On the scalability of CFD tool for supersonic jet flow configurations
•Scalability follows the ideal case when running on 2k cores with 1 billion points.•The solver presents good strong scalability when using up to 3000 processing units.•Super-linear strong scaling is also observed in the tests performed.•The worst scenario studied in the paper present a weak scalabil...
Gespeichert in:
Veröffentlicht in: | Parallel computing 2020-05, Vol.93, p.102620-13, Article 102620 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 13 |
---|---|
container_issue | |
container_start_page | 102620 |
container_title | Parallel computing |
container_volume | 93 |
creator | Junqueira-Junior, Carlos Azevedo, João Luiz F. Panetta, Jairo Wolf, William R. Yamouni, Sami |
description | •Scalability follows the ideal case when running on 2k cores with 1 billion points.•The solver presents good strong scalability when using up to 3000 processing units.•Super-linear strong scaling is also observed in the tests performed.•The worst scenario studied in the paper present a weak scalability efficiency of 70%.•Validation study indicates good agreement with experimental and numerical references.
New regulations are imposing noise emissions limitations for the aviation industry which are pushing researchers and engineers to invest efforts in studying the aeroacoustics phenomena. Following this trend, an in-house computational fluid dynamics tool is build to reproduce high fidelity results of supersonic jet flows for aeroacoustic analogy applications. The solver is written using the large eddy simulation formulation that is discretized using a finite difference approach and an explicit time integration. Numerical simulations of supersonic jet flows are very expensive and demand efficient high-performance computing. Therefore, non-blocking message passage interface protocols and parallel Input/Output features are implemented into the code in order to perform simulations which demand up to one billion grid points. The present work addresses the evaluation of code improvements along with the computational performance of the solver running on a computer with maximum theoretical peak of 2.727 PFlops. Different mesh configurations, whose size varies from a few hundred thousand to approximately one billion grid points, are evaluated in the present paper. Calculations are performed using different workloads in order to assess the strong and weak scalability of the parallel computational tool. Moreover, validation results of a realistic flow condition are also presented in the current work. |
doi_str_mv | 10.1016/j.parco.2020.102620 |
format | Article |
fullrecord | <record><control><sourceid>elsevier_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_02516947v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0167819120300132</els_id><sourcerecordid>S0167819120300132</sourcerecordid><originalsourceid>FETCH-LOGICAL-c382t-e95641b8d569f0e60dcb44a9b69b5ae457fe6be63467ab0720d5f6af299de4113</originalsourceid><addsrcrecordid>eNp9kLFOwzAURS0EEqXwBSxeGVJsx3HigaEqLUWq1AVmy3aeqaMQV3Za1L-nIYiR6UlX91zpHYTuKZlRQsVjM9vraMOMETYkTDBygSa0KllW5rm4RJNzq8wqKuk1ukmpIYQIXpEJWm473O8AJ6tbbXzr-xMODi9Wz7gPocUuRJwOe4gpdN7iBnrs2vCFbeic_zhE3fvQpVt05XSb4O73TtH7avm2WGeb7cvrYr7JbF6xPgNZCE5NVRdCOgKC1NZwrqUR0hQaeFE6EAZEzkWpDSkZqQsntGNS1sApzafoYdzd6Vbto__U8aSC9mo936ghI6ygQvLyOHTzsWtjSCmC-wMoUYM11agfa2qwpkZrZ-pppOD8xtFDVMl66CzUPoLtVR38v_w3-hN10A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>On the scalability of CFD tool for supersonic jet flow configurations</title><source>Access via ScienceDirect (Elsevier)</source><creator>Junqueira-Junior, Carlos ; Azevedo, João Luiz F. ; Panetta, Jairo ; Wolf, William R. ; Yamouni, Sami</creator><creatorcontrib>Junqueira-Junior, Carlos ; Azevedo, João Luiz F. ; Panetta, Jairo ; Wolf, William R. ; Yamouni, Sami</creatorcontrib><description>•Scalability follows the ideal case when running on 2k cores with 1 billion points.•The solver presents good strong scalability when using up to 3000 processing units.•Super-linear strong scaling is also observed in the tests performed.•The worst scenario studied in the paper present a weak scalability efficiency of 70%.•Validation study indicates good agreement with experimental and numerical references.
