Random number generation and simulation on vector and parallel computers

Abstract

Pseudo-random numbers are often required for simulations performed on parallel computers. The requirements for parallel random number generators are more stringent than those for sequential random number generators. As well as passing the usual sequential tests on each processor, a parallel random number generator must give different, independent sequences on each processor. We consider the requirements for a good parallel random number generator, and discuss generators for the uniform and normal distributions. We also describe a new class of generators for the normal distribution (based on a proposal by Wallace). These generators can give very fast vector or parallel implementations. Implementations of uniform and normal generators on vector and vector/parallel computers are discussed.