Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs

2020/11/30 by Heintz, Aneesh, Razavimaleki, Vesal, Duarte, Javier +18
#Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Physical sciences #High Energy Physics - Experiment (hep-ex) #Instrumentation and Detectors (physics.ins-det) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2012.01563

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.

Related

• Real-Time Analysis of Unstructured Data with Machine Learning on Heterogeneous Architectures
• Charged Particle Tracking with Machine Learning on FPGAs
• Low Latency Edge Classification GNN for Particle Trajectory Tracking on FPGAs
• Low Latency Neural Networks using Heterogenous Resources on FPGA for the Belle II Trigger
• Geometric GNNs for Charged Particle Tracking at GlueX