Parallel Direct Simulation Monte Carlo Computation Using CUDA on GPUs

被引：0
|
作者：
Su, C. -C. [1 ]
Hsieh, C. -W. [2 ]
Smith, M. R. [2 ]
Jermy, M. C. [3 ]
Wu, J. -S. [1 ,3 ]
机构：
[1] Natl Chiao Tung Univ, Dept Mech Engn, 1001 Ta Hsueh Rd, Hsinchu 30010, Taiwan
[2] Natl Ctr High Performance Comp, Hsinchu 30076, Taiwan
[3] Univ Canterbury, Dept Mech Engn, Christchurch 81401, New Zealand
来源：
27TH INTERNATIONAL SYMPOSIUM ON RAREFIED GAS DYNAMICS, 2010, PTS ONE AND TWO | 2011年 / 1333卷
关键词：
Rarefied Gas Dynamics; Parallel Simulation; Direct Simulation Monte Carlo (DSMC); CUDA; GPU;
D O I：
10.1063/1.3562672
中图分类号：
O4 [物理学];
学科分类号：
0702 ;
摘要：
In this study computations of the two-dimensional Direct Simulation Monte Carlo (DSMC) method using Graphics Processing Units (GPUs) are presented. An all-device (GPU) computational approach is adopted-where the entire computation is performed on the GPU device, leaving the CPU idle-which includes particle moving, indexing, collisions between particles and state sampling. The subsequent application to GPU computation requires various changes to the original DSMC method to ensure efficient performance on the GPU device. Communications between the host (CPU) and device (GPU) occur only during problem initialization and simulation conclusion when results are only copied from the device to the host. Several multi-dimensional benchmark tests are employed to demonstrate the correctness of the DSMC implementation. We demonstrate here the application of DSMC using a single-GPU, with speedups of 3 similar to 10 times as compared to a high-end Intel CPU (Intel Xeon X5472) depending upon the size and the level of rarefaction encountered in the simulation.
引用
收藏
页码：343 / +
页数：2
相关论文
共 50 条
  • [21] Mixed Monte Carlo parallel algorithms for matrix computation
    Fathi, B
    Liu, B
    Alexandrov, V
    [J]. COMPUTATIONAL SCIENCE-ICCS 2002, PT II, PROCEEDINGS, 2002, 2330 : 609 - 618
  • [22] Parallel graph component labelling with GPUs and CUDA
    Hawick, K. A.
    Leist, A.
    Playne, D. P.
    [J]. PARALLEL COMPUTING, 2010, 36 (12) : 655 - 678
  • [23] Parallel wavelet-based clustering algorithm on GPUs using CUDA
    Yildirim, Ahmet Artu
    Ozdogan, Cem
    [J]. WORLD CONFERENCE ON INFORMATION TECHNOLOGY (WCIT-2010), 2011, 3
  • [24] Parallel SOR for Solving the Convection Diffusion Equation Using GPUs with CUDA
    Cotronis, Yiannis
    Konstantinidis, Elias
    Louka, Maria A.
    Missirlis, Nikolaos M.
    [J]. EURO-PAR 2012 PARALLEL PROCESSING, 2012, 7484 : 575 - 586
  • [25] The direct simulation Monte Carlo method
    Alexander, FJ
    Garcia, AL
    [J]. COMPUTERS IN PHYSICS, 1997, 11 (06): : 588 - 593
  • [26] Development and performance analysis of a parallel Monte Carlo neutron transport simulation program for GPU-Cluster using MPI and CUDA technologies
    Pereira, Claudio M. N. A.
    Mol, Antonio C. A.
    Heimlich, Adino
    Moraes, Sergio R. S.
    Resende, Pedro
    [J]. PROGRESS IN NUCLEAR ENERGY, 2013, 65 : 88 - 94
  • [27] Parallel Monte Carlo simulation algorithm for the spectral reflectance and transmittance of the wind-generated bubble layers in the upper ocean using CUDA
    Yang, Yu
    Guo, Lixin
    [J]. OPTICS EXPRESS, 2020, 28 (22) : 33538 - 33555
  • [28] Nonlinear acoustic simulatlions using direct simulation Monte Carlo
    Danforth, AL
    Long, LN
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2004, 116 (04): : 1948 - 1955
  • [29] GPU accelerated Monte Carlo simulation of Brownian motors dynamics with CUDA
    Spiechowicz, J.
    Kostur, M.
    Machura., L.
    [J]. Computer Physics Communications, 2015, 191 (01) : 140 - 149
  • [30] GPU accelerated Monte Carlo simulation of Brownian motors dynamics with CUDA
    Spiechowicz, J.
    Kostur, M.
    Machura, L.
    [J]. Computer Physics Communications, 2015, 191 : 140 - 149
12345