Graph Neural Networks for Charged Particle Tracking on FPGAs
This work addresses the computational bottleneck for deploying GNNs in real-time particle tracking at the HL-LHC, representing an incremental advancement in hardware acceleration for domain-specific applications.
The paper tackles the challenge of implementing graph neural networks (GNNs) for charged particle tracking in high-luminosity LHC conditions by developing an automated workflow to convert GNNs into FPGA firmware, enabling their use in trigger-level applications with designs targeting various graph sizes and latency requirements.
The determination of charged particle trajectories in collisions at the CERN Large Hadron Collider (LHC) is an important but challenging problem, especially in the high interaction density conditions expected during the future high-luminosity phase of the LHC (HL-LHC). Graph neural networks (GNNs) are a type of geometric deep learning algorithm that has successfully been applied to this task by embedding tracker data as a graph -- nodes represent hits, while edges represent possible track segments -- and classifying the edges as true or fake track segments. However, their study in hardware- or software-based trigger applications has been limited due to their large computational cost. In this paper, we introduce an automated translation workflow, integrated into a broader tool called $\texttt{hls4ml}$, for converting GNNs into firmware for field-programmable gate arrays (FPGAs). We use this translation tool to implement GNNs for charged particle tracking, trained using the TrackML challenge dataset, on FPGAs with designs targeting different graph sizes, task complexites, and latency/throughput requirements. This work could enable the inclusion of charged particle tracking GNNs at the trigger level for HL-LHC experiments.