Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs

Abstract

We develop and study FPGA implementations of algorithms for charged particle tracking based on graph neural networks. The two complementary FPGA designs are based on OpenCL, a framework for writing programs that execute across heterogeneous platforms, and hls4ml, a high-level-synthesis-based compiler for neural network to firmware conversion. We evaluate and compare the resource usage, latency, and tracking performance of our implementations based on a benchmark dataset. We find a considerable speedup over CPU-based execution is possible, potentially enabling such algorithms to be used effectively in future computing workflows and the FPGA-based Level-1 trigger at the CERN Large Hadron Collider.

arXiv comment8 pages, 4 figures, To appear in Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020)

References in corpus (9)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Description and performance of track and primary-vertex reconstruction with the CMS tracker
• Interaction Networks for Learning about Objects, Relations and Physics
• Performance of the CMS Level-1 trigger in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Performance of the ATLAS Track Reconstruction Algorithms in Dense Environments in LHC Run 2
• Operation of the ATLAS trigger system in Run 2
• Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
• The Tracking Machine Learning challenge : Accuracy phase
• Novel deep learning methods for track reconstruction

Cited by in corpus (14)

• Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
• Applications and Techniques for Fast Machine Learning in Science
• Charged particle tracking via edge-classifying interaction networks
• Graph Neural Networks for Charged Particle Tracking on FPGAs
• Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
• Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics
• Real-time Artificial Intelligence for Accelerator Control: A Study at the Fermilab Booster
• Accelerating Graph-based Tracking Tasks with Symbolic Regression
• Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking
• Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
• BitHEP -- The Limits of Low-Precision ML in HEP
• TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Era