谭光明,贾伟乐,王展,元国军,邵恩,孙凝晖*.面向模拟智能的计算系统[J].中国科学院院刊,2024,39(1):17-26.

面向模拟智能的计算系统

Computing system for simulation intelligence

谭光明
中国科学院计算技术研究所 北京 100190
TAN Guangming
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
贾伟乐
中国科学院计算技术研究所 北京 100190
JIA Weile
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
王展
中国科学院计算技术研究所 北京 100190
WANG Zhan
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
元国军
中国科学院计算技术研究所 北京 100190
YUAN Guojun
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
邵恩
中国科学院计算技术研究所 北京 100190
SHAO En
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
孙凝晖*
中国科学院计算技术研究所 北京 100190
SUN Ninghui*
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China

         科学模拟;模拟智能;人工智能;计算系统;Z级计算

        scientific simulation;simulation intelligence;artificial intelligence;computing system;Zetta-scale computing

        科学研究中的计算机模拟称为科学模拟（scientific simulation），文章从其狭义和广义层面出发，把科学模拟分为数值计算（numerical computation）、模拟智能（simulation intelligence）和科学大脑（sciencebrain） 3个阶段，并描述了各阶段的特征。目前，科学模拟正在进入模拟智能阶段，即在科学大数据和人工智能的驱动下，科学模拟正从传统的数值计算逐步转向与人工智能相融合的模拟方式。文章针对支撑模拟智能阶段的计算系统展开讨论，阐述了其设计指导思想、基本方法和关键技术等问题。

        This study refers computer simulation in scientific research to as scientific simulation. Based on its narrow and broad definitions, this study divides scientific simulation into three stages: numerical computation, simulation intelligence, and science brain. Now, scientific simulation is entering the era of simulation intelligence, i. e., driven by scientific big data and artificial intelligence technology, scientific simulation is shifting from traditional numerical simulation to simulation integrated with artificial intelligence. In order to understand what the right computing system for simulation intelligence is, the design guidelines, basic methods, and key technical problems are discussed.