| MPI＋OpenMP混合编程模型在大规模三对角线性方程组求解中的应用 |
| |
| 引用本文： | 郑汉垣,刘智翔,封卫兵,张武.MPI＋OpenMP混合编程模型在大规模三对角线性方程组求解中的应用[J].微电子学与计算机,2011,28(8). |
| |
| 作者姓名： | 郑汉垣 刘智翔 封卫兵 张武 |
| |
| 作者单位： | 1. 上海大学计算机工程与科学学院,上海200072／龙岩学院计算机系,福建龙岩364000
2. 上海大学计算机工程与科学学院,上海,200072 |
| |
| 基金项目： | 上海市科委重点项目(10510500600); 教育部2008年度高等学校博士学科点专项科研基金项目(200802800007); 上海市重点学科建设项目资助基金项目(J50103) |
| |
| 摘 要： | 分布式共享存储系统的特点是每个节点内是共享存储的,而节点间是分布式存储.为了更好地利用这种多级体系结构,讨论了MPI＋OpenMP混合编程模型的性能及实现方法,建立了大规模三对角线性方程组的MPI＋OpenMP混合并行算法,并在上海大学高性能计算集群上与单纯MPI算法进行了性能方面的比较.结果表明,MPI＋OpenMP混合并行算法具有更好的加速比和扩展性.
|
| 关 键 词： | 混合编程模型 分布共享存储 三对角线性方程组 MPI |
MPI and OpenMP Paradigms and Its Application of Solving Large Scale Tridiagonal Linear Systems |
| |
| ZHENG Han-yuan,LIU Zhi-xiang,FENG Wei-bing,ZHANG Wu.MPI and OpenMP Paradigms and Its Application of Solving Large Scale Tridiagonal Linear Systems[J].Microelectronics & Computer,2011,28(8). |
| |
| Authors: | ZHENG Han-yuan LIU Zhi-xiang FENG Wei-bing ZHANG Wu |
| |
| Affiliation: | ZHENG Han-yuan1,2,LIU Zhi-xiang1,FENG Wei-bing1,ZHANG Wu1(1 School of Computer Science,Shanghai University,Shanghai 200072,China,2 Department of Computer,Longyan University,Lingyan 364000,China) |
| |
| Abstract: | The distributed shared memory system is characterized by shared memory multi-processors on each node and distributed memory among nodes.In order to make use of this hierarchical architecture,this paper discusses the performance of MPI+OpenMP hybrid programming paradigm and different implementations.We design a multi-granularity parallel algorithm for solving larger scale tridiagonal linear systems,and compare its performance with pure MPI algorithm on the high performance computer of Shanghai University.The... |
| |
| Keywords: | hybrid paradigm distributed shared memory tridiagonal linear systems MPI |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
