Nek5000/RS performance on advanced GPU architectures

The authors explore performance scalability of the open-source thermal-fluids code, NekRS, on the U.S. Department of Energy's leadership computers, Crusher, Frontier, Summit, Perlmutter, and Polaris. Particular attention is given to analyzing performance and time-to-solution at the strong-scale...

Full description

Saved in:
Bibliographic Details
Main Authors: Misun Min, Yu-Hsiang Lan, Paul Fischer, Thilina Rathnayake, John Holmen
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in High Performance Computing
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fhpcp.2024.1303358/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850023973218156544
author Misun Min
Yu-Hsiang Lan
Paul Fischer
Paul Fischer
Paul Fischer
Thilina Rathnayake
John Holmen
author_facet Misun Min
Yu-Hsiang Lan
Paul Fischer
Paul Fischer
Paul Fischer
Thilina Rathnayake
John Holmen
author_sort Misun Min
collection DOAJ
description The authors explore performance scalability of the open-source thermal-fluids code, NekRS, on the U.S. Department of Energy's leadership computers, Crusher, Frontier, Summit, Perlmutter, and Polaris. Particular attention is given to analyzing performance and time-to-solution at the strong-scale limit for a target efficiency of 80%, which is typical for production runs on the DOE's high-performance computing systems. Several examples of anomalous behavior are also discussed and analyzed.
format Article
id doaj-art-90bdae3918aa4a6b9e098f177f28caa6
institution DOAJ
issn 2813-7337
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in High Performance Computing
spelling doaj-art-90bdae3918aa4a6b9e098f177f28caa62025-08-20T03:01:14ZengFrontiers Media S.A.Frontiers in High Performance Computing2813-73372025-02-01210.3389/fhpcp.2024.13033581303358Nek5000/RS performance on advanced GPU architecturesMisun Min0Yu-Hsiang Lan1Paul Fischer2Paul Fischer3Paul Fischer4Thilina Rathnayake5John Holmen6Mathematics and Computer Science Divison, Argonne National Laboratory, Lemont, IL, United StatesDepartment of Computer Science, University of Illinois Urbana-Champaign, Urbana, IL, United StatesMathematics and Computer Science Divison, Argonne National Laboratory, Lemont, IL, United StatesDepartment of Computer Science, University of Illinois Urbana-Champaign, Urbana, IL, United StatesDepartment of Mechanical Science and Engineering, University of Illinois Urbana-Champaign, Urbana, IL, United StatesDepartment of Computer Science, University of Illinois Urbana-Champaign, Urbana, IL, United StatesOak Ridge National Laboratory, Oak Ridge Leadership Computing Facility, Oak Ridge, TN, United StatesThe authors explore performance scalability of the open-source thermal-fluids code, NekRS, on the U.S. Department of Energy's leadership computers, Crusher, Frontier, Summit, Perlmutter, and Polaris. Particular attention is given to analyzing performance and time-to-solution at the strong-scale limit for a target efficiency of 80%, which is typical for production runs on the DOE's high-performance computing systems. Several examples of anomalous behavior are also discussed and analyzed.https://www.frontiersin.org/articles/10.3389/fhpcp.2024.1303358/fullNek5000/RSexascalestrong scalingsmall modular reactorrod-bundle
spellingShingle Misun Min
Yu-Hsiang Lan
Paul Fischer
Paul Fischer
Paul Fischer
Thilina Rathnayake
John Holmen
Nek5000/RS performance on advanced GPU architectures
Frontiers in High Performance Computing
Nek5000/RS
exascale
strong scaling
small modular reactor
rod-bundle
title Nek5000/RS performance on advanced GPU architectures
title_full Nek5000/RS performance on advanced GPU architectures
title_fullStr Nek5000/RS performance on advanced GPU architectures
title_full_unstemmed Nek5000/RS performance on advanced GPU architectures
title_short Nek5000/RS performance on advanced GPU architectures
title_sort nek5000 rs performance on advanced gpu architectures
topic Nek5000/RS
exascale
strong scaling
small modular reactor
rod-bundle
url https://www.frontiersin.org/articles/10.3389/fhpcp.2024.1303358/full
work_keys_str_mv AT misunmin nek5000rsperformanceonadvancedgpuarchitectures
AT yuhsianglan nek5000rsperformanceonadvancedgpuarchitectures
AT paulfischer nek5000rsperformanceonadvancedgpuarchitectures
AT paulfischer nek5000rsperformanceonadvancedgpuarchitectures
AT paulfischer nek5000rsperformanceonadvancedgpuarchitectures
AT thilinarathnayake nek5000rsperformanceonadvancedgpuarchitectures
AT johnholmen nek5000rsperformanceonadvancedgpuarchitectures