Performance analysis of viscous flow computations on various parallel architectures

D. Drikakis, E. Schreck, F. Durst

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

A study on the performance of parallel viscous flow computations on various parallel architectures is presented. An implicit computational fluid dynamics code was utilized to solve the axisymmetric compressible Navier-Stokes equations, and parallelization of the code was obtained by the grid partitioning technique. Several hardware and software issues, such as, different communication possibilities and their effect on the parallel performance, the numerical and parallel efficiency for single grid and mesh-sequencing solutions, double and single precision calculations, and the effect of the number of processors on the computing time and the parallel performance, were investigated. Calculations for laminar and turbulent benchmark cases were performed on four parallel platforms and the results were compared with corresponding computations done on the Cray Y-MP utilizing only one processor. A theoretical model for the prediction of the parallel efficiency was also derived and it was verified for single grid and mesh-sequencing solutions by comparing the measured efficiencies with those of the predicted ones.
LanguageEnglish
Pages835-841
Number of pages7
JournalJournal of Fluids Engineering
Volume116
Issue number4
DOIs
Publication statusPublished - 1 Dec 1994

Fingerprint

Parallel architectures
Viscous flow
Navier Stokes equations
Computational fluid dynamics
Hardware
Communication

Keywords

  • computational fluid dynamics
  • computational methods
  • CFD
  • computer simulation
  • Navier-Stokes equations
  • parallel processing systems
  • supercomputers
  • Cray Y-MP supercomputer
  • grid partitioning technique
  • viscous flow

Cite this

Drikakis, D. ; Schreck, E. ; Durst, F. / Performance analysis of viscous flow computations on various parallel architectures. In: Journal of Fluids Engineering. 1994 ; Vol. 116, No. 4. pp. 835-841.
@article{aa2e7744711e40b388398621d8a73e9c,
title = "Performance analysis of viscous flow computations on various parallel architectures",
abstract = "A study on the performance of parallel viscous flow computations on various parallel architectures is presented. An implicit computational fluid dynamics code was utilized to solve the axisymmetric compressible Navier-Stokes equations, and parallelization of the code was obtained by the grid partitioning technique. Several hardware and software issues, such as, different communication possibilities and their effect on the parallel performance, the numerical and parallel efficiency for single grid and mesh-sequencing solutions, double and single precision calculations, and the effect of the number of processors on the computing time and the parallel performance, were investigated. Calculations for laminar and turbulent benchmark cases were performed on four parallel platforms and the results were compared with corresponding computations done on the Cray Y-MP utilizing only one processor. A theoretical model for the prediction of the parallel efficiency was also derived and it was verified for single grid and mesh-sequencing solutions by comparing the measured efficiencies with those of the predicted ones.",
keywords = "computational fluid dynamics, computational methods, CFD, computer simulation, Navier-Stokes equations, parallel processing systems, supercomputers, Cray Y-MP supercomputer, grid partitioning technique, viscous flow",
author = "D. Drikakis and E. Schreck and F. Durst",
note = "cited By 8",
year = "1994",
month = "12",
day = "1",
doi = "10.1115/1.2911858",
language = "English",
volume = "116",
pages = "835--841",
journal = "Journal of Fluids Engineering",
issn = "0098-2202",
number = "4",

}

Performance analysis of viscous flow computations on various parallel architectures. / Drikakis, D.; Schreck, E.; Durst, F.

In: Journal of Fluids Engineering, Vol. 116, No. 4, 01.12.1994, p. 835-841.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Performance analysis of viscous flow computations on various parallel architectures

AU - Drikakis, D.

AU - Schreck, E.

AU - Durst, F.

N1 - cited By 8

PY - 1994/12/1

Y1 - 1994/12/1

N2 - A study on the performance of parallel viscous flow computations on various parallel architectures is presented. An implicit computational fluid dynamics code was utilized to solve the axisymmetric compressible Navier-Stokes equations, and parallelization of the code was obtained by the grid partitioning technique. Several hardware and software issues, such as, different communication possibilities and their effect on the parallel performance, the numerical and parallel efficiency for single grid and mesh-sequencing solutions, double and single precision calculations, and the effect of the number of processors on the computing time and the parallel performance, were investigated. Calculations for laminar and turbulent benchmark cases were performed on four parallel platforms and the results were compared with corresponding computations done on the Cray Y-MP utilizing only one processor. A theoretical model for the prediction of the parallel efficiency was also derived and it was verified for single grid and mesh-sequencing solutions by comparing the measured efficiencies with those of the predicted ones.

AB - A study on the performance of parallel viscous flow computations on various parallel architectures is presented. An implicit computational fluid dynamics code was utilized to solve the axisymmetric compressible Navier-Stokes equations, and parallelization of the code was obtained by the grid partitioning technique. Several hardware and software issues, such as, different communication possibilities and their effect on the parallel performance, the numerical and parallel efficiency for single grid and mesh-sequencing solutions, double and single precision calculations, and the effect of the number of processors on the computing time and the parallel performance, were investigated. Calculations for laminar and turbulent benchmark cases were performed on four parallel platforms and the results were compared with corresponding computations done on the Cray Y-MP utilizing only one processor. A theoretical model for the prediction of the parallel efficiency was also derived and it was verified for single grid and mesh-sequencing solutions by comparing the measured efficiencies with those of the predicted ones.

KW - computational fluid dynamics

KW - computational methods

KW - CFD

KW - computer simulation

KW - Navier-Stokes equations

KW - parallel processing systems

KW - supercomputers

KW - Cray Y-MP supercomputer

KW - grid partitioning technique

KW - viscous flow

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-0028130879&partnerID=40&md5=f16ac75bff8ebfdc10481e7163977e16

U2 - 10.1115/1.2911858

DO - 10.1115/1.2911858

M3 - Article

VL - 116

SP - 835

EP - 841

JO - Journal of Fluids Engineering

T2 - Journal of Fluids Engineering

JF - Journal of Fluids Engineering

SN - 0098-2202

IS - 4

ER -