Title :
Automatic load balancing in parallel direct simulation methods
Author :
Cremonesi, Paolo
Author_Institution :
Dipartimento di Elettronica e Inf., Politecnico di Milano, Italy
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;
Conference_Titel :
Massively Parallel Computing Systems, 1994., Proceedings of the First International Conference on
Conference_Location :
Ischia
Print_ISBN :
0-8186-6322-7
DOI :
10.1109/MPCS.1994.367063