2024/02/15 by H. Zhao, Zhao, Haoran, A. Naylor +19
Computer Science · #Computational Physics (physics.comp-ph) #Data Analysis #Distributed and Parallel Computing Systems #FOS: Physical sciences #Graph Theory and Algorithms #High Energy Physics - Experiment (hep-ex) #Neural Networks and Applications #Statistics and Probability (physics.data-an)
paper · pdf · doi:10.48550/arxiv.2402.09633
openalex publication_date 2024/02/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Recent studies have shown promising results for track finding in dense environments using Graph Neural Network (GNN)-based algorithms. However, GNN-based track finding is computationally slow on CPUs, necessitating the use of coprocessors to accelerate the inference time. Additionally, the large input graph size demands a large device memory for efficient computation, a requirement not met by all computing facilities used for particle physics experiments, particularly those lacking advanced GPUs. Furthermore, deploying the GNN-based track-finding algorithm in a production environment requires the installation of all dependent software packages, exclusively utilized by this algorithm. These computing challenges must be addressed for the successful implementation of GNN-based track-finding algorithm into production settings. In response, we introduce a ``GNN-based tracking as a service'' approach, incorporating a custom backend within the NVIDIA Triton inference server to facilitate GNN-based tracking. This paper presents the performance of this approach using the Perlmutter supercomputer at NERSC.