Vectorization and parallelization of finite strip method for dynamic Mindlin plate problems

Hsin-Chu Chen

Center for Advanced Computer Studies, University of Southwestern Louisiana, Lafayette, LA

Ai-Fang He

Department of Mathematics, Illinois State University, Bloomington, IL


Abstract

The finite strip method is a semi-analytical finite element process which allows for a discrete analysis of certain types of physical problems by discretizing the domain of the problem into finite strips. This method decomposes a single large problem into m smaller independent subproblems when m harmonic functions are employed, thus yielding natural parallelism at a very high level. Once this level of parallelism has been utilized, the medium-grain and/or fine-grain parallelism must then be exploited within the computations involved in each harmonic term when the method is implemented on multiprocessors with vector capability or on multiprocessors with three levels of parallelism. In this paper we address vectorization and parallelization strategies for the dynamic analysis of simply-supported Mindlin plate bending problems and show how to prevent potential conflicts in memory access during the assemblage process. The vector and parallel implementations of this method and the performance results of a test problem under scalar, vector, and vector-concurrent execution modes on the Alliant FX/80 are also presented.