Parallel Random Numbers, Simulation, and Reproducible Research

被引：8
作者：
Hill, David R. C. [1 ,2 ]
机构：
[1] Clermont Univ, Aubiere, France
[2] Univ Blaise Pascal, Aubiere, France
来源：
COMPUTING IN SCIENCE & ENGINEERING | 2015年 / 17卷 / 04期
关键词：
Generators; Computational modeling; Context; Numerical models; Context modeling; Stochastic processes; Parallel processing; scientific computing; parallel random numbers; stochastic simulation; high-performance computing; reproducibility; STOCHASTIC SIMULATIONS; RIGOROUS DISTRIBUTION; STREAMS; RECONSTRUCTION;
D O I：
10.1109/MCSE.2015.79
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
Parallel and distributed simulation is an area with extensive research into effective solutions. In the context of parallel stochastic simulations, it's important to know the right techniques for generating parallel pseudorandom numbers. In addition, it's possible and necessary for anyone wishing to produce a scientific work of quality to pay attention to numerical reproducibility of simulation results. Significant differences are observed in the results of parallel stochastic simulations if practitioners fail to apply best practices. By implementing a rigorous method, it's possible to reproduce the same numerical results for parallel stochastic simulations and to check them with their sequential counterpart. © 1999-2011 IEEE.
引用
收藏
页码：66 / 71
页数：6
相关论文
共 30 条
[1]  
Coddington P. D., 1998, P INT C SUP JUL, P282
[2]   SIMULA - AN ALGOL-BASED SIMULATION LANGUAGE [J].
DAHL, OJ ;
NYGAARD, K .
COMMUNICATIONS OF THE ACM, 1966, 9 (09) :671-&
[3]   PARALLELIZATION OF RANDOM NUMBER GENERATORS AND LONG-RANGE CORRELATIONS [J].
DEMATTEIS, A ;
PAGNUTTI, S .
NUMERISCHE MATHEMATIK, 1988, 53 (05) :595-608
[4]   CONTROLLING CORRELATIONS IN PARALLEL MONTE-CARLO [J].
DEMATTEIS, A ;
PAGNUTTI, S .
PARALLEL COMPUTING, 1995, 21 (01) :73-84
[5]  
Drummond Chris, 2009, 4 WORKSH EV METH MAC
[6]   Fully 3D Monte Carlo image reconstruction in SPELT using functional regions [J].
El Bitar, Ziad ;
Lazaro, Delphine ;
Coello, Christopher ;
Breton, Vincent ;
Hill, David ;
Buvat, Irene .
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2006, 569 (02) :399-403
[7]  
Fomel S, 2009, COMPUT SCI ENG, V11, P5, DOI 10.1109/MCSE.2009.14
[8]   Efficient jump ahead for F2-linear random number generators [J].
Haramoto, Hiroshi ;
Matsumoto, Makoto ;
Nishimura, Takuji ;
Panneton, Francois ;
L'Ecuyer, Pierre .
INFORMS JOURNAL ON COMPUTING, 2008, 20 (03) :385-390
[9]   Don't trust parallel Monte Carlo! [J].
Hellekalek, P .
TWELFTH WORKSHOP ON PARALLEL AND DISTRIBUTED SIMULATION - PADS'98, PROCEEDINGS, 1998, :82-89
[10]   Distribution of random streams for simulation practitioners [J].
Hill, David R. C. ;
Mazel, Claude ;
Passerat-Palmbach, Jonathan ;
Traore, Mamadou K. .
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2013, 25 (10) :1427-1442
123