Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis

Garng Morton Huang, W. Ongsakul

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

5 Citations (Scopus)

Abstract

In our earlier papers, the parallelization and implementations of Gauss-Seidel (G-S) algorithms for power flow analysis have been investigated on a Sequent Balance shared memory (SM) machine. In this paper, we generalize the idea to more general computer architectures and demonstrate how to effectively increase the speedup upper bounds of G-S algorithms by properly managing the bottlenecks on both Sequent Balance SM and nCUBE2 distributed memory (DM) machines. We propose a new synchronization scheme which can reduce the synchronization overhead on the Sequent Balance Machine.

Original languageEnglish
Title of host publication1993 IEEE Power Industry Computer Applications Conference
PublisherPubl by IEEE
Pages75-81
Number of pages7
ISBN (Print)078031302X
Publication statusPublished - 1 Jan 1993
Externally publishedYes
Event1993 IEEE Power Industry Computer Applications Conference - Scottsdale, AZ, USA
Duration: 4 May 19937 May 1993

Other

Other1993 IEEE Power Industry Computer Applications Conference
CityScottsdale, AZ, USA
Period4/5/937/5/93

Fingerprint

Data storage equipment
Synchronization
Computer architecture

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Huang, G. M., & Ongsakul, W. (1993). Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis. In 1993 IEEE Power Industry Computer Applications Conference (pp. 75-81). Publ by IEEE.

Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis. / Huang, Garng Morton; Ongsakul, W.

1993 IEEE Power Industry Computer Applications Conference. Publ by IEEE, 1993. p. 75-81.

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

Huang, GM & Ongsakul, W 1993, Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis. in 1993 IEEE Power Industry Computer Applications Conference. Publ by IEEE, pp. 75-81, 1993 IEEE Power Industry Computer Applications Conference, Scottsdale, AZ, USA, 4/5/93.
Huang GM, Ongsakul W. Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis. In 1993 IEEE Power Industry Computer Applications Conference. Publ by IEEE. 1993. p. 75-81
Huang, Garng Morton ; Ongsakul, W. / Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis. 1993 IEEE Power Industry Computer Applications Conference. Publ by IEEE, 1993. pp. 75-81
@inproceedings{91f6fe12a3824745a89a4edf8e7a5aa9,
title = "Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis",
abstract = "In our earlier papers, the parallelization and implementations of Gauss-Seidel (G-S) algorithms for power flow analysis have been investigated on a Sequent Balance shared memory (SM) machine. In this paper, we generalize the idea to more general computer architectures and demonstrate how to effectively increase the speedup upper bounds of G-S algorithms by properly managing the bottlenecks on both Sequent Balance SM and nCUBE2 distributed memory (DM) machines. We propose a new synchronization scheme which can reduce the synchronization overhead on the Sequent Balance Machine.",
author = "Huang, {Garng Morton} and W. Ongsakul",
year = "1993",
month = "1",
day = "1",
language = "English",
isbn = "078031302X",
pages = "75--81",
booktitle = "1993 IEEE Power Industry Computer Applications Conference",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Managing the bottlenecks in parallel Gauss-Seidel type algorithms for power flow analysis

AU - Huang, Garng Morton

AU - Ongsakul, W.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - In our earlier papers, the parallelization and implementations of Gauss-Seidel (G-S) algorithms for power flow analysis have been investigated on a Sequent Balance shared memory (SM) machine. In this paper, we generalize the idea to more general computer architectures and demonstrate how to effectively increase the speedup upper bounds of G-S algorithms by properly managing the bottlenecks on both Sequent Balance SM and nCUBE2 distributed memory (DM) machines. We propose a new synchronization scheme which can reduce the synchronization overhead on the Sequent Balance Machine.

AB - In our earlier papers, the parallelization and implementations of Gauss-Seidel (G-S) algorithms for power flow analysis have been investigated on a Sequent Balance shared memory (SM) machine. In this paper, we generalize the idea to more general computer architectures and demonstrate how to effectively increase the speedup upper bounds of G-S algorithms by properly managing the bottlenecks on both Sequent Balance SM and nCUBE2 distributed memory (DM) machines. We propose a new synchronization scheme which can reduce the synchronization overhead on the Sequent Balance Machine.

UR - http://www.scopus.com/inward/record.url?scp=0027187292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027187292&partnerID=8YFLogxK

M3 - Conference contribution

SN - 078031302X

SP - 75

EP - 81

BT - 1993 IEEE Power Industry Computer Applications Conference

PB - Publ by IEEE

ER -