Democratizing HPC Access and Use with Knowledge Graphs
Open Access
- 12 November 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 243-251
Abstract
The field of High-Performance Computing (HPC) is undergoing rapid evolution, with an expanding and diverse user base harnessing its unparalleled computational capabilities. As the range of HPC applications grows, newcomers to the field are faced with the daunting task of optimizing their applications for efficient execution on HPC systems. Traditional documentation, often spanning dozens of pages, is cumbersome for finding answers and ill-suited for integration with emerging conversational AI-powered user interfaces like chatbots. Addressing this challenge, we propose a novel HPC ontology crafted to encapsulate HPC runtime relations in a scalable fashion. Our proposed ontology not only facilitates the transfer and querying of this knowledge but also serves as a foundational pillar for our AI-powered Speech Assistant Interface (SAI)[13]. This ensures reproducibility, reliability, and optimal performance when executing tasks. In this paper, we elucidate the relationships and properties underpinning our ontology and showcase how users can interact with knowledge graphs based on our proposed ontology to derive insights.Keywords
Funding Information
- NSF (National Science Foundation) (#1818253, #1854828, #1931537, #2007991, #2018627)
This publication has 11 references indexed in Scilit:
- HPC Ontology: Towards a Unified Ontology for Managing Training Datasets and AI Models for High-Performance Computing2021
- An ontology for heterogeneous resources management interoperability and HPC in the cloudFuture Generation Computer Systems, 2018
- Open OnDemand: A web-based client portal for HPC centersJournal of Open Source Software, 2018
- Rethinking the Inception Architecture for Computer Vision2016
- OntoSoft2015
- The protégé projectAI Matters, 2015
- The Software Ontology (SWO): a resource for reproducibility in biomedical data analysis, curation and digital preservationJournal of Biomedical Semantics, 2014
- The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]IEEE Signal Processing Magazine, 2012
- ImageNet: A large-scale hierarchical image database2009
- On integrating learning object metadata inside the opencyc knowledge base2004