- Home
- Physics Simulation Software
- hoomd-tf
On the recordRead 12 Oct 202621 facts
hoomd-tf
On the record
- Assessment tools
- Nohoomd-tf.readthedocs.io · read 23 Sep 2026
- Built-in utilities
- Built-in utilities include RDF calculation, EDS biasing, and coarse-grained simulation force matching.hoomd-tf.readthedocs.io · read 12 Oct 2026
- Early termination
- It supports online machine learning with early termination during molecular dynamics simulations.hoomd-tf.readthedocs.io · read 12 Oct 2026
- GPU execution
- The project is designed to reduce latency with GPU-to-GPU communication between GPU-accelerated HOOMD-blue and TensorFlow.hoomd-tf.readthedocs.io · read 5 Oct 2026
- GPU performance
- The project says it uses GPU-to-GPU communication to minimize latency between GPU-accelerated HOOMD-blue and TensorFlow.hoomd-tf.readthedocs.io · read 12 Oct 2026
- 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.hoomd-tf.readthedocs.io · read 12 Oct 2026
- Integration
- The documented installation requires Python, TensorFlow, and HOOMD-blue.hoomd-tf.readthedocs.io · read 12 Oct 2026
- 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.hoomd-tf.readthedocs.io · read 5 Oct 2026
- 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.hoomd-tf.readthedocs.io · read 5 Oct 2026
- Lesson library
- Nohoomd-tf.readthedocs.io · read 23 Sep 2026
- License and cost
- The project paper says HOOMD-TF is freely available under the MIT license on GitHub.par.nsf.gov · read 12 Oct 2026
- Memory control
- For models without molecule batching, tfcompute.attach accepts batch_size to split work into smaller batches for simulations with limited GPU memory.hoomd-tf.readthedocs.io · read 5 Oct 2026
- Model inputs
- The TensorFlow interface exposes HOOMD-blue neighbor lists and particle positions to models.hoomd-tf.readthedocs.io · read 12 Oct 2026
- Model interface
- Users build Keras models as SimModel subclasses, with particle neighbor lists, positions, and box data available as tensors.hoomd-tf.readthedocs.io · read 5 Oct 2026
- Molecule batching
- MolSimModel can arrange positions, neighbor lists, and forces by molecule, including molecules of different sizes.hoomd-tf.readthedocs.io · read 5 Oct 2026
- Optional dependencies
- MDAnalysis and NetworkX are optional; documented utility functions use them for trajectory parsing and coarse-grained graph generation.hoomd-tf.readthedocs.io · read 12 Oct 2026
- Purpose
- HOOMD-TF is a plugin that enables TensorFlow in HOOMD-blue simulations.hoomd-tf.readthedocs.io · read 12 Oct 2026
- 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.hoomd-tf.readthedocs.io · read 12 Oct 2026
