一个网络并行计算的性能预测模型

一个网络并行计算的性能预测模型 A PERFORMANCE PREDICTION MODEL FOR PARALLEL COMPUTING ON NETWORK OF WORKSTATION 张建军 Zhang Jianjun 1 first-author 陈莘萌 Chen Xinmeng 1 武汉大学计算机科学与技术学院 武汉大学计算机科学与技术学院 College of Computer Science and Technology, Wuhan University, Wuhan 430072,China) \ \ College of Computer Science and Technology, Wuhan University, Wuhan 430072,China) \ \ 首先针对网络并行系统中的树状结构的计算提出了一个性能预测模型框架．在此框架的基础上，提出了一个针对分而治之并行程序设计范例的性能预测模型，并给出了应用实例．还讨论了如何使用这一模型评估性能以获得最佳计算规模． In order to effectively program Parallel Computing on NOW（Network of Workstation）, users must be able to evaluate how well the system performs for a given application . In this paper , we present an framework that can be used to evaluate tree structured computing on NOW. Based on this framework , we derive model for a famous parallel programming paradigm Divide and Conquer. We discuss how this model can be used to evaluate performance to determine the reasonable calculating system size and how it could be used to restructure the application to improve performance. 网络并行计算 程序设计范例 性能预测 Parallel computing on NOW programming paradigm performance prediction TP393 1999-01-01 2021-04-01 1