面向异构融合处理器的性能分析、优化及应用综述  

Survey on Performance Analysis,Optimization,and Applications of Heterogeneous Fusion Processors

作　　者：张峰 翟季冬[3] 陈政 林甲灶 杜小勇[1,2] ZHANG Feng;ZHAI Ji-Dong;CHEN Zheng;LIN Jia-Zao;DU Xiao-Yong(Key Laboratory of Data Engineering and Knowledge Engineering(Renmin University of China),Ministry of Education,Beijing 100872,China;School of Information,Renmin University of China,Beijing 100872,China;Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China;Department of Information Management,Peking University,Beijing 100871,China)

机构地区：[1]数据工程与知识工程教育部重点实验室(中国人民大学),北京100872 [2]中国人民大学信息学院,北京100872 [3]清华大学计算机科学与技术系,北京100084 [4]北京大学信息管理系,北京100871

出　　处：《软件学报》2020年第8期2603-2624,共22页Journal of Software

基　　金：国家重点研发计划(2016YFB0200100);国家自然科学基金(61732014,61722208,61802412)。

摘　　要：随着异构计算技术的不断进步,CPU和GPU等设备相集成的异构融合处理器在近些年得到了充分的发展,并引起了学术界和工业界的关注.将多种设备进行集成带来了许多好处,例如,多种设备可以访问同样的内存,可以进行细粒度的交互.然而,这也带来了系统编程和优化方面的巨大挑战.充分发挥异构融合处理器的性能,需要充分利用集成体系结构中共享内存等特性;同时,还需结合具体应用特征对异构融合处理器上的不同设备进行优化.首先对目前涉及异构融合处理器的研究工作进行了分析,之后介绍了异构融合处理器的性能分析工作,并进一步介绍了相关优化技术,随后对异构融合处理器的应用进行了总结.最后,对异构融合处理器未来的研究方向进行展望,并进行了总结.With the development of heterogeneous computing technology,heterogeneous fusion processors,such as CPU-GPU integrated processors,have been fully developed in recent years,and arouse attention from both academia and industry.The fusion of different devices has several advantages.For example,all devices share the same memory and can have fine-grained cooperation.However,many system programming challenges and optimization challenges have emerged.To take full advantage of the capacity of heterogeneous fusion processors,it is needed to utilize features of heterogeneous fusion processors such as shared memory,and to perform architecture optimizations to different devices according to different applications.The research work related to heterogeneous fusion processors is first analyzed and summarized.Second,the related work about performance analysis is introduced.Third,the optimizations on heterogeneous fusion processors are summarized.A summarization for the applications that utilize heterogeneous fusion processors is also provided.At last,the future directions are provided on heterogeneous fusion processors and conclusion is given.

关 键 词：CPU GPU 异构融合处理器 性能分析 性能优化 

分 类 号：TP306[自动化与计算机技术—计算机系统结构]