hoomd-tf

Spec sheet

Purpose

HOOMD-TF is a plugin that enables TensorFlow in HOOMD-blue simulations.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Assessment tools

NoRead 23 Sep 2026 · hoomd-tf.readthedocs.io

Built-in utilities

Built-in utilities include RDF calculation, EDS biasing, and coarse-grained simulation force matching.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Early termination

It supports online machine learning with early termination during molecular dynamics simulations.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

GPU execution

The project is designed to reduce latency with GPU-to-GPU communication between GPU-accelerated HOOMD-blue and TensorFlow.Read 5 Oct 2026 · hoomd-tf.readthedocs.io

GPU performance

The project says it uses GPU-to-GPU communication to minimize latency between GPU-accelerated HOOMD-blue and TensorFlow.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

GPU setup limit

The guide warns that CUDA version mismatches between TensorFlow and HOOMD-blue can complicate GPU setup and recommends compiling HOOMD-blue for GPU use.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Integration

The documented installation requires Python, TensorFlow, and HOOMD-blue.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Known compatibility constraint

The guide says TensorFlow and HOOMD must use matching CUDA toolkit versions for GPU use, and recommends compiling HOOMD-blue for GPU mode because of CUDA version mismatches on conda.Read 5 Oct 2026 · hoomd-tf.readthedocs.io

Latest documented release

The changelog lists version 2.4, dated 2021-07-26, with the ability to compute mapped neighbor lists and positions while a simulation runs.Read 5 Oct 2026 · hoomd-tf.readthedocs.io

Lesson library

NoRead 23 Sep 2026 · hoomd-tf.readthedocs.io

License and cost

The project paper says HOOMD-TF is freely available under the MIT license on GitHub.Read 12 Oct 2026 · par.nsf.gov

Memory control

For models without molecule batching, tfcompute.attach accepts batch_size to split work into smaller batches for simulations with limited GPU memory.Read 5 Oct 2026 · hoomd-tf.readthedocs.io

Model inputs

The TensorFlow interface exposes HOOMD-blue neighbor lists and particle positions to models.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Model interface

Users build Keras models as SimModel subclasses, with particle neighbor lists, positions, and box data available as tensors.Read 5 Oct 2026 · hoomd-tf.readthedocs.io

Molecule batching

MolSimModel can arrange positions, neighbor lists, and forces by molecule, including molecules of different sizes.Read 5 Oct 2026 · hoomd-tf.readthedocs.io

Optional dependencies

MDAnalysis and NetworkX are optional; documented utility functions use them for trajectory parsing and coarse-grained graph generation.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Requirements

The compilation guide lists Python 3.6 or later, TensorFlow 2.3 or later, and HOOMD-blue 2.6.0 or later as requirements.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Support and guidance

The documentation provides a quickstart, compilation instructions, tutorials, API documentation, and a known-issues section.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Training

Models can be trained during a simulation using HOOMD-blue forces as labels, with an option to train periodically rather than every step.Read 5 Oct 2026 · hoomd-tf.readthedocs.io

Use cases

It supports online force matching, online machine learning, and collective variable calculations using TensorFlow tensor operations.Read 12 Oct 2026 · hoomd-tf.readthedocs.io

Where Specifiction places it

• Physics Simulation Software#86 of 896.7