大规模并行处理系统及其程序设计方法研究——Cache缺失延迟、层次算法和可定域性  

THE STUDY OF AN MPP SYSTEM AND ITS PROGRAMMING METHODS

作　　者：王文义[1,2] 董绍静[1,2] 

机构地区：[1]郑州工业大学计算机科学与技术系 [2]肯塔基大学计算中心

出　　处：《计算机研究与发展》1999年第5期589-593,共5页Journal of Computer Research and Development

摘　　要：实践表明，大规模并行处理系统（ｍａｓｓｉｖｅｌｙｐａｒａｌｅｌｐｒｏｃｅｓｉｎｇｓｙｓｔｅｍ，ＭＰＰ）的实际有效速度与其理论峰值速度往往存在着较大差距，有时仅能达到峰值速度的２５％左右．鉴于目前许多领域的高性能科学计算都要把ＭＰＰ系统作为主要的实现工具，因此上述问题已引起国内外专家的普遍关注．文中讨论了影响大规模并行处理系统有效速度主要因素之一的Ｃａｃｈｅ缺失问题，并以ＥｘｅｍｐｌａｒＳＰＰ１２００／ＸＡ为例，在层次算法和可定域性两个方面实验并总结了提高系统应用性能的若干程序设计方法．Practice shows that in most cases the effective speed of a massively parallel processing system(MPP) is much lower than its peak speed,often reaching only about 25% of the latter.At present MPP is used to perform high\|performance scientific computation in many research fields,so the above\|mentioned problem has been followed with interest by experts both at home and abroad.Here discussed is the cache missing latency problem,that is one of the main factors influencing MPP systems effective speed. Taking Exemplar SPP1200/XA for example, some programming methods for increasing the systems application properties are tested and summarized in discussing both the hierarchical algorithm and localizability.

关 键 词：CACHE 缺失延迟 并行处理系统 程序设计方法 

分 类 号：TP338.6[自动化与计算机技术—计算机系统结构] TP311.11[自动化与计算机技术—计算机科学与技术]