Parallelization of the moving particle pressure mesh (MPPM) fluid flow solver by using OpenMP

Abdalla M.E. Ibrahim, Khai Ching Ng, Mohd Zamri Yusoff

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The MPPM numerical method parallelization by utilizing the OpenMP environment is reported in this paper. The objective of this work is to reduce the MPPM method computation time by exploiting the otherwise idle processors and overall improve the efficiency of the method. The code solving the Rayleigh-Taylor instability model was originally written using Fortran77 and is considerably slow and was rewritten in C language then parallelized using OpenMP directives. The highest obtained speedup value resulting from OpenMP parallelization is found to be 2.3 which is achieved through utilizing 6 threads out of the available 12 threads. The work presents the possible performance improvement and the importance of addressing the sequential nature of the code in order to further enhance its efficiency.

Original languageEnglish
Pages (from-to)2515-2519
Number of pages5
JournalARPN Journal of Engineering and Applied Sciences
Volume12
Issue number8
Publication statusPublished - 01 Apr 2017

Fingerprint

Flow of fluids
Numerical methods

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

@article{5b7bf5d3d87f41af8247cad2b62b9ca0,
title = "Parallelization of the moving particle pressure mesh (MPPM) fluid flow solver by using OpenMP",
abstract = "The MPPM numerical method parallelization by utilizing the OpenMP environment is reported in this paper. The objective of this work is to reduce the MPPM method computation time by exploiting the otherwise idle processors and overall improve the efficiency of the method. The code solving the Rayleigh-Taylor instability model was originally written using Fortran77 and is considerably slow and was rewritten in C language then parallelized using OpenMP directives. The highest obtained speedup value resulting from OpenMP parallelization is found to be 2.3 which is achieved through utilizing 6 threads out of the available 12 threads. The work presents the possible performance improvement and the importance of addressing the sequential nature of the code in order to further enhance its efficiency.",
author = "Ibrahim, {Abdalla M.E.} and Ng, {Khai Ching} and Yusoff, {Mohd Zamri}",
year = "2017",
month = "4",
day = "1",
language = "English",
volume = "12",
pages = "2515--2519",
journal = "ARPN Journal of Engineering and Applied Sciences",
issn = "1819-6608",
publisher = "Asian Research Publishing Network (ARPN)",
number = "8",

}

Parallelization of the moving particle pressure mesh (MPPM) fluid flow solver by using OpenMP. / Ibrahim, Abdalla M.E.; Ng, Khai Ching; Yusoff, Mohd Zamri.

In: ARPN Journal of Engineering and Applied Sciences, Vol. 12, No. 8, 01.04.2017, p. 2515-2519.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Parallelization of the moving particle pressure mesh (MPPM) fluid flow solver by using OpenMP

AU - Ibrahim, Abdalla M.E.

AU - Ng, Khai Ching

AU - Yusoff, Mohd Zamri

PY - 2017/4/1

Y1 - 2017/4/1

N2 - The MPPM numerical method parallelization by utilizing the OpenMP environment is reported in this paper. The objective of this work is to reduce the MPPM method computation time by exploiting the otherwise idle processors and overall improve the efficiency of the method. The code solving the Rayleigh-Taylor instability model was originally written using Fortran77 and is considerably slow and was rewritten in C language then parallelized using OpenMP directives. The highest obtained speedup value resulting from OpenMP parallelization is found to be 2.3 which is achieved through utilizing 6 threads out of the available 12 threads. The work presents the possible performance improvement and the importance of addressing the sequential nature of the code in order to further enhance its efficiency.

AB - The MPPM numerical method parallelization by utilizing the OpenMP environment is reported in this paper. The objective of this work is to reduce the MPPM method computation time by exploiting the otherwise idle processors and overall improve the efficiency of the method. The code solving the Rayleigh-Taylor instability model was originally written using Fortran77 and is considerably slow and was rewritten in C language then parallelized using OpenMP directives. The highest obtained speedup value resulting from OpenMP parallelization is found to be 2.3 which is achieved through utilizing 6 threads out of the available 12 threads. The work presents the possible performance improvement and the importance of addressing the sequential nature of the code in order to further enhance its efficiency.

UR - http://www.scopus.com/inward/record.url?scp=85018861183&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018861183&partnerID=8YFLogxK

M3 - Article

VL - 12

SP - 2515

EP - 2519

JO - ARPN Journal of Engineering and Applied Sciences

JF - ARPN Journal of Engineering and Applied Sciences

SN - 1819-6608

IS - 8

ER -