Parallel stratified and rotating turbulence simulation based on MPIs

Byung Uck Kim, Sung Bong Yang

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

Abstract

We describe a parallel implementation for large-eddy simulation (LES) of the stratified and rotating turbulence based on MPI. The parallelization strategy is specified by eliminating the tridiagonal solver with explicit method and by a domain decomposition for solving the poisson equation. In this simulation we have run on CRAY-T3E under the message passing platform MPI with various domain decompositions. The processing time and speed up with respect to each domain decomposition and the scalability of this parallel code of LES are presented. The results show that we can gain up to 16 times faster speed up on 64 processors with xyz-direction domain decomposition and scalable up to 128x128x128 which processing time is almost similar to that of 40x40x40 on a single processor machine with a sequential code.

Original languageEnglish
Title of host publicationProceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages884-888
Number of pages5
Volume2
ISBN (Electronic)0769505902, 9780769505909
DOIs
Publication statusPublished - 2000 Jan 1
Event4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000 - Beijing, China
Duration: 2000 May 142000 May 17

Other

Other4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000
CountryChina
CityBeijing
Period00/5/1400/5/17

Fingerprint

Turbulence
Decomposition
Large eddy simulation
Poisson equation
Message passing
Processing
Scalability

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Kim, B. U., & Yang, S. B. (2000). Parallel stratified and rotating turbulence simulation based on MPIs. In Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000 (Vol. 2, pp. 884-888). [843566] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HPC.2000.843566
Kim, Byung Uck ; Yang, Sung Bong. / Parallel stratified and rotating turbulence simulation based on MPIs. Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 2000. pp. 884-888
@inproceedings{aa35182c375941eeab4da6c4862e60f0,
title = "Parallel stratified and rotating turbulence simulation based on MPIs",
abstract = "We describe a parallel implementation for large-eddy simulation (LES) of the stratified and rotating turbulence based on MPI. The parallelization strategy is specified by eliminating the tridiagonal solver with explicit method and by a domain decomposition for solving the poisson equation. In this simulation we have run on CRAY-T3E under the message passing platform MPI with various domain decompositions. The processing time and speed up with respect to each domain decomposition and the scalability of this parallel code of LES are presented. The results show that we can gain up to 16 times faster speed up on 64 processors with xyz-direction domain decomposition and scalable up to 128x128x128 which processing time is almost similar to that of 40x40x40 on a single processor machine with a sequential code.",
author = "Kim, {Byung Uck} and Yang, {Sung Bong}",
year = "2000",
month = "1",
day = "1",
doi = "10.1109/HPC.2000.843566",
language = "English",
volume = "2",
pages = "884--888",
booktitle = "Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Kim, BU & Yang, SB 2000, Parallel stratified and rotating turbulence simulation based on MPIs. in Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000. vol. 2, 843566, Institute of Electrical and Electronics Engineers Inc., pp. 884-888, 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000, Beijing, China, 00/5/14. https://doi.org/10.1109/HPC.2000.843566

Parallel stratified and rotating turbulence simulation based on MPIs. / Kim, Byung Uck; Yang, Sung Bong.

Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 2000. p. 884-888 843566.

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

TY - GEN

T1 - Parallel stratified and rotating turbulence simulation based on MPIs

AU - Kim, Byung Uck

AU - Yang, Sung Bong

PY - 2000/1/1

Y1 - 2000/1/1

N2 - We describe a parallel implementation for large-eddy simulation (LES) of the stratified and rotating turbulence based on MPI. The parallelization strategy is specified by eliminating the tridiagonal solver with explicit method and by a domain decomposition for solving the poisson equation. In this simulation we have run on CRAY-T3E under the message passing platform MPI with various domain decompositions. The processing time and speed up with respect to each domain decomposition and the scalability of this parallel code of LES are presented. The results show that we can gain up to 16 times faster speed up on 64 processors with xyz-direction domain decomposition and scalable up to 128x128x128 which processing time is almost similar to that of 40x40x40 on a single processor machine with a sequential code.

AB - We describe a parallel implementation for large-eddy simulation (LES) of the stratified and rotating turbulence based on MPI. The parallelization strategy is specified by eliminating the tridiagonal solver with explicit method and by a domain decomposition for solving the poisson equation. In this simulation we have run on CRAY-T3E under the message passing platform MPI with various domain decompositions. The processing time and speed up with respect to each domain decomposition and the scalability of this parallel code of LES are presented. The results show that we can gain up to 16 times faster speed up on 64 processors with xyz-direction domain decomposition and scalable up to 128x128x128 which processing time is almost similar to that of 40x40x40 on a single processor machine with a sequential code.

UR - http://www.scopus.com/inward/record.url?scp=84960463011&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960463011&partnerID=8YFLogxK

U2 - 10.1109/HPC.2000.843566

DO - 10.1109/HPC.2000.843566

M3 - Conference contribution

VL - 2

SP - 884

EP - 888

BT - Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim BU, Yang SB. Parallel stratified and rotating turbulence simulation based on MPIs. In Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000. Vol. 2. Institute of Electrical and Electronics Engineers Inc. 2000. p. 884-888. 843566 https://doi.org/10.1109/HPC.2000.843566