Geometric GNNs for Charged Particle Tracking at GlueX

TL;DR

This paper demonstrates that Graph Neural Networks can effectively and efficiently improve charged particle tracking in nuclear physics experiments like GlueX, outperforming traditional methods in accuracy and speed, and explores hardware implementation trade-offs.

Contribution

The study introduces a GNN-based approach for particle track finding in high-energy physics, showing superior performance and speed over traditional algorithms, and compares GPU and FPGA implementations.

Findings

GNN outperforms traditional track finding methods in efficiency and speed.

Batch processing on GPUs significantly accelerates inference.

GPU and FPGA implementations present different trade-offs in performance and resource use.

Abstract

Nuclear physics experiments are aimed at uncovering the fundamental building blocks of matter. The experiments involve high-energy collisions that produce complex events with many particle trajectories. Tracking charged particles resulting from collisions in the presence of a strong magnetic field is critical to enable the reconstruction of particle trajectories and precise determination of interactions. It is traditionally achieved through combinatorial approaches that scale worse than linearly as the number of hits grows. Since particle hit data naturally form a 3-dimensional point cloud and can be structured as graphs, Graph Neural Networks (GNNs) emerge as an intuitive and effective choice for this task. In this study, we evaluate the GNN model for track finding on the data from the GlueX experiment at Jefferson Lab. We use simulation data to train the model and test on both simulation and real GlueX measurements. We demonstrate that GNN-based track finding outperforms the currently used traditional method at GlueX in terms of segment-based efficiency at a fixed purity while providing faster inferences. We show that the GNN model can achieve significant speedup by processing multiple events in batches, which exploits the parallel computation capability of Graphical Processing Units (GPUs). Finally, we compare the GNN implementation on GPU and FPGA and describe the trade-off.