Characterizing Machine Learning Force Fields as Emerging Molecular Dynamics Workloads on Graphics Processing Units

TL;DR

This paper analyzes the computational performance of machine learning force fields in molecular dynamics on GPUs, identifying bottlenecks and opportunities for hardware optimization to advance drug discovery applications.

Contribution

It provides a detailed performance characterization of MLFFs on GPUs using novel benchmark molecules, highlighting specific computational bottlenecks and guiding future hardware improvements.

Findings

Descriptor and force computation are key bottlenecks.

Memory handling issues limit GPU efficiency.

Opportunities exist for hardware optimization in MLFF MD simulations.

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.