论文标题
通过机器学习将分子动力学的极限以1亿个原子推向1亿个原子
Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning
论文作者
论文摘要
35年来，{\ it by Itif}分子动力学（AIMD）一直是对第一原理对复杂原子现象进行建模的选择方法。但是，大多数AIMD应用程序受到数千原子的系统的计算成本的限制。我们报告说，基于机器学习的模拟协议（深度潜在的分子动力学），同时保留{\ it i n od ost}精度，可以使用高度优化的代码（GPU DEEPMD-kit）在summit超级计算机上模拟每天超过1亿原子的1纳秒长轨迹。我们的代码可以有效地扩展到整个Summit SuperCuputer，以双重精度达到$ 91 $ PFLOPS（$ 45.5 \％的峰值）和{$ 162 $/$ 275 $ 275 $ pflops in Myfer-Single/Half Precision}。这项工作的最大成就是，它打开了以{\ it It ob selive}精度模拟前所未有的大小和时间尺度的大门。它还为下一代超级计算机带来了新的挑战，以更好地整合机器学习和物理建模。
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.
