HPMR在并行矩阵计算中的应用  

Application of HPMR in Parallel Matrix Computation

作　　者：郑启龙[1,2] 吴晓伟[1,2] 房明[1,2] 王昊[1,2] 汪胜[1,2] 王向前[1,2] 

机构地区：[1]中国科学技术大学计算机科学技术学院,合肥230027 [2]安徽省高性能计算与应用重点实验室,合肥230026

出　　处：《计算机工程》2010年第8期49-51,共3页Computer Engineering

基　　金：核高基重大专项基金资助项目(2009ZX01034-001-001-002);国家自然科学基金资助重点项目(60533020);安徽省自然科学基金资助项目(090412068)

摘　　要：为了解决传统并行编程难度大、效率低的问题,提出一种基于MapReduce模型的并行编程方法,在高性能MapReduce平台上实现矩阵并行LU分解。实验结果表明,相比传统并行编程模型,MapReduce模型并行程序可较好满足高性能数值计算需求,其编程简洁性和可读性能有效提升并行编程效率。In order to solve the problems of difficulty and low efficiency in traditional parallel programming,this paper presents a parallel programming method based on MapReduce model,realizes matrix parallel LU decomposition under High Performance MapReduce（HPMR） platform.Experimental result shows that the parallel programs implemented via the MapReduce model can meet the need of high-performance numerical computing,and its programming simplicity and readability to enhance the efficiency of parallel programming compared with traditional parallel programming models.

关 键 词：高性能MapReduce 并行编程 数值计算 LU分解 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]