Graph Neural Networks for Charged Particle Tracking on FPGAs

TL;DR

This paper presents a workflow for converting graph neural networks into FPGA firmware to enable real-time charged particle tracking at the HL-LHC, addressing computational challenges and facilitating hardware implementation.

Contribution

It introduces an automated translation tool integrated with hls4ml for deploying GNNs on FPGAs, tailored for high-energy physics tracking tasks.

Findings

Successful implementation of GNNs on FPGAs for particle tracking

Achieved designs with different graph sizes and latency requirements

Potential for real-time trigger-level processing at HL-LHC

Abstract

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.