Graph Neural Networks for Charged Particle Tracking on FPGAs

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 $\text{hls4ml}$, 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.

arXiv comment28 pages, 17 figures, 1 table, published version

References in corpus (28)

• Adam: A Method for Stochastic Optimization
• Array Programming with NumPy
• Description and performance of track and primary-vertex reconstruction with the CMS tracker
• Fast inference of deep neural networks in FPGAs for particle physics
• ParticleNet: Jet Tagging via Particle Clouds
• Performance of the CMS Level-1 trigger in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
• Graph Neural Networks in Particle Physics
• Performance of the ATLAS Track Reconstruction Algorithms in Dense Environments in LHC Run 2
• Operation of the ATLAS trigger system in Run 2
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Fast convolutional neural networks on FPGAs with hls4ml
• JEDI-net: a jet identification algorithm based on interaction networks
• GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms
• Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML
• Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
• Fast inference of Boosted Decision Trees in FPGAs for particle physics
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• The Tracking Machine Learning challenge : Accuracy phase
• Charged particle tracking via edge-classifying interaction networks
• Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference
• Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics
• Graph Neural Networks for Particle Tracking and Reconstruction
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• Graph Processing on FPGAs: Taxonomy, Survey, Challenges
• Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs
• GRIP: A Graph Neural Network Accelerator Architecture

Cited by in corpus (9)

• The Tracking Machine Learning challenge : Throughput phase
• LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics
• GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization
• Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics
• Real-time Graph Building on FPGAs for Machine Learning Trigger Applications in Particle Physics
• Accelerating Graph-based Tracking Tasks with Symbolic Regression
• Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks
• BitHEP -- The Limits of Low-Precision ML in HEP
• TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Era