Physics and Computing Performance of the Exa.TrkX TrackML Pipeline
Authors: Xiangyang Ju (Lawrence Berkeley National Laboratory), Daniel Murnane (Lawrence Berkeley National Laboratory), Paolo Calafiura (Lawrence Berkeley National Laboratory), Nicholas Choma (Lawrence Berkeley National Laboratory), Sean Conlon (Lawrence Berkeley National Laboratory), Steve Farrell (Lawrence Berkeley National Laboratory), Yaoyuan Xu (Lawrence Berkeley National Laboratory), Maria Spiropulu (California Institute of Technology), Jean-Roch Vlimant (California Institute of Technology), Adam Aurisano (University of Cincinnati), V Hewes (University of Cincinnati), Giuseppe Cerati (Fermi National Accelerator Laboratory), Lindsey Gray (Fermi National Accelerator Laboratory), Thomas Klijnsma (Fermi National Accelerator Laboratory), Jim Kowalkowski (Fermi National Accelerator Laboratory), Markus Atkinson (University of Illinois at Urbana-Champaign), Mark Neubauer (University of Illinois at Urbana-Champaign), Gage DeZoort (Princeton University), Savannah Thais (Princeton University), Aditi Chauhan (University of Washington), Alex Schuy (University of Washington), Shih-Chieh Hsu (University of Washington), Alex Ballow (Youngstown State University), and Alina Lazar (Youngstown State University)
Abstract: The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. The Exa.TrkX tracking pipeline clusters detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-like tracking detector), has been demonstrated on various detectors, including the DUNE LArTPC and the 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.
Explore the paper tree
Click on the tree nodes to be redirected to a given paper and access their summaries and virtual assistant
Look for similar papers (in beta version)
By clicking on the button above, our algorithm will scan all papers in our database to find the closest based on the contents of the full papers and not just on metadata. Please note that it only works for papers that we have generated summaries for and you can rerun it from time to time to get a more accurate result while our database grows.