86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy

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 the GPU version is 7 times faster than the CPU version with 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.

arXiv comment29 pages, 11 figures

References in corpus (17)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• A flexible algorithm for calculating pair interactions on SIMD architectures
• Strong scaling of general-purpose molecular dynamics simulations on GPUs
• O(N) methods in electronic structure calculations
• Deep Potential: a general representation of a many-body potential energy surface
• Silicon liquid structure and crystal nucleation from ab-initio deep Metadynamics
• Deep neural network for the dielectric response of insulators
• Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
• Deep learning inter-atomic potential model for accurate irradiation damage simulations
• Isotope Effects in Liquid Water via Deep Potential Molecular Dynamics
• Deep Density: circumventing the Kohn-Sham equations via symmetry preserving neural networks

Cited by in corpus (34)

• DeePMD-kit v2: A software package for Deep Potential models
• A deep potential model with long-range electrostatic interactions
• Deep Potentials for Materials Science
• A practical guide to machine learning interatomic potentials -- Status and future
• Physics-Informed Neural Operator for Learning Partial Differential Equations
• Phase equilibrium of water with hexagonal and cubic ice using the SCAN functional
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Ground state energy functional with Hartree-Fock efficiency and chemical accuracy
• i-PI 3.0: a flexible and efficient framework for advanced atomistic simulations
• Unraveling the Crystallization Kinetics of the Ge${}_2$Sb${}_2$Te${}_5$ Phase Change Compound with a Machine-Learned Interatomic Potential
• Condensed Matter Systems Exposed to Radiation: Multiscale Theory, Simulations, and Experiment
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Thermal Transport by Electrons and Ions in Warm Dense Aluminum: A Combined Density Functional Theory and Deep Potential Study
• Integrating Machine Learning with Physics-Based Modeling
• Machine Learned Interatomic Potential for Dispersion Strengthened Plasma Facing Components
• Modeling the High-Pressure Solid and Liquid Phases of Tin from Deep Potentials with ab initio Accuracy
• Ab Initio Generalized Langevin Equation
• MGNN: Moment Graph Neural Network for Universal Molecular Potentials
• Improved random batch Ewald method in molecular dynamics simulations
• Combining stochastic density functional theory with deep potential molecular dynamics to study warm dense matter
• Best Practices for Fitting Machine Learning Interatomic Potentials for Molten Salts: A Case Study Using NaCl-MgCl2
• Unraveling Antagonistic Collision-Controlled Reactivity in Energetic Molecular Perovskites with Deep Potential Molecular Dynamics
• Boron adatom adsorption on graphene: A case study in computational chemistry methods for surface interactions
• Efficient force field and energy emulation through partition of permutationally equivalent atoms
• Smart-PGSim: Using Neural Network to Accelerate AC-OPF Power Grid Simulation
• Noise-Robust End-to-End Quantum Control using Deep Autoregressive Policy Networks
• A neural network potential with self-trained atomic fingerprints: a test with the mW water potential
• Shifting sands of hardware and software in exascale quantum mechanical simulations
• Deep-learning interatomic potential for irradiation damage simulations in MoS2 with ab initial accuracy
• Mapping the Structure of Oxygen-Doped Wurtzite Aluminum Nitride Coatings From Ab Initio Random Structure Search and Experiments
• Self-learning path integral hybrid Monte Carlo with mixed ab initio and machine learning potentials for modeling nuclear quantum effects in water
• On the Estimation of Centre of Mass in Periodic Systems
• Training Data Set Refinement for the Machine Learning Potential of Li-Si Alloys via Structural Similarity Analysis
• Intrinsic structure of relaxor ferroelectrics from first principles