Moving from exascale to zettascale computing:challenges and techniques  

从E级计算到Z级计算的新挑战与新技术（英文）

作　　者：Xiang-ke LIAO Kai LU Can-qun YANG Jin-wen LI Yuan YUAN Ming-che LAI Li-bo HUANG Ping-jing LU Jian-bin FANG Jing REN Jie SHEN 

机构地区：[1]College of Computer,National University of Defense Technology

出　　处：《Frontiers of Information Technology & Electronic Engineering》2018年第10期1236-1244,共9页信息与电子工程前沿（英文版）

基　　金：Project supported by the National Key Technology R&D Program of China(No.2016YFB0200401)

摘　　要：ttigh-performance computing （HPC） is essential for both traditional and emerging scientific fields, enabling scientific activities to make progress. With the development of high-performance computing, it is foreseeable that exascale computing will be put into practice around 2020. As Moore＇s law approaches its limit, high-perfornlance computing will face severe challenges when moving from exaseale to zettascale, making tile next 10 years after 2020 a vital period to develop key HPC techniques. In this study, we discuss the challenges of enabling zettascale computing with respect to both hardware and software. We then present a perspective of fllture HPC technology evolution and revolution, leading to our main recommendations in support of zettaseale computing in the coming future.高性能计算已成为促进传统与新兴领域科技创新取得进展的基础设施。随着高性能计算的发展,E级系统(每秒1018次浮点运算)预计2020年前后投入使用。实现E级计算后的10年(2020–2030)将成为E级计算向Z级计算(每秒1021次浮点运算)过渡的关键时期,计算能力提升将面临前所未有的挑战。从硬件和软件方面分析未来高性能计算的挑战,展望后E级计算时代的技术发展与革新,并提出未来实现E级计算向Z级计算过渡的可行性建议。

关 键 词：High-performance COMPUTING Zettascale Micro-architectures INTERCONNECTION Storage system Manufacturing process PROGRAMMING models and environments 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]