基于微处理器的并行计算系统的构建及性能分析  

The construction and performance analysis of microprocessor parallel computing system

作　　者：李晓佳[1] 董延华[1] LI Xiaojia;DONG Yanhua(College of Computer,Jilin Normal University,Siping 136000,China)

机构地区：[1]吉林师范大学计算机学院

出　　处：《智能计算机与应用》2019年第6期121-123,131,共4页Intelligent Computer and Applications

摘　　要：随着材料科学技术的发展,模拟计算需要处理的数据量逐渐增多,仅通过提高单个处理器的运算速度和传统的串行计算技术已难以解决上述问题。大规模问题的解决通常需要高性能计算集群的支持,由于其花费较高,中小型及个人的科研支出无力承担。本文主要介绍微处理器集群的优势及特点,利用普通PC机搭建并行计算环境,通过实例的运行,验证并行计算的优势及高效性。With the development of material science technology,the analog computation needs to deal with more and more data.Improving the operational speed of single processor and using the traditional serial computing technology can’t solve these problems.Solving large-scale problems usually requires the support of HPC clusters whose price is very high,and the small and medium-sized institutions can’t afford. This paper mainly introduces the advantages and characteristics of microprocessor cluster,uses ordinary PC to build a parallel computing environment,and verifies the advantages and efficiency of parallel computing through the operation of examples.

关 键 词：微处理器 串行计算 并行计算 

分 类 号：TP338.6[自动化与计算机技术—计算机系统结构]