New regulations are imposing noise emissions limitations for the aviation industry which are pushing researchers and engineers to invest efforts in studying the aeroacoustics phenomena. Following this trend, an in-house computational fluid dynamics tool is build to reproduce high fidelity results of supersonic jet flows for aeroacoustic analogy applications. The solver is written using the large eddy simulation formulation that is discretized using a finite difference approach and an explicit time integration. Numerical simulations of supersonic jet flows are very expensive and demand efficient high-performance computing. Therefore, non-blocking message passage interface protocols and parallel Input/Output features are implemented into the code in order to perform simulations which demand up to one billion grid points. The present work addresses the evaluation of code improvements along with the computational performance of the solver running on a computer with maximum theoretical peak of 2.727 PFlops. Different mesh configurations, whose size varies from a few hundred thousand to approximately one billion grid points, are evaluated in the present paper. Calculations are performed using different workloads in order to assess the strong and weak scalability of the parallel computational tool. Moreover, validation results of a realistic flow condition are also presented in the current work.</description><identifier>ISSN: 0167-8191</identifier><identifier>EISSN: 1872-7336</identifier><identifier>DOI: 10.1016/j.parco.2020.102620</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Computational fluid dynamics ; Engineering Sciences ; Fluids mechanics ; Large eddy simulation ; Mechanics ; Scalability ; Supersonic jet flow</subject><ispartof>Parallel computing, 2020-05, Vol.93, p.102620-13, Article 102620</ispartof><rights>2020 Elsevier B.V.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c382t-e95641b8d569f0e60dcb44a9b69b5ae457fe6be63467ab0720d5f6af299de4113</citedby><cites>FETCH-LOGICAL-c382t-e95641b8d569f0e60dcb44a9b69b5ae457fe6be63467ab0720d5f6af299de4113</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.parco.2020.102620$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,780,784,885,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttps://hal.science/hal-02516947$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Junqueira-Junior, Carlos</creatorcontrib><creatorcontrib>Azevedo, João Luiz F.</creatorcontrib><creatorcontrib>Panetta, Jairo</creatorcontrib><creatorcontrib>Wolf, William R.</creatorcontrib><creatorcontrib>Yamouni, Sami</creatorcontrib><title>On the scalability of CFD tool for supersonic jet flow configurations</title><title>Parallel computing</title><description>•Scalability follows the ideal case when running on 2k cores with 1 billion points.•The solver presents good strong scalability when using up to 3000 processing units.•Super-linear strong scaling is also observed in the tests performed.•The worst scenario studied in the paper present a weak scalability efficiency of 70%.•Validation study indicates good agreement with experimental and numerical references.
New regulations are imposing noise emissions limitations for the aviation industry which are pushing researchers and engineers to invest efforts in studying the aeroacoustics phenomena. Following this trend, an in-house computational fluid dynamics tool is build to reproduce high fidelity results of supersonic jet flows for aeroacoustic analogy applications. The solver is written using the large eddy simulation formulation that is discretized using a finite difference approach and an explicit time integration. Numerical simulations of supersonic jet flows are very expensive and demand efficient high-performance computing. Therefore, non-blocking message passage interface protocols and parallel Input/Output features are implemented into the code in order to perform simulations which demand up to one billion grid points. The present work addresses the evaluation of code improvements along with the computational performance of the solver running on a computer with maximum theoretical peak of 2.727 PFlops. Different mesh configurations, whose size varies from a few hundred thousand to approximately one billion grid points, are evaluated in the present paper. Calculations are performed using different workloads in order to assess the strong and weak scalability of the parallel computational tool. Moreover, validation results of a realistic flow condition are also presented in the current work.