Parallel overlapping-mesh algorithm

J. Rokicki, J. Zółtak, D. Drikakis, J. Majewski

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

Abstract

The paper presents parallelization of an overlapping mesh technique and its implementation in the case of inviscid compressible flows around complex geometries. The present overlapping grid technique is based on the solution of the the equations on each grid separately, with boundary conditions adjusted iteratively through a blended-function-based procedure. The load-balancing and parallel performance issues are investigated for several grid systems. A simple model has also been developed for describing the parallel efficiency of the simulations and it is shown that the model results agree well with the parallel performance experiments.
LanguageEnglish
Title of host publicationSixth International Conference on Applications of High-Performance Computers in Engineering
EditorsM. Ingber, H. Power, C. A. Brebbia
Pages335-344
Number of pages10
Volume6
Publication statusPublished - 26 Jan 2000

Publication series

NameAdvances in High Performance Computing
PublisherWIT Press
Volume6
ISSN (Print)1368-7638

Fingerprint

Compressible flow
Resource allocation
Boundary conditions
Geometry
Experiments

Keywords

  • overlapping mesh techniques
  • grid systems
  • parallel performance

Cite this

Rokicki, J., Zółtak, J., Drikakis, D., & Majewski, J. (2000). Parallel overlapping-mesh algorithm. In M. Ingber, H. Power, & C. A. Brebbia (Eds.), Sixth International Conference on Applications of High-Performance Computers in Engineering (Vol. 6, pp. 335-344). (Advances in High Performance Computing; Vol. 6).
Rokicki, J. ; Zółtak, J. ; Drikakis, D. ; Majewski, J. / Parallel overlapping-mesh algorithm. Sixth International Conference on Applications of High-Performance Computers in Engineering. editor / M. Ingber ; H. Power ; C. A. Brebbia. Vol. 6 2000. pp. 335-344 (Advances in High Performance Computing).
@inproceedings{c27f4fd50e0942e39ed7c7bdc69ac5a9,
title = "Parallel overlapping-mesh algorithm",
abstract = "The paper presents parallelization of an overlapping mesh technique and its implementation in the case of inviscid compressible flows around complex geometries. The present overlapping grid technique is based on the solution of the the equations on each grid separately, with boundary conditions adjusted iteratively through a blended-function-based procedure. The load-balancing and parallel performance issues are investigated for several grid systems. A simple model has also been developed for describing the parallel efficiency of the simulations and it is shown that the model results agree well with the parallel performance experiments.",
keywords = "overlapping mesh techniques, grid systems, parallel performance",
author = "J. Rokicki and J. Z{\'o}łtak and D. Drikakis and J. Majewski",
year = "2000",
month = "1",
day = "26",
language = "English",
volume = "6",
series = "Advances in High Performance Computing",
publisher = "WIT Press",
pages = "335--344",
editor = "M. Ingber and H. Power and Brebbia, {C. A.}",
booktitle = "Sixth International Conference on Applications of High-Performance Computers in Engineering",

}

Rokicki, J, Zółtak, J, Drikakis, D & Majewski, J 2000, Parallel overlapping-mesh algorithm. in M Ingber, H Power & CA Brebbia (eds), Sixth International Conference on Applications of High-Performance Computers in Engineering. vol. 6, Advances in High Performance Computing, vol. 6, pp. 335-344.

Parallel overlapping-mesh algorithm. / Rokicki, J.; Zółtak, J.; Drikakis, D.; Majewski, J.

Sixth International Conference on Applications of High-Performance Computers in Engineering. ed. / M. Ingber; H. Power; C. A. Brebbia. Vol. 6 2000. p. 335-344 (Advances in High Performance Computing; Vol. 6).

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

TY - GEN

T1 - Parallel overlapping-mesh algorithm

AU - Rokicki, J.

AU - Zółtak, J.

AU - Drikakis, D.

AU - Majewski, J.

PY - 2000/1/26

Y1 - 2000/1/26

N2 - The paper presents parallelization of an overlapping mesh technique and its implementation in the case of inviscid compressible flows around complex geometries. The present overlapping grid technique is based on the solution of the the equations on each grid separately, with boundary conditions adjusted iteratively through a blended-function-based procedure. The load-balancing and parallel performance issues are investigated for several grid systems. A simple model has also been developed for describing the parallel efficiency of the simulations and it is shown that the model results agree well with the parallel performance experiments.

AB - The paper presents parallelization of an overlapping mesh technique and its implementation in the case of inviscid compressible flows around complex geometries. The present overlapping grid technique is based on the solution of the the equations on each grid separately, with boundary conditions adjusted iteratively through a blended-function-based procedure. The load-balancing and parallel performance issues are investigated for several grid systems. A simple model has also been developed for describing the parallel efficiency of the simulations and it is shown that the model results agree well with the parallel performance experiments.

KW - overlapping mesh techniques

KW - grid systems

KW - parallel performance

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-2942625558&partnerID=40&md5=2fda1b72b37e0324b4a1294db1d87db2

M3 - Conference contribution book

VL - 6

T3 - Advances in High Performance Computing

SP - 335

EP - 344

BT - Sixth International Conference on Applications of High-Performance Computers in Engineering

A2 - Ingber, M.

A2 - Power, H.

A2 - Brebbia, C. A.

ER -

Rokicki J, Zółtak J, Drikakis D, Majewski J. Parallel overlapping-mesh algorithm. In Ingber M, Power H, Brebbia CA, editors, Sixth International Conference on Applications of High-Performance Computers in Engineering. Vol. 6. 2000. p. 335-344. (Advances in High Performance Computing).