新兴高性能计算行业应用及发展战略
|
摘要
数据密集型新兴行业应用快速发展,是近年来高性能计算应用日益广泛和深入的主要特征。新兴高性能行业应用,在高性能计算系统技术创新、计算环境创新与应用创新等各个层面,都带来了新的挑战与机遇。文章在系统总结领域应用进展的基础上,概括了新兴行业应用的技术特点与挑战,提出了加大高性能计算系统核心技术创新力度、构建面向新型应用的高性能计算环境、大力推进高性能应用软件研发、大力推进传统应用的新方法开发,以及大力推进大数据人工智能等新领域基准评测工具研发等发展战略建议。
The rapid development of data-intensive emerging application areas in recent years is one of major characteristics of the extensive and in-depth applications of high performance computing(HPC). The HPC applications in the emerging areas bring new challenges and opportunities at all levels of HPC, including system technological innovation, computing environment innovation, and application innovation. Based on reviewing the application progress of HPC in the emerging areas, this paper summarizes the current technical characteristics and challenges, and provides strategic recommendations for the development of emerging HPC application areas, including increasing the core technology innovation of HPC systems, building HPC environment for emerging application areas, promoting the development of HPC application software and new methods for traditional applications, as well as promoting the development of benchmarking tools in new areas such as big data and artificial intelligence.
The rapid development of data-intensive emerging application areas in recent years is one of major characteristics of the extensive and in-depth applications of high performance computing(HPC). The HPC applications in the emerging areas bring new challenges and opportunities at all levels of HPC, including system technological innovation, computing environment innovation, and application innovation. Based on reviewing the application progress of HPC in the emerging areas, this paper summarizes the current technical characteristics and challenges, and provides strategic recommendations for the development of emerging HPC application areas, including increasing the core technology innovation of HPC systems, building HPC environment for emerging application areas, promoting the development of HPC application software and new methods for traditional applications, as well as promoting the development of benchmarking tools in new areas such as big data and artificial intelligence.
引文
1 Reinsel D,武连峰,Gantz J F,et al.IDC:2025年中国将拥有全球最大的数据圈.Framingham:IDC,2019.
2 Libbrecht M W,Noble W S.Machine learning applications in genetics and genomics.Nature Reviews Genetics,2015,16(6):321-332.
3 Wang J X,Cao H L,Zhang J Z,et al.Computational protein design with deep learning neural networks.Scientific Reports,2018,8(1):6349.
4 Jordan J,Ippen T,Helias M,et al.Extremely scalable spiking neuronal network simulation code:from laptops to exascale computers.Frontiers in Neuroinformatics,2018,12(2):1-21.
5 Damodaran S K,Couretas J M.Cyber modeling&simulation for cyber-range events//Proceedings of the Conference on Summer Computer Simulation.San Diego:Society for Computer Simulation International,2015:1-8.
6 Erfani S M,Rajasegarar S,Karunasekera S,et al.Highdimensional and large-scale anomaly detection using a linear one-class SVM with deep learning.Pattern Recognition,2016,58:121-134.
7 McGovern A,Elmore K L,Gagne D J,et al.Using artificial intelligence to improve real-time decision-making for highimpact weather.Bulletin of the American Meteorological Society,2017,98(10):2073-2090.
8 Kurth T,Treichler S,Romero J,et al.Exascale deep learning for climate analytics//Proceedings of the International Conference for High Performance Computing,Networking,Storage,and Analysis(SC).Dallas:IEEE Press,2018:649-660.
9 Jouppi N P,Young C,Patil N,et al.In-datacenter performance analysis of a tensor processing unit//ISCA’17 Proceedings of the 44th Annual International Symposium on Computer Architecture.Toronto:IEEE Press,2017:1-12.
10 Vanderbauwhede W,Benkrid K.High-performance Computing Using FPGAs.New York:Springer,2013.
2 Libbrecht M W,Noble W S.Machine learning applications in genetics and genomics.Nature Reviews Genetics,2015,16(6):321-332.
3 Wang J X,Cao H L,Zhang J Z,et al.Computational protein design with deep learning neural networks.Scientific Reports,2018,8(1):6349.
4 Jordan J,Ippen T,Helias M,et al.Extremely scalable spiking neuronal network simulation code:from laptops to exascale computers.Frontiers in Neuroinformatics,2018,12(2):1-21.
5 Damodaran S K,Couretas J M.Cyber modeling&simulation for cyber-range events//Proceedings of the Conference on Summer Computer Simulation.San Diego:Society for Computer Simulation International,2015:1-8.
6 Erfani S M,Rajasegarar S,Karunasekera S,et al.Highdimensional and large-scale anomaly detection using a linear one-class SVM with deep learning.Pattern Recognition,2016,58:121-134.
7 McGovern A,Elmore K L,Gagne D J,et al.Using artificial intelligence to improve real-time decision-making for highimpact weather.Bulletin of the American Meteorological Society,2017,98(10):2073-2090.
8 Kurth T,Treichler S,Romero J,et al.Exascale deep learning for climate analytics//Proceedings of the International Conference for High Performance Computing,Networking,Storage,and Analysis(SC).Dallas:IEEE Press,2018:649-660.
9 Jouppi N P,Young C,Patil N,et al.In-datacenter performance analysis of a tensor processing unit//ISCA’17 Proceedings of the 44th Annual International Symposium on Computer Architecture.Toronto:IEEE Press,2017:1-12.
10 Vanderbauwhede W,Benkrid K.High-performance Computing Using FPGAs.New York:Springer,2013.