GPUMDkit

A Toolkit for GPUMD & NEP

GPUMDkit is a toolkit for the GPUMD (Graphics Processing Units Molecular Dynamics) and NEP (neuroevolution potential) program. It provides a set of tools to streamline the use of common scripts in GPUMD and NEP, simplifying workflows and enhancing efficiency.

Get Started

Key Features

Script Invocation

Easily run scripts for GPUMD and NEP

Workflow Automation

Automate common tasks to save time and reduce manual intervention

User-Friendly Interface

Intuitive shell commands designed to enhance user experience

Analysis Tools

Comprehensive tools for analyzing simulation results

Quick Start


# Clone the repository
git clone https://github.com/zhyan0603/GPUMDkit.git

# Set environment variables
export GPUMD_path=/your_dir_of_GPUMD
export GPUMDkit_path=/your_dir_of_GPUMDkit
export PATH=${GPUMDkit_path}:${PATH}
source ${GPUMDkit_path}/Scripts/utils/completion.sh

# Make script executable and run
chmod +x gpumdkit.sh
gpumdkit.sh

Documentation

Format Conversion

Convert between various formats

Read More >

Sample Structures

Sample structures by various methods

Read More >

Workflow

Workflows for active-learning iterations

Read More >

Calculators

Calculate various properties of your system

Read More >

Publications

Impact of Lithium Nonstoichiometry on Ionic Diffusion in Tetragonal Garnet-Type Li7La3Zr2O12

Zihan Yan, Yizhou Zhu
Chem. Mater. 2024, 36, 23, 11551–11557
Read

Improving robustness and training efficiency of machine-learned potentials by incorporating short-range empirical potentials

Zihan Yan, Zheyong Fan, Yizhou Zhu
arXiv:2504.15925
Read

Join Us & Citation

Contribute Code

Help improve GPUMDkit by contributing Python/Shell scripts through Pull Requests.

Submit PR

Contact Us

Have questions or suggestions? Feel free to reach out to us via email.

Send Email

Citation

As of now, GPUMDkit is a toy model, free for anyone to use and experiment with. If you like it, please star us on GitHub.

Star on GitHub