</description><subject>Computational fluid dynamics</subject><subject>Engineering Sciences</subject><subject>Fluids mechanics</subject><subject>Large eddy simulation</subject><subject>Mechanics</subject><subject>Scalability</subject><subject>Supersonic jet flow</subject><issn>0167-8191</issn><issn>1872-7336</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp9kLFOwzAURS0EEqXwBSxeGVJsx3HigaEqLUWq1AVmy3aeqaMQV3Za1L-nIYiR6UlX91zpHYTuKZlRQsVjM9vraMOMETYkTDBygSa0KllW5rm4RJNzq8wqKuk1ukmpIYQIXpEJWm473O8AJ6tbbXzr-xMODi9Wz7gPocUuRJwOe4gpdN7iBnrs2vCFbeic_zhE3fvQpVt05XSb4O73TtH7avm2WGeb7cvrYr7JbF6xPgNZCE5NVRdCOgKC1NZwrqUR0hQaeFE6EAZEzkWpDSkZqQsntGNS1sApzafoYdzd6Vbto__U8aSC9mo936ghI6ygQvLyOHTzsWtjSCmC-wMoUYM11agfa2qwpkZrZ-pppOD8xtFDVMl66CzUPoLtVR38v_w3-hN10A</recordid><startdate>20200501</startdate><enddate>20200501</enddate><creator>Junqueira-Junior, Carlos</creator><creator>Azevedo, João Luiz F.</creator><creator>Panetta, Jairo</creator><creator>Wolf, William R.</creator><creator>Yamouni, Sami</creator><general>Elsevier B.V</general><general>Elsevier</general><scope>AAYXX</scope><scope>CITATION</scope><scope>1XC</scope><scope>VOOES</scope></search><sort><creationdate>20200501</creationdate><title>On the scalability of CFD tool for supersonic jet flow configurations</title><author>Junqueira-Junior, Carlos ; Azevedo, João Luiz F. ; Panetta, Jairo ; Wolf, William R. ; Yamouni, Sami</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c382t-e95641b8d569f0e60dcb44a9b69b5ae457fe6be63467ab0720d5f6af299de4113</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computational fluid dynamics</topic><topic>Engineering Sciences</topic><topic>Fluids mechanics</topic><topic>Large eddy simulation</topic><topic>Mechanics</topic><topic>Scalability</topic><topic>Supersonic jet flow</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Junqueira-Junior, Carlos</creatorcontrib><creatorcontrib>Azevedo, João Luiz F.</creatorcontrib><creatorcontrib>Panetta, Jairo</creatorcontrib><creatorcontrib>Wolf, William R.</creatorcontrib><creatorcontrib>Yamouni, Sami</creatorcontrib><collection>CrossRef</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>Parallel computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Junqueira-Junior, Carlos</au><au>Azevedo, João Luiz F.</au><au>Panetta, Jairo</au><au>Wolf, William R.</au><au>Yamouni, Sami</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>On the scalability of CFD tool for supersonic jet flow configurations</atitle><jtitle>Parallel computing</jtitle><date>2020-05-01</date><risdate>2020</risdate><volume>93</volume><spage>102620</spage><epage>13</epage><pages>102620-13</pages><artnum>102620</artnum><issn>0167-8191</issn><eissn>1872-7336</eissn><abstract>•Scalability follows the ideal case when running on 2k cores with 1 billion points.•The solver presents good strong scalability when using up to 3000 processing units.•Super-linear strong scaling is also observed in the tests performed.•The worst scenario studied in the paper present a weak scalability efficiency of 70%.•Validation study indicates good agreement with experimental and numerical references.
New regulations are imposing noise emissions limitations for the aviation industry which are pushing researchers and engineers to invest efforts in studying the aeroacoustics phenomena. Following this trend, an in-house computational fluid dynamics tool is build to reproduce high fidelity results of supersonic jet flows for aeroacoustic analogy applications. The solver is written using the large eddy simulation formulation that is discretized using a finite difference approach and an explicit time integration. Numerical simulations of supersonic jet flows are very expensive and demand efficient high-performance computing. Therefore, non-blocking message passage interface protocols and parallel Input/Output features are implemented into the code in order to perform simulations which demand up to one billion grid points. The present work addresses the evaluation of code improvements along with the computational performance of the solver running on a computer with maximum theoretical peak of 2.727 PFlops. Different mesh configurations, whose size varies from a few hundred thousand to approximately one billion grid points, are evaluated in the present paper. Calculations are performed using different workloads in order to assess the strong and weak scalability of the parallel computational tool. Moreover, validation results of a realistic flow condition are also presented in the current work.</abstract><pub>Elsevier B.V</pub><doi>10.1016/j.parco.2020.102620</doi><tpages>13</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0167-8191 |
ispartof | Parallel computing, 2020-05, