pattern based incomplete LU (ILU) preconditioners in a localized preconditioner implementation. Our current studies are concerned with preconditioner performance for solving two different cases with and without known contact information. For the cases with contact information, we use localized threshold value based incomplete LU (ILUT) preconditioner to improve efficiency. For the cases without contact information, we use a global sparse approximate inverse preconditioner with a static sparsity pattern to achieve robustness. Numerical results from simulating ground motion on a parallel supercomputer are given to compare the effectiveness of these parallel preconditioning techniques.

KW - Fault contact problem

KW - Preconditioning techniques

KW - Solid Earth simulation

KW - Sparse matrices

UR - http://www.scopus.com/inward/record.url?scp=84947233784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947233784&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2003.1213468

DO - 10.1109/IPDPS.2003.1213468

M3 - Conference contribution

AN - SCOPUS:84947233784

T3 - Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003

BT - Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003

T2 - International Parallel and Distributed Processing Symposium, IPDPS 2003

Y2 - 22 April 2003 through 26 April 2003

ER -

Global and localized parallel preconditioning techniques for large scale solid Earth simulations

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this