一个面向I/O密集型并行应用的性能模型  

A Performance Model of I/O-Intensive Parallel Applications

作　　者：陈永然[1] 齐星云[1] 窦文华[1] 

机构地区：[1]国防科学技术大学计算机学院,长沙410073

出　　处：《计算机研究与发展》2007年第4期707-713,共7页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(40245023);计算物理国家重点实验室基金项目(51479040103KG0201)

摘　　要：近几年,性能模型作为一种新的并行系统性能分析方法,得到学术界和工业界的广泛重视.给出了一个开放式性能模型框架结构PMPS(n)并实现了该框架下的一个面向I/O密集型并行应用模型PMPS(3),使用该模型分析了各种NPB程序在PⅣ机群系统上的性能.实验结果表明,对存储密集型应用,PMPS(3)模型与PERC模型预测结果相当;对I/O密集型应用性能的预测,PMPS(3)模型优于PERC模型.进一步分析发现,应用的数据相关、控制相关和操作重叠会影响模型预测结果.实验结果还说明了PMPS(n)性能模型具有很好的扩展性.High performance computing （HPC） is widely used in science and engineering to solve large computation problems. The peak performances of computers increase in a continuous and rapid way. But the sustained performances achieved by real applications do not increase in the same scale as the peak performances do and the gap between them is widening. Performance model of parallel systems, which is one of effective ways to solve this problem, draws the attentions of the research community as well as the industry community. In this paper, an open performance model infrastructure PMPS（ n ） and a realization of this infrastructure-PMPS（3）, a performance model of I/O-intensive parallel application, are given and used to perform NPB benchmarking on PIV cluster systems. The experiment results indicate that PMPS（3） can forecast better than PERC for I/O intensive applications, and can do as well as PERC for storageintensive applications. Through further analysis, it is indicated that the results of the performance model can be influenced by the data correlations, control correlations and operation overlaps. Then such factors must be considered in the performance models to improve the forecast precision. The experiment results also show that PMPS（n） has very good scalability.

关 键 词：性能模型 机器轮廓 应用特征 褶合方法 I/O密集型 并行系统 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]