brucefan1983/GPUMD
Graphics Processing Units Molecular Dynamics
This tool helps scientists and engineers simulate the behavior of materials at the atomic level, especially for large systems or long timescales. It takes details about a material's atomic structure and interatomic forces as input, then calculates and outputs how the atoms move and interact over time. Researchers in materials science, chemistry, and condensed matter physics can use this to understand properties like thermal conductivity or material stability.
738 stars. Actively maintained with 100 commits in the last 30 days.
Use this if you need to perform highly efficient, large-scale molecular dynamics simulations using machine-learned potentials on GPU hardware to study material properties.
Not ideal if you primarily work with CPU-only systems or require a molecular dynamics package that does not leverage GPU acceleration.
Stars
738
Forks
175
Language
Cuda
License
GPL-3.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
100
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/brucefan1983/GPUMD"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
iree-org/iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
uxlfoundation/oneDAL
oneAPI Data Analytics Library (oneDAL)
rapidsai/cuml
cuML - RAPIDS Machine Learning Library
NVIDIA/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra
NVIDIA/nccl
Optimized primitives for collective multi-GPU communication