Paper
Characterizing Machine Learning Force Fields as Emerging Molecular Dynamics Workloads on Graphics Processing Units
Authors
Udari De Alwis, Benjamin E. Mayer, Tom J. Ashby, Maria Barrera, Timon Evenblij, Joyjit Kundu
Abstract
Molecular dynamics (MD) simulates the time evolution of atomic systems governed by interatomic forces, and the fidelity of these simulations depends critically on the underlying force model. Classical force fields (CFFs) rely on fixed functional forms fitted to experimental or theoretical data, offering computational efficiency and broad applicability but limited accuracy in chemically diverse or reactive environments. In contrast, machine learning force fields (MLFFs) deliver near quantum chemical accuracy at molecular-mechanics cost by learning interatomic interactions directly from high level electronic structure data. While MLFFs offer improved accuracy at a fraction of the cost of quantum methods, they introduce significant computational overhead, particularly in descriptor evaluation and neural network inference. These operations pose challenges for parallel hardware due to irregular memory access, minimum data reuse and inefficient kernel execution. This work investigates the hardware performance of such models using poly alanine chains, a novel benchmark molecule system(s) with controllable input size, which used as performance evaluation test cases highlighting the computational bottlenecks of the graphical processor units when scaling out MLFF simulations. The analysis identifies key bottlenecks in descriptor and force computation, memory handling, highlighting the opportunities for improvements in the emerging area of MLFF based MD in drug discovery, that has received limited attention from a computer architecture perspective.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.04092v1</id>\n <title>Characterizing Machine Learning Force Fields as Emerging Molecular Dynamics Workloads on Graphics Processing Units</title>\n <updated>2026-03-04T14:02:56Z</updated>\n <link href='https://arxiv.org/abs/2603.04092v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.04092v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Molecular dynamics (MD) simulates the time evolution of atomic systems governed by interatomic forces, and the fidelity of these simulations depends critically on the underlying force model. Classical force fields (CFFs) rely on fixed functional forms fitted to experimental or theoretical data, offering computational efficiency and broad applicability but limited accuracy in chemically diverse or reactive environments. In contrast, machine learning force fields (MLFFs) deliver near quantum chemical accuracy at molecular-mechanics cost by learning interatomic interactions directly from high level electronic structure data. While MLFFs offer improved accuracy at a fraction of the cost of quantum methods, they introduce significant computational overhead, particularly in descriptor evaluation and neural network inference. These operations pose challenges for parallel hardware due to irregular memory access, minimum data reuse and inefficient kernel execution. This work investigates the hardware performance of such models using poly alanine chains, a novel benchmark molecule system(s) with controllable input size, which used as performance evaluation test cases highlighting the computational bottlenecks of the graphical processor units when scaling out MLFF simulations. The analysis identifies key bottlenecks in descriptor and force computation, memory handling, highlighting the opportunities for improvements in the emerging area of MLFF based MD in drug discovery, that has received limited attention from a computer architecture perspective.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.PF'/>\n <published>2026-03-04T14:02:56Z</published>\n <arxiv:comment>Accepted to IEEE ISPASS - 2026</arxiv:comment>\n <arxiv:primary_category term='cs.PF'/>\n <author>\n <name>Udari De Alwis</name>\n </author>\n <author>\n <name>Benjamin E. Mayer</name>\n </author>\n <author>\n <name>Tom J. Ashby</name>\n </author>\n <author>\n <name>Maria Barrera</name>\n </author>\n <author>\n <name>Timon Evenblij</name>\n </author>\n <author>\n <name>Joyjit Kundu</name>\n </author>\n </entry>"
}