PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS.

Marsha Berger, Shahid H. Bokhari

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

Abstract

The authors consider the partitioning of a problem on a domain with unequal work estimates in different subdomains in a way that balances the work load across multiple processors. Such a problem arises, for example, in solving partial differential equations using an adaptive method that places extra grid points in certain subregions of the domain. A binary decomposition of the domain to partition it into rectangles requiring equal computational effort is used. The communication costs of mapping this partitioning onto a tree machine and a mesh-connected array are analyzed. The communication cost can be used to determine the optimal depth of this partitioning.

Original languageEnglish (US)
Title of host publicationProceedings of the International Conference on Parallel Processing
EditorsDouglas DeGroot
PublisherIEEE
Pages166-170
Number of pages5
ISBN (Print)0818606371
StatePublished - 1985

Fingerprint

Communication
Partial differential equations
Costs
Decomposition

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Berger, M., & Bokhari, S. H. (1985). PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS. In D. DeGroot (Ed.), Proceedings of the International Conference on Parallel Processing (pp. 166-170). IEEE.

PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS. / Berger, Marsha; Bokhari, Shahid H.

Proceedings of the International Conference on Parallel Processing. ed. / Douglas DeGroot. IEEE, 1985. p. 166-170.

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

Berger, M & Bokhari, SH 1985, PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS. in D DeGroot (ed.), Proceedings of the International Conference on Parallel Processing. IEEE, pp. 166-170.
Berger M, Bokhari SH. PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS. In DeGroot D, editor, Proceedings of the International Conference on Parallel Processing. IEEE. 1985. p. 166-170
Berger, Marsha ; Bokhari, Shahid H. / PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS. Proceedings of the International Conference on Parallel Processing. editor / Douglas DeGroot. IEEE, 1985. pp. 166-170
@inproceedings{ea74d01ba7274dc6a0703e7fb22cbffe,
title = "PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS.",
abstract = "The authors consider the partitioning of a problem on a domain with unequal work estimates in different subdomains in a way that balances the work load across multiple processors. Such a problem arises, for example, in solving partial differential equations using an adaptive method that places extra grid points in certain subregions of the domain. A binary decomposition of the domain to partition it into rectangles requiring equal computational effort is used. The communication costs of mapping this partitioning onto a tree machine and a mesh-connected array are analyzed. The communication cost can be used to determine the optimal depth of this partitioning.",
author = "Marsha Berger and Bokhari, {Shahid H.}",
year = "1985",
language = "English (US)",
isbn = "0818606371",
pages = "166--170",
editor = "Douglas DeGroot",
booktitle = "Proceedings of the International Conference on Parallel Processing",
publisher = "IEEE",

}

TY - GEN

T1 - PARTITIONING STRATEGY FOR PDES ACROSS MULTIPROCESSORS.

AU - Berger, Marsha

AU - Bokhari, Shahid H.

PY - 1985

Y1 - 1985

N2 - The authors consider the partitioning of a problem on a domain with unequal work estimates in different subdomains in a way that balances the work load across multiple processors. Such a problem arises, for example, in solving partial differential equations using an adaptive method that places extra grid points in certain subregions of the domain. A binary decomposition of the domain to partition it into rectangles requiring equal computational effort is used. The communication costs of mapping this partitioning onto a tree machine and a mesh-connected array are analyzed. The communication cost can be used to determine the optimal depth of this partitioning.

AB - The authors consider the partitioning of a problem on a domain with unequal work estimates in different subdomains in a way that balances the work load across multiple processors. Such a problem arises, for example, in solving partial differential equations using an adaptive method that places extra grid points in certain subregions of the domain. A binary decomposition of the domain to partition it into rectangles requiring equal computational effort is used. The communication costs of mapping this partitioning onto a tree machine and a mesh-connected array are analyzed. The communication cost can be used to determine the optimal depth of this partitioning.

UR - http://www.scopus.com/inward/record.url?scp=0022185145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022185145&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0022185145

SN - 0818606371

SP - 166

EP - 170

BT - Proceedings of the International Conference on Parallel Processing

A2 - DeGroot, Douglas

PB - IEEE

ER -