Hiroshima University

This paper proposes a type of pseudorandom number generator,Mersenne Twister for Graphic Processor (MTGP), for efficient generation on graphic processessing units (GPUs). MTGP supports large state sizes such as 11213 bits, and uses the high parallelism of GPUs in computing many steps of the recursion in parallel. The second proposal is a parameter-set generator for MTGP, named MTGP Dynamic Creator (MTGPDC). MT-GPDC creates up to 232 distinct parameter sets which generate sequences with high-dimensional uniformity. This facility is suitable for a large grid of GPUs where each GPU requires independent random number streams. MTGP is based on linear recursion over the two-element eld, and has better high dimensional equidistribution than the Mersenne Twister pseudorandom number generator. 1 Random number generation for GPU A Graphic Processing Unit (GPU) is a highly parallel processor designed fo