Template library for Multi-GPU pseudorandom number recursion-based generators

TitleTemplate library for Multi-GPU pseudorandom number recursion-based generators
Publication TypeConference Paper
Year of Publication2013
AuthorsSzałkowski D., Stpiczyński P
Conference NameProceedings of the 2013 Federated Conference on Computer Science and Information Systems
PublisherIEEE
AbstractThe aim of the paper is to show how to design and implement fast parallel algorithms for Linear Congruential, Lagged Fibonacci and Wichmann-Hill pseudorandom number generators. The new algorithms employ the divide-and-conquer approach for solving linear recurrence systems. They are implemented on multi GPU-accelerated systems using CUDA. Numerical experiments performed on a computer system with two Fermi GPU cards show that our software achieve good performance in comparison to the widely used NVIDIA CURAND Library.

Historia zmian

Data aktualizacji: 18/02/2016 - 15:10; autor zmian: Piotr Gawron (gawron@iitis.pl)