首页 | 本学科首页   官方微博 | 高级检索  
     

系统负载与并行程序运行时间的关系
引用本文:雷州,徐志伟,祝明发.系统负载与并行程序运行时间的关系[J].计算机研究与发展,2000,37(7):813-818.
作者姓名:雷州  徐志伟  祝明发
作者单位:1. 国家智能计算机研究开发中心,北京,100080
2. 中国科学院计算技术研究所,北京,100080
基金项目:国家“八六三”高技术研究发展计划基金,国家杰出青年科学基金
摘    要:负载共享技术在并行处理中是至关重要的,通过对大量负载共享献的考究发现,以前的研究都是基于一定系统负载而进行平衡自救的设计,它们很少考虑到所选定的系统负载与程序运行时间之间的准确关系,为了确定系统负载对并行程序运行的影响,确定了影响并行程序运行的两个重要系统因素:CPU负载和网络负载,为了不失一般性,也为了简化网络负载的测量,选用2NASPVM并行Benchmark作为实验测试对象;为了得到程序运

关 键 词:CPU负载  并行计算机  并行程序  运行时间

THE RELATIONSHIP BETWEEN SYSTEM LOADS AND RUNTIME OF PARALLEL PROGRAMS
LEI Zhou,XU Zhi-Wei,ZHU Ming-Fa.THE RELATIONSHIP BETWEEN SYSTEM LOADS AND RUNTIME OF PARALLEL PROGRAMS[J].Journal of Computer Research and Development,2000,37(7):813-818.
Authors:LEI Zhou  XU Zhi-Wei  ZHU Ming-Fa
Abstract:Load balancing is an important technique to improve the performance of parallel processing. Previous studies used load indices to balance workload. However, the real relationship between runtime of parallel programs and system loads is rarely proposed. Through lots of experiments, two important conclusions are obtained: one about the relationship between runtime of parallel programs and CPU load, and the other about the relationship between runtime and network load. In order to be typical and get network load easily, NAS PVM Benchmarks are used as test applications. A tool of job submission is designed to record the exact runtimes of test applications.
Keywords:CPU load    network load  load sharing
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号