GPU-accelerated machine learning inference as a service for computing in neutrino experiments

Abstract

Machine learning algorithms are becoming increasingly prevalent and performant in the reconstruction of events in accelerator-based neutrino experiments. These sophisticated algorithms can be computationally expensive. At the same time, the data volumes of such experiments are rapidly increasing. The demand to process billions of neutrino events with many machine learning algorithm inferences creates a computing challenge. We explore a computing model in which heterogeneous computing with GPU coprocessors is made available as a web service. The coprocessors can be efficiently and elastically deployed to provide the right amount of computing for a given processing task. With our approach, Services for Optimized Network Inference on Coprocessors (SONIC), we integrate GPU acceleration specifically for the ProtoDUNE-SP reconstruction chain without disrupting the native computing workflow. With our integrated framework, we accelerate the most time-consuming task, track and particle shower hit identification, by a factor of 17. This results in a factor of 2.7 reduction in the total processing time when compared with CPU-only production. For this particular task, only 1 GPU is required for every 68 CPU threads, providing a cost-effective solution.

15 pages, 7 figures, 2 tables

References in corpus (18)

• Design and Construction of the MicroBooNE Detector
• Supernova Neutrino Detection
• CP Violation and Neutrino Oscillations
• A Convolutional Neural Network Neutrino Event Classifier
• IceCube: An Instrument for Neutrino Astronomy
• DUNE as the Next-Generation Solar Neutrino Experiment
• First results on ProtoDUNE-SP liquid argon time projection chamber performance from a beam test at the CERN Neutrino Platform
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Neutrino Mass Hierarchy
• Allen: A high level trigger on GPUs for LHCb
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• FPGA-accelerated machine learning inference as a service for particle physics computing
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• Scalable Deep Convolutional Neural Networks for Sparse, Locally Dense Liquid Argon Time Projection Chamber Data
• Bringing heterogeneity to the CMS software framework
• GPU-based reconstruction and data compression at ALICE during LHC Run 3
• Running a Pre-Exascale, Geographically Distributed, Multi-Cloud Scientific Simulation
• Underground physics with DUNE

Cited by in corpus (7)

• Applications and Techniques for Fast Machine Learning in Science
• Charged particle tracking via edge-classifying interaction networks
• GPU coprocessors as a service for deep learning inference in high energy physics
• Separation of track- and shower-like energy deposits in ProtoDUNE-SP using a convolutional neural network
• Accelerating Machine Learning Inference with GPUs in ProtoDUNE Data Processing
• Portable acceleration of CMS computing workflows with coprocessors as a service
• SuperSONIC: Cloud-Native Infrastructure for ML Inferencing