OpenACC acceleration for the PN–PN-2 algorithm in Nek5000

Evelyn Otero; Jing Gong; Misun Min; Paul Fischer; Philipp Schlatter; Erwin Laure

doi:10.1016/j.jpdc.2019.05.010

OpenACC acceleration for the P_N–P_N-2 algorithm in Nek5000

Evelyn Otero, Jing Gong, Misun Min, Paul Fischer, Philipp Schlatter, Erwin Laure

Research output: Contribution to journal › Article › peer-review

Abstract

Due to its high performance and throughput capabilities, GPU-accelerated computing is becoming a popular technology in scientific computing, in particular using programming models such as CUDA and OpenACC. The main advantage with OpenACC is that it enables to simply port codes in their “original” form to GPU systems through compiler directives, thus allowing an incremental approach. An OpenACC implementation is applied to the CFD code Nek5000 for simulation of incompressible flows, based on the spectral-element method. The work follows up previous implementations and focuses now on the P_N−P_N−2 method for the spatial discretization of the Navier–Stokes equations. Performance results of the ported code show a speed-up of up to 3.1 on multi-GPU for a polynomial order N>11.

Original language	English (US)
Pages (from-to)	69-78
Number of pages	10
Journal	Journal of Parallel and Distributed Computing
Volume	132
DOIs	https://doi.org/10.1016/j.jpdc.2019.05.010
State	Published - Oct 2019
Externally published	Yes

Keywords

GPU programming
High performance computing
Nek5000
OpenACC
Spectral element method

ASJC Scopus subject areas

Software
Theoretical Computer Science
Hardware and Architecture
Computer Networks and Communications
Artificial Intelligence

Online availability

10.1016/j.jpdc.2019.05.010

Library availability

Discover UIUC Full Text

Cite this

@article{122071a9747946edb5ec9d83705f4532,

title = "OpenACC acceleration for the PN–PN-2 algorithm in Nek5000",

abstract = "Due to its high performance and throughput capabilities, GPU-accelerated computing is becoming a popular technology in scientific computing, in particular using programming models such as CUDA and OpenACC. The main advantage with OpenACC is that it enables to simply port codes in their “original” form to GPU systems through compiler directives, thus allowing an incremental approach. An OpenACC implementation is applied to the CFD code Nek5000 for simulation of incompressible flows, based on the spectral-element method. The work follows up previous implementations and focuses now on the PN−PN−2 method for the spatial discretization of the Navier–Stokes equations. Performance results of the ported code show a speed-up of up to 3.1 on multi-GPU for a polynomial order N>11.",

keywords = "GPU programming, High performance computing, Nek5000, OpenACC, Spectral element method",

author = "Evelyn Otero and Jing Gong and Misun Min and Paul Fischer and Philipp Schlatter and Erwin Laure",

note = "Funding Information: This work is partially supported by EU project ExaFLOW, the Stiftelsen f{\"o}r strategisk forskning (SSF) , and the Swedish e-Science Research Center (SeRC) via the SESSI flagship project. We also acknowledge the Swedish National Infrastructure for Computing (SNIC) for providing resources at HPC2N (Ume{\aa}), and Cray for giving access to the Swan system. Publisher Copyright: {\textcopyright} 2019 Elsevier Inc.",

year = "2019",

month = oct,

doi = "10.1016/j.jpdc.2019.05.010",

language = "English (US)",

volume = "132",

pages = "69--78",

journal = "Journal of Parallel and Distributed Computing",

issn = "0743-7315",

publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - OpenACC acceleration for the PN–PN-2 algorithm in Nek5000

AU - Otero, Evelyn

AU - Gong, Jing

AU - Min, Misun

AU - Fischer, Paul

AU - Schlatter, Philipp

AU - Laure, Erwin

N1 - Funding Information: This work is partially supported by EU project ExaFLOW, the Stiftelsen för strategisk forskning (SSF) , and the Swedish e-Science Research Center (SeRC) via the SESSI flagship project. We also acknowledge the Swedish National Infrastructure for Computing (SNIC) for providing resources at HPC2N (Umeå), and Cray for giving access to the Swan system. Publisher Copyright: © 2019 Elsevier Inc.

PY - 2019/10

Y1 - 2019/10

N2 - Due to its high performance and throughput capabilities, GPU-accelerated computing is becoming a popular technology in scientific computing, in particular using programming models such as CUDA and OpenACC. The main advantage with OpenACC is that it enables to simply port codes in their “original” form to GPU systems through compiler directives, thus allowing an incremental approach. An OpenACC implementation is applied to the CFD code Nek5000 for simulation of incompressible flows, based on the spectral-element method. The work follows up previous implementations and focuses now on the PN−PN−2 method for the spatial discretization of the Navier–Stokes equations. Performance results of the ported code show a speed-up of up to 3.1 on multi-GPU for a polynomial order N>11.

AB - Due to its high performance and throughput capabilities, GPU-accelerated computing is becoming a popular technology in scientific computing, in particular using programming models such as CUDA and OpenACC. The main advantage with OpenACC is that it enables to simply port codes in their “original” form to GPU systems through compiler directives, thus allowing an incremental approach. An OpenACC implementation is applied to the CFD code Nek5000 for simulation of incompressible flows, based on the spectral-element method. The work follows up previous implementations and focuses now on the PN−PN−2 method for the spatial discretization of the Navier–Stokes equations. Performance results of the ported code show a speed-up of up to 3.1 on multi-GPU for a polynomial order N>11.

KW - GPU programming

KW - High performance computing

KW - Nek5000

KW - OpenACC

KW - Spectral element method

UR - http://www.scopus.com/inward/record.url?scp=85066835225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066835225&partnerID=8YFLogxK

U2 - 10.1016/j.jpdc.2019.05.010

DO - 10.1016/j.jpdc.2019.05.010

M3 - Article

AN - SCOPUS:85066835225

SN - 0743-7315

VL - 132

SP - 69

EP - 78

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

ER -