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

Producción científica: Conference contribution › revisión exhaustiva

2 Citas (Scopus)

Resumen

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.

Idioma original	English
Título de la publicación alojada	Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003
ISBN (versión digital)	0769519261, 9780769519265
DOI	https://doi.org/10.1109/IPDPS.2003.1213468
Estado	Published - 2003
Evento	International Parallel and Distributed Processing Symposium, IPDPS 2003 - Nice, France Duración: abr 22 2003 → abr 26 2003

Serie de la publicación

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

Conference

Conference	International Parallel and Distributed Processing Symposium, IPDPS 2003
País/Territorio	France
Ciudad	Nice
Período	4/22/03 → 4/26/03

Nota bibliográfica

Publisher Copyright:
© 2003 IEEE.

Financiación

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.

Financiadores	Número del financiador
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

ASJC Scopus subject areas

Computational Theory and Mathematics
Theoretical Computer Science
Software

Acceder al documento

10.1109/IPDPS.2003.1213468

Otros archivos y enlaces

Citar esto

Wang, K., Kim, S., Zhang, J., Nakajima, K., & Okuda, H. (2003). Global and localized parallel preconditioning techniques for large scale solid Earth simulations. En Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2003 Artículo 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. En 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).

Producción científica: Conference contribution › revisión exhaustiva

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 - https://www.scopus.com/pages/publications/84947233784

UR - https://www.scopus.com/pages/publications/84947233784#tab=citedBy

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

Resumen

Serie de la publicación

Conference

Nota bibliográfica

Financiación

ASJC Scopus subject areas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto