TorchFF: A high-performance GPU-accelerated differentiable force field library
The Journal of Chemical Physics · 28.07.2026 · 165 (4)
DOI: 10.1063/5.0339981 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 28.07.2026. Verfasst von Yingze Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Kenneth S. Pitzer Theory Center and Department of Chemistry, Berkeley, California 94720, USA. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Molecular dynamics (MD) and the development of next-generation force fields increasingly rely on automatic differentiation for efficient simulated property prediction and parameter optimization. However, standard FFs and machine learning frameworks often suffer from significant performance bottlenecks—such as kernel launch overhead and memory bandwidth limitations—when executing the many-atom, small-kernel operations characteristic of MD simulations. Here, we present TorchFF, a high-performance, differentiable library that extends PyTorch with a suite of customized CUDA operators specifically engineered for molecular modeling. By implementing performance-critical routines—including bonded interactions, multipolar electrostatics, particle mesh Ewald, and neighbor list searches—as backend-optimized primitives, TorchFF bridges the gap between the flexible Python ecosystem and the execution speed of compiled MD engines.
Autor:innen und Institutionen
- Kenneth S. Pitzer Theory Center and Department of Chemistry, Berkeley, California 94720, USA.
- Department of Materials Science and Engineering, University of California, Berkeley, California 94720, USA.
- Department of Bioengineering, Berkeley, California 94720, USA.
- Department of Chemical and Biomolecular Engineering, University of California, Berkeley, California 94720, USA.
ORCID-Profile: Yingze Wang, Aalim S Abdullah, Rohith Srinivaas Mohanakrishnan, Teresa Head-Gordon
Förderung
- National Science Foundation
Zitieren
APA
Wang, Y., Abdullah, A. S., Mohanakrishnan, R. S., & Head-Gordon, T. (2026). TorchFF: A high-performance GPU-accelerated differentiable force field library. The Journal of Chemical Physics, 165(4). https://doi.org/10.1063/5.0339981
Vancouver
Wang Y, Abdullah AS, Mohanakrishnan RS, Head-Gordon T. TorchFF: A high-performance GPU-accelerated differentiable force field library. The Journal of Chemical Physics. 2026;165(4). doi:10.1063/5.0339981
BibTeX
@article{Wang2026,
author = {Wang, Yingze and Abdullah, Aalim S and Mohanakrishnan, Rohith Srinivaas and Head-Gordon, Teresa},
title = {TorchFF: A high-performance GPU-accelerated differentiable force field library},
journal = {The Journal of Chemical Physics},
year = {2026},
volume = {165},
number = {4},
doi = {10.1063/5.0339981}
}
EUVIMED