Implementing a neural network interatomic model with performance portability for emerging exascale architectures

  title={Implementing a neural network interatomic model with performance portability for emerging exascale architectures},
  author={Saaketh Desai and Samuel Temple Reeve and J. F. Belak},
  journal={Comput. Phys. Commun.},

Figures from this paper

Machine learning for multi-fidelity scale bridging and dynamical simulations of materials

A perspective on the challenges in multi-fidelity scale bridging is provided and the developments leading up to the use of machine learning algorithms and data-science towards addressing this grand challenge are traced.

Enabling particle applications for exascale computing platforms

The Co-design Center for Particle Applications (CoPA) is addressing challenges faced by particle-based applications across four “sub-motifs”: short-range particle–particle interactions, those which often dominate molecular dynamics (MD) and smoothed particle hydrodynamics (SPH) methods, long-range particles, and linear-scaling electronic structure and quantum molecular dynamics algorithms.

Emerging materials intelligence ecosystems propelled by machine learning

The emerging materials intelligence ecosystems are reviewed and the potential of human–machine partnerships for fast and efficient virtual materials screening, development and discovery is discussed.



Library-Based LAMMPS Implementation of High-Dimensional Neural Network Potentials.

A library of functions developed for the implementation of neural network potentials within the molecular dynamics package LAMMPS is presented and its performance using liquid water as a test system is demonstrated.

Strong scaling of general-purpose molecular dynamics simulations on GPUs

Routine Microsecond Molecular Dynamics Simulations with AMBER on GPUs. 1. Generalized Born

An implementation of generalized Born implicit solvent all-atom classical molecular dynamics within the AMBER program package that runs entirely on CUDA enabled NVIDIA graphics processing units (GPUs) and shows performance that is on par with, and in some cases exceeds, that of traditional supercomputers.

Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning

A general-purpose neural network potential is trained that approaches CCSD(T)/CBS accuracy on benchmarks for reaction thermochemistry, isomerization, and drug-like molecular torsions.

High-Performance Molecular Dynamics Simulation for Biological and Materials Sciences: Challenges of Performance Portability

This work assesses key accelerating programming components of four different best-performing molecular dynamics programs-- GROMACS, NAMD, LAMMPS and CP2K-- each having a particular scope of application, for contribution to performance and for portability, and finds the contributions of the non-portable components to speed are essential to the programs' performances.

Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics

We introduce a scheme for molecular simulations, the deep potential molecular dynamics (DPMD) method, based on a many-body potential and interatomic forces generated by a carefully crafted deep