基于模糊聚类分析的构件并行技术研究  

Research on Component Parallel Technology Based on Fuzzy Clustering Analysis

作　　者：杜静[1] 敖富江[2] 杨学军[1] 杨灿群[1] 

机构地区：[1]国防科技大学计算机学院,长沙410073 [2]国防科技大学机电工程与自动化学院,长沙410073

出　　处：《计算机学报》2007年第11期1939-1946,共8页Chinese Journal of Computers

基　　金：国家自然科学基金(60621003;60633050)资助.~~

摘　　要：提出了一种新的面向科学计算的构件技术——基于模糊聚类分析的构件并行技术,旨在提高构件间的并行度和数据局部性,避免通信瓶颈.该技术分为两个阶段:域划分和子构件组合.其中域划分利用了编译时的数据依赖分析技术.然后考虑访问步长的影响,利用不定方程,提出了区间重叠度的概念.基于此利用所设计的基于区间重叠度的模糊聚类算法实现子构件分类组合,并给出了算法的形式化描述.实验结果表明,通过该算法的编译时优化,构件程序能够获得良好的数据局部性、适中的粒度以及高度的并行性,算法具有很好的可扩展性.This paper proposes a new scientific computing-oriented component technology-Component Parallel Technology Based on Fuzzy Clustering Analysis, aiming at improving parallelism and data locality among components, and avoiding communication bottleneck. The technology is composed of two parts： Domain partition and sub-component combination. Domain partition uses data dependence analysis technique during compile time. Then considering the effect of access stride, the concept of interval overlap degree is proposed by using indefinite equation. Based on this, it implements the classification and combination of sub-components by using fuzzy clustering algorithm for interval overlap degree designed by the authors, and presents the formal description of the algorithm. The experimental results show that the algorithm is efficient and scalable for scientific component programs in terms of fine data locality, moderate granularity and high parallelism.

关 键 词：通信瓶颈 并行度 数据局部性 区间重叠度 模糊聚类 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]