An official website of the United States government
Abstract Computing demands for large scientific experiments, such as the CMS experiment at the CERN LHC, will increase dramatically in the next decades. To complement the future performance increases of software running on central processing units (CPUs), explorations of coprocessor usage in data processing hold great potential and interest. Coprocessors are a class of computer processors that supplement CPUs, often improving the execution of certain functions due to architectural design choices. We explore the approach of Services for Optimized Network Inference on Coprocessors (SONIC) and study the deployment of this as-a-service approach in large-scale data processing. In the studies, we take a data processing workflow of the CMS experiment and run the main workflow on CPUs, while offloading several machine learning (ML) inference tasks onto either remote or local coprocessors, specifically graphics processing units (GPUs). With experiments performed at Google Cloud, the Purdue Tier-2 computing center, and combinations of the two, we demonstrate the acceleration of these ML algorithms individually on coprocessors and the corresponding throughput improvement for the entire workflow. This approach can be easily generalized to different types of coprocessors and deployed on local CPUs without decreasing the throughput performance. We emphasize that the SONIC approach enables high coprocessor usage and enables the portability to run workflows on different types of coprocessors.
more »
« less
This content will become publicly available on July 18, 2026
SuperSONIC: Cloud-Native Infrastructure for ML Inferencing
The increasing computational demand from growing data rates and complex machine learning (ML) algorithms in large-scale scientific experiments has driven the adoption of the Services for Optimized Network Inference on Coprocessors (SONIC) approach. SONIC accelerates ML inference by offloading it to local or remote coprocessors to optimize resource utilization. Leveraging its portability to different types of coprocessors, SONIC enhances data processing and model deployment efficiency for cutting-edge research in high energy physics (HEP) and multi-messenger astrophysics (MMA). We developed the SuperSONIC project, a scalable server infrastructure for SONIC, enabling the deployment of computationally intensive tasks to Kubernetes clusters equipped with graphics processing units (GPUs). Using NVIDIA Triton Inference Server, SuperSONIC decouples client workflows from server infrastructure, standardizing communication, optimizing throughput, load balancing, and monitoring. SuperSONIC has been successfully deployed for the CMS and ATLAS experiments at the CERN Large Hadron Collider (LHC), the IceCube Neutrino Observatory (IceCube), and the Laser Interferometer Gravitational-Wave Observatory (LIGO) and tested on Kubernetes clusters at Purdue University, the National Research Platform (NRP), and the University of Chicago. SuperSONIC addresses the challenges of the Cloud-native era by providing a reusable, configurable framework that enhances the efficiency of accelerator-based inference deployment across diverse scientific domains and industries.
more »
« less
- PAR ID:
- 10618428
- Publisher / Repository:
- ACM
- Date Published:
- Page Range / eLocation ID:
- 1 to 5
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)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.more » « less
-
The adaptation of machine learning (ML) in scientific and medical research in recent years has heralded a new era of innovation, catalyzing breakthroughs that were once deemed unattainable. In this paper, we present the Machine Learning Hub (ML Hub) – a web application offering a single point of access to pre-trained ML models and datasets, catering to users across varying expertise levels. Built upon the NSF-funded Tapis v3 Application Programming Interface (API) and Tapis User Interface (TapisUI), the platform offers a user-friendly interface for model discovery, dataset exploration, and inference server deployment.more » « less
-
The adaptation of machine learning (ML) in scientific and medical research in recent years has heralded a new era of innovation, catalyzing breakthroughs that were once deemed unattainable. In this paper, we present the Machine Learning Hub (ML Hub) – a web application offering a single point of access to pre-trained ML models and datasets, catering to users across varying expertise levels. Built upon the NSF-funded Tapis v3 Application Programming Interface (API) and Tapis User Interface (TapisUI), the platform offers a user-friendly interface for model discovery, dataset exploration, and inference server deployment.more » « less
-
null (Ed.)With the advent of the fourth industrial revolution, industry practitioners are moving towards container-based infrastructure for managing their digital workloads. Kubernetes, a container orchestration tool, is reported to help industry practitioners in automated management of cloud infrastructure and rapid deployment of software services. Despite reported benefits, Kubernetes installations are susceptible to security defects, as it occurred for Tesla in 2018. Understanding how frequently security defects appear in Kubernetes installations can help cybersecurity researchers to investigate security-related vulnerabilities for Kubernetes and generate security best practices to avoid them. In this position paper, we first quantify how frequently security defects appear in Kubernetes manifests, i.e., configuration files that are use to install and manage Kubernetes. Next, we lay out a list of future research directions that researchers can pursue.We apply qualitative analysis on 5,193 commits collected from 38 open source repositories and observe that 0.79% of the 5,193 commits are security-related. Based on our findings, we posit that security-related defects are under-reported and advocate for rigorous research that can systematically identify undiscovered security defects that exist in Kubernetes manifests. We predict that the increasing use of Kubernetes with unresolved security defects can lead to large-scale security breaches.more » « less
