Developing and Using a Geometric Multigrid, Unstructured Grid Mini-Application to Assess Many-Core Architectures

Andrew Owenson, Steven Wright, Richard Bunt, Stephen Jarvis, Yoon Ho, Matthew Street

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

Abstract

Achieving high-performance of large scientific codes is a difficult task. This has led to the development of numerous mini-applications that are more tractable to analyse, while retaining performance characteristics of their full-sized counterparts. These 'mini-apps' also enable faster hardware evaluation, and for sensitive codes allow evaluation of systems outside of access approval processes. In this paper we develop a mini-application of a geometric multigrid, unstructured grid Computational Fluid Dynamics (CFD) code, designed to exhibit similar performance characteristics without sharing code. We detail our experiences developing this application, using guidelines detailed in existing research, and contribute further additions to these to aid future mini-application developers. Our application is validated against the inviscid flux routine of HYDRA, a CFD code developed by Rolls-Royce, which confirms that the parent kernel and mini-application share fundamental causes of parallel inefficiency. We then use the mini-application to assess the impact of Intel's Knights Landing (KNL) on performance. We find that the mini-app and parent kernel continue to share scaling characteristics, however a comparison with Broadwell performance exposed significant differences between the kernels that were undetected by the validation.

Original languageEnglish
Title of host publicationProceedings - 26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2018
EditorsIgor Kotenko, Ivan Merelli, Pietro Lio
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages68-76
Number of pages9
ISBN (Electronic)9781538649756
DOIs
Publication statusPublished - 6 Jun 2018
Event26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2018 - Cambridge, United Kingdom
Duration: 21 Mar 201823 Mar 2018

Publication series

NameProceedings - 26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2018

Conference

Conference26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2018
Country/TerritoryUnited Kingdom
CityCambridge
Period21/03/1823/03/18

Keywords

  • computational fluid dynamics
  • high performance computing
  • performance analysis
  • scientific computing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'Developing and Using a Geometric Multigrid, Unstructured Grid Mini-Application to Assess Many-Core Architectures'. Together they form a unique fingerprint.

Cite this