The Limits of Reproducibility in Numerical Simulation

被引:15
作者
Diethelm, Kai
机构
[1] Gesellschaft Fr Numerische Simulation (GNS), Germany
关键词
numerical analysis; Parallel algorithms; scientific computing;
D O I
10.1109/MCSE.2011.21
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Modern computational simulation's increasing and mainly speed-oriented use of HPC systems often conflicts with the goal of making research reproducible. Indeed, the simulations that result from HPC use often behave reproducibly in only a limited way As a discussion of this phenomenon's technical background describes, the problems entailed will be very difficult to overcome.
引用
收藏
页码:64 / 71
页数:8
相关论文
共 18 条
[1]  
Ahn C.W., 2006, Advances in Evolutionary Algorithms
[2]  
Biegler L., 2011, LARGE SCALE INVERSE
[3]  
Buckheit JB, 1995, WAVELETS STAT, P55, DOI 10.1007/978-1-4612-2544-75
[4]  
Evans M., 2000, Approximating integrals via Monte Carlo and deterministic methods
[5]  
Fomel S, 2009, COMPUT SCI ENG, V11, P5, DOI 10.1109/MCSE.2009.14
[6]   Using accurate arithmetics to improve numerical reproducibility and stability in parallel applications [J].
He, Y ;
Ding, CHQ .
JOURNAL OF SUPERCOMPUTING, 2001, 18 (03) :259-277
[7]   THE ACCURACY OF FLOATING-POINT SUMMATION [J].
HIGHAM, NJ .
SIAM JOURNAL ON SCIENTIFIC COMPUTING, 1993, 14 (04) :783-799
[8]   LITERATE PROGRAMMING [J].
KNUTH, DE .
COMPUTER JOURNAL, 1984, 27 (02) :97-111
[9]  
LeMaitre OP, 2010, SCI COMPUT, P1, DOI 10.1007/978-90-481-3520-2
[10]  
Meurant Gerard, 2006, The Lanczos and Conjugate Gradient Algorithms: from Theory to Finite Precision Computations