Cost-effective parallel preconditioner for network-based computing

Hyoung Joong Kim; Hyung Soo Kim; Kyung Choi; Hyang Beom Lee; Hyun Kyo Jung; Song Yop Hahn

doi:10.1109/20.582626

Cost-effective parallel preconditioner for network-based computing

Hyoung Joong Kim, Hyung Soo Kim, Kyung Choi, Hyang Beom Lee, Hyun Kyo Jung, Song Yop Hahn

School of Cybersecurity

Research output: Contribution to journal › Article › peer-review

Abstract

A linear solver, the QMR, for a very large linear system is implemented for network-based computing. Network-based computing with cluster of workstations or inexpensive personal computers recently has become an important and very successful technique. Network-based computing enables fast computation and resolves shortage of storage with inexpensive computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and sufficient storage to challenge large-scale problems. Assume that the total storage available in computers is just sufficient for solving the problem. This is often the case in real-world applications since the linear system is too large. Thus, any preconditioner which requires more storage than that available is excluded. Classical Jacobi, Gauss-Seidel, and SOR and its variant, SSOR, is considered. Performance of preconditioners is analyzed.

Original language	English
Pages (from-to)	1800-1803
Number of pages	4
Journal	IEEE Transactions on Magnetics
Volume	33
Issue number	2 PART 2
DOIs	https://doi.org/10.1109/20.582626
Publication status	Published - 1997

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/20.582626

Cite this

@article{29e5c754009e4e7e841261e2d7f6e015,

title = "Cost-effective parallel preconditioner for network-based computing",

abstract = "A linear solver, the QMR, for a very large linear system is implemented for network-based computing. Network-based computing with cluster of workstations or inexpensive personal computers recently has become an important and very successful technique. Network-based computing enables fast computation and resolves shortage of storage with inexpensive computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and sufficient storage to challenge large-scale problems. Assume that the total storage available in computers is just sufficient for solving the problem. This is often the case in real-world applications since the linear system is too large. Thus, any preconditioner which requires more storage than that available is excluded. Classical Jacobi, Gauss-Seidel, and SOR and its variant, SSOR, is considered. Performance of preconditioners is analyzed.",

author = "Kim, {Hyoung Joong} and Kim, {Hyung Soo} and Kyung Choi and Lee, {Hyang Beom} and Jung, {Hyun Kyo} and Hahn, {Song Yop}",

year = "1997",

doi = "10.1109/20.582626",

language = "English",

volume = "33",

pages = "1800--1803",

journal = "IEEE Transactions on Magnetics",

issn = "0018-9464",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2 PART 2",

}

TY - JOUR

T1 - Cost-effective parallel preconditioner for network-based computing

AU - Kim, Hyoung Joong

AU - Kim, Hyung Soo

AU - Choi, Kyung

AU - Lee, Hyang Beom

AU - Jung, Hyun Kyo

AU - Hahn, Song Yop

PY - 1997

Y1 - 1997

N2 - A linear solver, the QMR, for a very large linear system is implemented for network-based computing. Network-based computing with cluster of workstations or inexpensive personal computers recently has become an important and very successful technique. Network-based computing enables fast computation and resolves shortage of storage with inexpensive computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and sufficient storage to challenge large-scale problems. Assume that the total storage available in computers is just sufficient for solving the problem. This is often the case in real-world applications since the linear system is too large. Thus, any preconditioner which requires more storage than that available is excluded. Classical Jacobi, Gauss-Seidel, and SOR and its variant, SSOR, is considered. Performance of preconditioners is analyzed.

AB - A linear solver, the QMR, for a very large linear system is implemented for network-based computing. Network-based computing with cluster of workstations or inexpensive personal computers recently has become an important and very successful technique. Network-based computing enables fast computation and resolves shortage of storage with inexpensive computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and sufficient storage to challenge large-scale problems. Assume that the total storage available in computers is just sufficient for solving the problem. This is often the case in real-world applications since the linear system is too large. Thus, any preconditioner which requires more storage than that available is excluded. Classical Jacobi, Gauss-Seidel, and SOR and its variant, SSOR, is considered. Performance of preconditioners is analyzed.

UR - http://www.scopus.com/inward/record.url?scp=0031098904&partnerID=8YFLogxK

U2 - 10.1109/20.582626

DO - 10.1109/20.582626

M3 - Article

AN - SCOPUS:0031098904

SN - 0018-9464

VL - 33

SP - 1800

EP - 1803

JO - IEEE Transactions on Magnetics

JF - IEEE Transactions on Magnetics

IS - 2 PART 2

ER -

Cost-effective parallel preconditioner for network-based computing

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this