TY - CPAPER
AU - Przemysław Stpiczyński
AU - D. Szatkowski
AU - J. Potiopa
AB - Abstract—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.
BT - Proceedings of the Federated Conference on Computer Science and Information Systems
LA - eng
N1 - Federated Conference on computer Science and Information Systems, September 9-12, 2012, Wroclaw, Poland
N2 - Abstract—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.
PB - IEEE Computer Society Press
PY - 2012
EP - 571–578
T2 - Proceedings of the Federated Conference on Computer Science and Information Systems
TI - Parallel GPU accelerated Recursion-based generators of pseudorandom numbers
ER -