35年来，{\it ab initio}分子动力学（AIMD）一直是从第一原理建模复杂原子现象的首选方法。然而，大多数有源植入式医疗器械的应用受到计算成本的限制，最多有数千个原子的系统。我们报告说，基于机器学习的模拟协议（深势分子动力学），同时保留{\it从头算}的准确性，可以模拟超过1纳秒长的轨迹超过1亿个原子每天，使用高度优化的代码（GPU DeePMD套件）的首脑会议超级计算机。我们的代码可以有效地扩展到整个首脑会议的超级计算机，获得$91$ PFLOPS在双精度（$45.5\%$的峰值）和{$162$/$275$ PFLOPS在混合单/半精度}。这项工作的巨大成就是，它打开了大门，模拟前所未有的规模和时间尺度与{\it从头}精度。它也为下一代超级计算机更好地集成机器学习和物理建模提出了新的挑战。
英文摘要：
For 35 years, {\it ab initio} molecular dynamics (AIMD) has been the method of choice for modeling complex atomistic phenomena from first principles. However, most AIMD applications are limited by computational cost to systems with thousands of atoms at most. We report that a machine learning-based simulation protocol (Deep Potential Molecular Dynamics), while retaining {\it ab initio} accuracy, can simulate more than 1 nanosecond-long trajectory of over 100 million atoms per day, using a highly optimized code (GPU DeePMD-kit) on the Summit supercomputer. Our code can efficiently scale up to the entire Summit supercomputer, attaining $91$ PFLOPS in double precision ($45.5\%$ of the peak) and {$162$/$275$ PFLOPS in mixed-single/half precision}. The great accomplishment of this work is that it opens the door to simulating unprecedented size and time scales with {\it ab initio} accuracy. It also poses new challenges to the next-generation supercomputer for a better integration of machine learning and physical modeling.
DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution
Peking University（北京大学）；AI for Science Institute（人工智能科学研究院）；Tsinghua University（清华大学）；HEDPS, CAPT, College of Engineering, Peking University（北京大学工学院理论力学与计算力学系、高超声速空气动力学国家重点实验室）；DP Technology（深势科技）；Academy for Advanced Interdisciplinary Studies, Peking University（北京大学前沿交叉学科研究院）；National Key Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics（中国科学院应用物理与计算数学研究所）
Extreme-Scale Linear-Scaling Kohn-Sham DFT at 100 Million Atoms: Bridging Quantum Simulations and Experiments
National Supercomputing Center in Shenzhen, Guangdong, China（深圳国家超级计算中心）；Peking University Shenzhen Graduate School, Guangdong, China（北京大学深圳研究生院）；Sun Yat-sen University, Guangdong, China（中山大学）；National Supercomputing Center in Wuxi, Jiangsu, China（无锡国家超级计算中心）；Tsinghua University, Beijing, China（清华大学）；ETH Zurich, Zurich, Switzerland（苏黎世联邦理工学院）；Tsinghua Shenzhen International Graduate School, Guangdong, China（清华大学深圳国际研究生院）
GPU-MetaD: Full-Life-Cycle GPU Accelerated Metadynamics with Machine Learning Potentials
National Laboratory of Solid State Microstructures, School of Physics and Collaborative Innovation Center of Advanced Microstructures, Nanjing University（南京大学固体微结构物理国家重点实验室、物理学院和先进微结构协同创新中心）；College of Physical Science and Technology, Bohai University（渤海大学物理科学与技术学院）
