00897nas a2200145   4500000000100000000000100001008004100002260003200043100002900075700001800104700001500122245008000137300001400217520052000231       2012                            d  bIEEE Computer Society Press1 aPrzemysław Stpiczyński1 aD. Szatkowski1 aJ. Potiopa00aParallel GPU accelerated Recursion-based generators of pseudorandom numbers  a571–5783 aAbstract—The aim of the paper is to show how to design fast parallel algorithms for linear congruential and lagged Fibonacci pseudorandom numbers generators. The new algorithms employ the divide-and-conquer approach for solving linear recurrence systems and can be easily implemented on GPU-accelerated hybrid systems using CUDA or OpenCL. Numerical experiments performed on a computer system with modern Fermi GPU show that they achieve good speedup in comparison to the standard CPU-based sequential algorithms.