On the Parallel Implementation of Quasi-Monte Carlo Algorithms

被引:0
|
作者
Atanassov, E. [1 ]
Gurov, T. [1 ]
Ivanovska, S. [1 ]
Karaivanova, A. [1 ]
Simchev, T. [1 ]
机构
[1] Bulgarian Acad Sci, Inst Informat & Commun Technol, Acad G Bonchev Str,Bl 25A, Sofia 1113, Bulgaria
来源
LARGE-SCALE SCIENTIFIC COMPUTING, LSSC 2017 | 2018年 / 10665卷
基金
欧盟地平线“2020”;
关键词
Low-discrepancy sequences; Quasi-Monte Carlo algorithms; High performance computing;
D O I
10.1007/978-3-319-73441-5_27
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The quasi-Monte Carlo algorithms utilize deterministic low-discrepancy sequences in order to increase the rate of convergence of stochastic simulation algorithms. Such kinds of algorithms are widely applicable and consume large share of the computational time on advanced HPC systems. The recent advances in HPC are increasingly rely on the use of accelerators and other similar devices that improve the energy efficiency and offer better performance for certain type of computations. The Xeon Phi coprocessors combine efficient vector floating point computations with familiar operational and development environment. One potentially difficult part of the conversion of a Monte Carlo algorithm into a quasi-Monte Carlo one is the generation of the lowdiscrepancy sequences. On such specialized equipment as the Xeon Phi, the value of memory increases due to the presence of a large number of computational cores. In order to allow quasi-Monte Carlo algorithms to make use of hybrid OpenMP+MPI programming, we implemented generation routines that save both memory space and memory bandwidth, with the aim to widen the applicability of quasi-Monte Carlo algorithms in environments with an extremely large number of computational elements. We present our implementation and compare it with regular Monte Carlo using a popular pseudorandom number generator, demonstrating the applicability and advantages of our approach.
引用
收藏
页码:258 / 265
页数:8
相关论文
共 50 条
  • [21] Density Estimation by Monte Carlo and Quasi-Monte Carlo
    L'Ecuyer, Pierre
    Puchhammer, Florian
    MONTE CARLO AND QUASI-MONTE CARLO METHODS, MCQMC 2020, 2022, 387 : 3 - 21
  • [22] On Monte Carlo and Quasi-Monte Carlo for Matrix Computations
    Alexandrov, Vassil
    Davila, Diego
    Esquivel-Flores, Oscar
    Karaivanova, Aneta
    Gurov, Todor
    Atanassov, Emanouil
    LARGE-SCALE SCIENTIFIC COMPUTING, LSSC 2017, 2018, 10665 : 249 - 257
  • [23] Monte Carlo and quasi-Monte Carlo methods - Preface
    Spanier, J
    Pengilly, JH
    MATHEMATICAL AND COMPUTER MODELLING, 1996, 23 (8-9) : R11 - R13
  • [24] Monte Carlo and quasi-Monte Carlo algorithms for the Barker-Ferry equation with low complexity
    Gurov, TV
    Witlock, PA
    Dimov, IT
    NUMERICAL METHODS AND APPLICATIONS, 2003, 2542 : 108 - 116
  • [25] Error in Monte Carlo, quasi-error in Quasi-Monte Carlo
    Kleiss, Ronald
    Lazopoulos, Achilleas
    COMPUTER PHYSICS COMMUNICATIONS, 2006, 175 (02) : 93 - 115
  • [26] Error estimates in Monte Carlo and Quasi-Monte Carlo integration
    Lazopouls, A
    ACTA PHYSICA POLONICA B, 2004, 35 (11): : 2617 - 2632
  • [27] A parallel quasi-Monte Carlo method for solving systems of linear equations
    Mascagni, M
    Karaivanova, A
    COMPUTATIONAL SCIENCE-ICCS 2002, PT II, PROCEEDINGS, 2002, 2330 : 598 - 608
  • [28] MATHEMATICAL BASIS OF MONTE CARLO AND QUASI-MONTE CARLO METHODS
    ZAREMBA, SK
    SIAM REVIEW, 1968, 10 (03) : 303 - &
  • [29] The error bounds and tractability of quasi-Monte Carlo algorithms in infinite dimension
    Hickernell, FJ
    Wang, XQ
    MATHEMATICS OF COMPUTATION, 2002, 71 (240) : 1641 - 1661
  • [30] When are quasi-Monte Carlo algorithms efficient for high dimensional integrals?
    Sloan, IH
    Wozniakowski, H
    JOURNAL OF COMPLEXITY, 1998, 14 (01) : 1 - 33