Edinburgh Research Explorer

The Technologies Required for Fusing HPC and Real-Time Data to Support Urgent Computing

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

https://ieeexplore.ieee.org/document/8944962
Original languageEnglish
Title of host publicationThe Technologies Required for Fusing HPC and Real-Time Data to Support Urgent Computing
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages24-34
Number of pages11
ISBN (Electronic)978-1-7281-5995-9
ISBN (Print)978-1-7281-5996-6
DOIs
Publication statusPublished - 30 Dec 2019
EventThe first international workshop on HPC for urgent decision making - Denver, United States
Duration: 17 Nov 201917 Nov 2019
http://www.urgenthpc.com

Workshop

WorkshopThe first international workshop on HPC for urgent decision making
Abbreviated titleUrgentHPC
CountryUnited States
CityDenver
Period17/11/1917/11/19
Internet address

Abstract

The use of High Performance Computing (HPC) to compliment urgent decision making in the event of disasters is an important future potential use of supercomputers. However, the usage modes involved are rather different from how HPC has been used traditionally. As such, there are many obstacles that need to be overcome, not least the unbounded wait times in the batch system queues, to make the use of HPC in disaster response practical. In this paper, we present how the VESTEC project plans to overcome these issues and develop a working prototype of an urgent computing control system. We describe the requirements for such a system and analyse the different technologies available that can be leveraged to successfully build such a system. We finally explore the design of the VESTEC system and discuss ongoing challenges that need to be addressed to realise a production level system.

Event

The first international workshop on HPC for urgent decision making

17/11/1917/11/19

Denver, United States

Event: Workshop

Download statistics

No data available

ID: 137049814