Cost-effective parallel processing for remote sensing applications

Hyong Joong Kim, Hyung Soo Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Network-based computing with cluster of personal computers or workstations recently has become an important and successful technique. Network-based computing enables fast computation and resolves short of storage with computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and storage to challenge very large-scale problems. Iterative solvers are used for the large sparse linear systems. Preconditioners accelerate the rate of convergence of the iterative solvers. However, parallelization of preconditioners is far from satisfaction so far. Thus, the simplest diagonal scaling is a good alternative for improved convergence and easy parallelization. In order to reduce communication overhead, a data compression technique is considered. Data communication time can be reduced at the cost of convergence rate. MATLAB simulation result is given in this paper. This method is effective to cluster of computers connected through slow networks.

Original languageEnglish
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
PublisherIEEE
Pages405-407
Number of pages3
Volume1
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 International Geoscience and Remote Sensing Symposium, IGARSS'96. Part 1 (of 4) - Lincoln, NE, USA
Duration: 1996 May 281996 May 31

Other

OtherProceedings of the 1996 International Geoscience and Remote Sensing Symposium, IGARSS'96. Part 1 (of 4)
CityLincoln, NE, USA
Period96/5/2896/5/31

Fingerprint

Remote sensing
remote sensing
Processing
cost
Costs
Computer workstations
Communication
Data compression
communication
Personal computers
MATLAB
Linear systems
compression
simulation
rate

ASJC Scopus subject areas

  • Software
  • Geology

Cite this

Kim, H. J., & Kim, H. S. (1996). Cost-effective parallel processing for remote sensing applications. In International Geoscience and Remote Sensing Symposium (IGARSS) (Vol. 1, pp. 405-407). IEEE.

Cost-effective parallel processing for remote sensing applications. / Kim, Hyong Joong; Kim, Hyung Soo.

International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 1 IEEE, 1996. p. 405-407.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, HJ & Kim, HS 1996, Cost-effective parallel processing for remote sensing applications. in International Geoscience and Remote Sensing Symposium (IGARSS). vol. 1, IEEE, pp. 405-407, Proceedings of the 1996 International Geoscience and Remote Sensing Symposium, IGARSS'96. Part 1 (of 4), Lincoln, NE, USA, 96/5/28.
Kim HJ, Kim HS. Cost-effective parallel processing for remote sensing applications. In International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 1. IEEE. 1996. p. 405-407
Kim, Hyong Joong ; Kim, Hyung Soo. / Cost-effective parallel processing for remote sensing applications. International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 1 IEEE, 1996. pp. 405-407
@inproceedings{a1dfe1c489f84f97bb0b68737212450e,
title = "Cost-effective parallel processing for remote sensing applications",
abstract = "Network-based computing with cluster of personal computers or workstations recently has become an important and successful technique. Network-based computing enables fast computation and resolves short of storage with computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and storage to challenge very large-scale problems. Iterative solvers are used for the large sparse linear systems. Preconditioners accelerate the rate of convergence of the iterative solvers. However, parallelization of preconditioners is far from satisfaction so far. Thus, the simplest diagonal scaling is a good alternative for improved convergence and easy parallelization. In order to reduce communication overhead, a data compression technique is considered. Data communication time can be reduced at the cost of convergence rate. MATLAB simulation result is given in this paper. This method is effective to cluster of computers connected through slow networks.",
author = "Kim, {Hyong Joong} and Kim, {Hyung Soo}",
year = "1996",
language = "English",
volume = "1",
pages = "405--407",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "IEEE",

}

TY - GEN

T1 - Cost-effective parallel processing for remote sensing applications

AU - Kim, Hyong Joong

AU - Kim, Hyung Soo

PY - 1996

Y1 - 1996

N2 - Network-based computing with cluster of personal computers or workstations recently has become an important and successful technique. Network-based computing enables fast computation and resolves short of storage with computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and storage to challenge very large-scale problems. Iterative solvers are used for the large sparse linear systems. Preconditioners accelerate the rate of convergence of the iterative solvers. However, parallelization of preconditioners is far from satisfaction so far. Thus, the simplest diagonal scaling is a good alternative for improved convergence and easy parallelization. In order to reduce communication overhead, a data compression technique is considered. Data communication time can be reduced at the cost of convergence rate. MATLAB simulation result is given in this paper. This method is effective to cluster of computers connected through slow networks.

AB - Network-based computing with cluster of personal computers or workstations recently has become an important and successful technique. Network-based computing enables fast computation and resolves short of storage with computers on the desks. Cluster of inexpensive computers offers them aggregated computing power and storage to challenge very large-scale problems. Iterative solvers are used for the large sparse linear systems. Preconditioners accelerate the rate of convergence of the iterative solvers. However, parallelization of preconditioners is far from satisfaction so far. Thus, the simplest diagonal scaling is a good alternative for improved convergence and easy parallelization. In order to reduce communication overhead, a data compression technique is considered. Data communication time can be reduced at the cost of convergence rate. MATLAB simulation result is given in this paper. This method is effective to cluster of computers connected through slow networks.

UR - http://www.scopus.com/inward/record.url?scp=0029699510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029699510&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029699510

VL - 1

SP - 405

EP - 407

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

PB - IEEE

ER -