Generation of discrete random variables on vector computers for Monte Carlo simulations

Description

The paper reviews existing methods for generating discrete random variables and their suitability for vector processing. A new method for generating discrete random variables for use in vectorized Monte Carlo simulations is presented. The method uses the concept of importance sampling and generates random variables by employing uniform distribution to speedup the computation. The sampled random variables are subsequently adjusted so that unbiased estimates are obtained. The method preserves both mean and variance of the original distribution. It is demonstrated that the method requires simpler coding and shorter execution time for both scalar and vector processing, when compared with other existing methods. The vectorization speedup of the method is demonstrated on an IBM 3090-180 machine with a vector facility. Keywords: discrete random variables, importance sampling, Monte Carlo simulation, parallel processing, supercomputing, vector processing