DSMC of the inner atmosphere of a comet on shared memory multiprocessors

Abstract

The high-performance algorithm of two-level parallelization for direct simulation Monte Carlo of unsteady flows has been described. The algorithm of parallel statistically independent runs is used on the first level of parallelization. The data parallelization corresponds to the second one. The problem of simulation of the inner atmosphere of a comet was used to study the speedup of the algorithm. It has been shown that speedup and efficiency of the algorithm get higher as the problem becomes more complex.