Vectorization and Parallelization of Finite Strip Method for Dynamic Mindlin Plate Problems

SUMMARY The nite strip method is a semi-analytical nite element process which allows for a discrete analysis of certain types of physical problems by discretizing the domain of the problem into nite 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. 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 connicts 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.