Effective Monte Carlo simulation on System-V massively parallel associative string processing architecture

Author

Ódor, Géza ; Krikelis, Argy ; Vesztergombi, György ; Rohrbach, Francois

Author_Institution

Res. Inst. for Tech. Phys. & Mater. Sci., Budapest, Hungary

fYear

1999

fDate

3-5 Feb 1999

Firstpage

281

Lastpage

288

Abstract

We show that the latest version of massively parallel processing associative string processing architecture (System-V) is applicable for fast Monte Carlo simulation if an effective on-processor random number generator is implemented. Our lagged Fibonacci generator can produce 10 ⁸ random numbers on a processor string of 12 K PE-s. The time dependent Monte Carlo algorithm of the one-dimensional non-equilibrium kinetic Ising model performs 80 faster than the corresponding serial algorithm on a 300 MHz UltraSparc

Keywords

Monte Carlo methods; associative processing; parallel architectures; Monte Carlo simulation; lagged Fibonacci generator; massively parallel associative string processing architecture; random number generator; system-V; time dependent Monte Carlo; Application specific processors; Clocks; Clustering algorithms; Computer architecture; High performance computing; Image processing; Kinetic theory; Materials science and technology; Parallel processing; Physics;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel and Distributed Processing, 1999. PDP '99. Proceedings of the Seventh Euromicro Workshop on

Conference_Location

Funchal

Print_ISBN

0-7695-0059-5

Type

conf

DOI

10.1109/EMPDP.1999.746690

Filename

746690