Abstract We present the GPU version of DeePMD-kit, which, upon training a deep neural network model using ab initio data, can drive extremely large-scale molecular dynamics (MD) simulation with ab initio accuracy. Our tests show that for a water system of 12 , 582 , 912 atoms, the GPU version can be 7 times faster than the CPU version under the same power consumption. The code can scale up to the entire Summit supercomputer. For a copper system of 113 , 246 , 208 atoms, the code can perform one nanosecond MD simulation per day, reaching a peak performance of 86 PFLOPS (43% of the peak). Such unprecedented ability to perform MD simulation with ab initio accuracy opens up the possibility of studying many important issues in materials and molecules, such as heterogeneous catalysis, electrochemical cells, irradiation damage, crack propagation, and biochemical reactions. Program summary Program Title: DeePMD-kit CPC Library link to program files: https://doi.org/10.17632/phyn4kgsfx.1 Developer’s repository link: https://doi.org/10.5281/zenodo.3961106 Licensing provisions: LGPL Programming language: C++/Python/CUDA Journal reference of previous version: Comput. Phys. Commun. 228 (2018), 178–184. Does the new version supersede the previous version?: Yes. Reasons for the new version: Parallelize and optimize the DeePMD-kit for modern high performance computers. Summary of revisions: The optimized DeePMD-kit is capable of computing 100 million atoms molecular dynamics with ab initio accuracy, achieving 86 PFLOPS in double precision. Nature of problem: Modeling the many-body atomic interactions by deep neural network models. Running molecular dynamics simulations with the models. Solution method: The Deep Potential for Molecular Dynamics (DeePMD) method is implemented based on the deep learning framework TensorFlow. Standard and customized TensorFlow operators are optimized for GPU. Massively parallel molecular dynamics simulations with DeePMD models on high performance computers are supported in the new version.

中文翻译：

---

1 亿个原子的 86 PFLOPS 深位势分子动力学模拟，具有从头算精度

摘要 我们提出了 GPU 版本的 DeePMD-kit，它在使用 ab initio 数据训练深度神经网络模型后，可以以 ab initio 精度驱动超大规模分子动力学 (MD) 模拟。我们的测试表明，对于 12 、 582 、 912 个原子的水系统，在相同功耗下，GPU 版本可以比 CPU 版本快 7 倍。该代码可以扩展到整个 Summit 超级计算机。对于 113、246、208 个原子的铜系统，该代码每天可以执行 1 纳秒 MD 模拟，达到 86 PFLOPS 的峰值性能（峰值的 43%）。这种以从头算精度执行 MD 模拟的前所未有的能力开辟了研究材料和分子中许多重要问题的可能性，例如多相催化、电化学电池、辐射损伤、裂纹扩展、和生化反应。程序摘要 程序名称：DeePMD-kit CPC 库程序文件链接：https://doi.org/10.17632/phyn4kgsfx.1 开发者存储库链接：https://doi.org/10.5281/zenodo.3961106 许可条款：LGPL 编程语言：C++/Python/CUDA 上一版本期刊参考：Comput. 物理。社区。228 (2018), 178–184。新版本是否取代以前的版本？：是的。新版本的原因：为现代高性能计算机并行化和优化 DeePMD 套件。修订摘要：优化后的 DeePMD-kit 能够从头算精度计算 1 亿个原子的分子动力学，双精度达到 86 PFLOPS。问题性质：通过深度神经网络模型对多体原子相互作用进行建模。使用模型运行分子动力学模拟。解决方法：Deep Potential for Molecular Dynamics（DeePMD）方法是基于深度学习框架TensorFlow实现的。标准和定制的 TensorFlow 运算符针对 GPU 进行了优化。新版本支持在高性能计算机上使用 DeePMD 模型进行大规模并行分子动力学模拟。