Automatic load balancing in parallel direct simulation methods

Author

Cremonesi, Paolo

Author_Institution

Dipartimento di Elettronica e Inf., Politecnico di Milano, Italy

fYear

1994

fDate

2-6 May 1994

Firstpage

323

Lastpage

327

Abstract

Performing Direct Simulation Monte Carlo (DSMC) calculations on parallel processors may result in a strongly unbalanced distribution of work. This situation affects the performances leading to very low speedups. A method that makes use of adaptive domain decomposition to dynamically distribute the computational work load is presented. The method had been implemented on a Transputer System with up to 8 processors (20 MHz Inmos T800), using the FORTRAN version of Parasoft Express Library for parallel computers. The problems studied were hypersonic flows of a chemically reacting gas in a two-dimensional domain. The adaptive decomposition method worked well in uniformly distributing the computational work over an arbitrary number of processors and reduced the average execution time by over 45% in certain cases

Keywords

Monte Carlo methods; digital simulation; parallel algorithms; resource allocation; Direct Simulation Monte Carlo; chemically reacting gas; hypersonic flows; load balancing; parallel direct simulation methods; parallel processors; Chemicals; Computational modeling; Computer simulation; Concurrent computing; Distributed computing; Libraries; Load management; Message passing; Monte Carlo methods; Scattering;

fLanguage

English

Publisher

ieee

Conference_Titel

Massively Parallel Computing Systems, 1994., Proceedings of the First International Conference on

Conference_Location

Ischia

Print_ISBN

0-8186-6322-7

Type

conf

DOI

10.1109/MPCS.1994.367063

Filename

367063