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

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. Th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-03
Main Authors: Wang, Michael, Yang, Tingjun, Maria Acosta Flechas, Harris, Philip, Hawks, Benjamin, Holzman, Burt, Knoepfel, Kyle, Krupa, Jeffrey, Pedro, Kevin, Tran, Nhan
Format: Article
Language:English
Subjects:
Algorithms
Central processing units
Coprocessors
CPUs
Experiments
Graphics processing units
Inference
Machine learning
Neutrinos
Reconstruction
Web services
Workflow
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2009.04509