Parallelization of test for assessing pseudorandom number generators using CUDA technology

Abstract

In general, the tests for assessing the quality of the pseudorandom number generators (PRNG) are very time consuming. The paper is devoted to the problem of PRNGs assessment tests acceleration. Our approach based on the using resources of graphics cards and technology nVIDIA CUDA. This paper gives examples of parallelization of several tests from A Statistical Test Suite for Random and Pseudorandom Number Generators for cryptographic applications of the National Institute of Standards and Technology. The results of the experiments show that the approach can significantly reduce the time of PRNGs testing.