Computational Technology Resources - CCP

Keywords: GPU, hybrid computing system, pseudorandom numbers, percolation models.

Summary

A general purpose PRN generation library LRND32 is further developed. The library for parallel PRN generation on NVIDIA GPUs is created. The performance of generators developed for CPU and GPU was compared with the performance of the available libraries of generators. The results are presented which confirm the efficiency of the developed methods. It is shown that Intel MKL MRG32k3a has a better speed of consecutive terms generation, but LRND32-255 / LRND32-1023 generators have a better speed of generation of PRNs with arbitrary numbers. Moreover, the period of Intel MKL MRG32k3a is 2⁶⁴ and ⁸³² times less respectively.

A numerical simulation using a dynamic percolation model (DPM) of oil displacement [3] was fulfilled for the percolation lattice of upto 10 billion points. Determination of the percolation threshold showed that the generated sequences are of high quality.

References

1: M.V. Iakobovski, "Parallel algorithm for pseudorandom numbers generation", Mathematical modeling Journal, 21(6), 59-68, 2009. (in Russian)
2: R.P. Brent, "Uniform Random Number Generators for Supercomputers", Computer Sciences Laboratory, Australian National University, in Proceedings Fifth Australian Supercomputer Conference (Melbourne, December 1992), 95-104, 1992.
3: S.S. Lapushkin, M.H. Brenerman, M.V. Iakobovski, "Modeling of dynamic filtration processes in percolation grids on high performance computer systems", Mathematical modeling Journal, 16(11), 77-88, 2004. (in Russian)

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £85 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 95 PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, GRID AND CLOUD COMPUTING FOR ENGINEERING Edited by: Paper 23 The Scalable GPU-based Parallel Algorithm for Uniform Pseudorandom Number Generation M.V. Iakobovski¹, M.A. Kornilina¹ and M.N. Voroniuk² ¹Keldysh Institute of Applied Mathematics, Russian Academy of Sciences, Moscow, Russia ²Moscow State Technological University "Stankin", Russia doi:10.4203/ccp.95.23 purchase the full-text of this paper Full Bibliographic Reference for this paper M.V. Iakobovski, M.A. Kornilina, M.N. Voroniuk, "The Scalable GPU-based Parallel Algorithm for Uniform Pseudorandom Number Generation", in , (Editors), "Proceedings of the Second International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 23, 2011. doi:10.4203/ccp.95.23 Keywords: GPU, hybrid computing system, pseudorandom numbers, percolation models. Summary A general purpose PRN generation library LRND32 is further developed. The library for parallel PRN generation on NVIDIA GPUs is created. The performance of generators developed for CPU and GPU was compared with the performance of the available libraries of generators. The results are presented which confirm the efficiency of the developed methods. It is shown that Intel MKL MRG32k3a has a better speed of consecutive terms generation, but LRND32-255 / LRND32-1023 generators have a better speed of generation of PRNs with arbitrary numbers. Moreover, the period of Intel MKL MRG32k3a is 2⁶⁴ and ⁸³² times less respectively. A numerical simulation using a dynamic percolation model (DPM) of oil displacement [3] was fulfilled for the percolation lattice of upto 10 billion points. Determination of the percolation threshold showed that the generated sequences are of high quality. References 1 M.V. Iakobovski, "Parallel algorithm for pseudorandom numbers generation", Mathematical modeling Journal, 21(6), 59-68, 2009. (in Russian) 2 R.P. Brent, "Uniform Random Number Generators for Supercomputers", Computer Sciences Laboratory, Australian National University, in Proceedings Fifth Australian Supercomputer Conference (Melbourne, December 1992), 95-104, 1992. 3 S.S. Lapushkin, M.H. Brenerman, M.V. Iakobovski, "Modeling of dynamic filtration processes in percolation grids on high performance computer systems", Mathematical modeling Journal, 16(11), 77-88, 2004. (in Russian) purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £85 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions