• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2013, Vol. 35 ›› Issue (11): 76-79.

• 论文 • 上一篇    下一篇

分数阶微分方程的一种细粒度数据级并行算法

龚春叶1,2,3,包为民1,闵昌万1,张烨琛1,刘杰3   

  1. (1.空间物理重点实验室,北京 100076;2.国防科学技术大学航天科学与工程学院,湖南 长沙 410073;3.国防科学技术大学计算机学院,湖南 长沙 410073)
  • 收稿日期:2013-08-25 修回日期:2013-10-15 出版日期:2013-11-25 发布日期:2013-11-25
  • 基金资助:

    国家自然科学基金资助项目(11175253)

A fine-grain data-level parallel algorithm
for fractional differential equations  

GONG Chun-ye1,2,3,BAO Wei-min1,MIN Chang-wan1,ZHANG Ye-chen1,LIU Jie3   

  1. (1.Science and Technology on Space Physics Laboratory,Beijing 100076;
    2.School  of Aerospace Science and Technology,National University of Defense Technology,Changsha 410073;
    3.School of Computer Science,National University of Defense Technology,Changsha 410073,China)
  • Received:2013-08-25 Revised:2013-10-15 Online:2013-11-25 Published:2013-11-25

摘要:

在GPU上基于CUDA编程模型提出针对Riesz空间分数阶扩散方程显式有限差分法的细粒度数据级并行算法。对算术逻辑操作的基本CUDA核心的细节及网格点值的计算优化进行了描述。实验结果表明,本文提出的并行算法与精确解符合得很好, 在NVIDIA Quadro FX 5800 GPU上的运行速度超过多核Intel Xeon E5540 CPU并行算法的运行速度四倍有余。关键词:

关键词: 分数阶微分方程, Riesz分数阶, 并行计算, 并行算法, GPU

Abstract:

The paper proposes a fine-grain data-level parallel algorithm for Riesz space fractional diffusion equation with explicit finite difference method and implements it with CUDA parallel programming model on GPU. The details of basic CUDA kernels for these operations and optimization of the production of grid points are described. The experimental results show that the parallel algorithm compares well with the exact analytic solution and runs more than four times faster on NVIDIA Quadro FX 5800 GPU than the parallel CPU solution on multi-core Intel Xeon E5540 CPU.

Key words: fractional differential equation;Riesz fractional;parallel computing;parallel algorithm;GPU