摘要

In this paper, we have researched and developed optimization solutions for implementing the Sobol random number generator in the Compute Unified Device Architecture. We have conducted a thorough analysis, using a series of experimental tests, for studying the solutions' influence on the execution time, on the number of generated samples per second and on the energy consumption. Lately, in the literature, there has been a lot of interest for developing random number generators, but none of the works so far (to our best knowledge) has developed optimization solutions targeted towards the Kepler GK104 architecture, harnessing its novel technical features.

  • 出版日期2015