Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking

TL;DR

This paper evaluates a geometric deep learning pipeline for particle tracking at the HL-LHC, demonstrating its effectiveness, scalability, and GPU acceleration on the full TrackML dataset, marking progress towards real detector data application.

Contribution

It extends the Exa.TrkX pipeline to full dataset validation, showing comparable performance to traditional algorithms and highlighting GPU benefits for large-scale particle tracking.

Findings

Achieves similar efficiency and purity as traditional tracking algorithms.

Scales nearly linearly with the number of particles, enabling efficient large-event processing.

Significantly benefits from GPU acceleration, reducing computational time.

Abstract

The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. Exa.TrkX's tracking pipeline groups detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity Calorimeter. This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS and CMS data. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms. Crucially for future HEP applications, the pipeline benefits significantly from GPU acceleration, and its computational requirements scale close to linearly with the number of particles in the event.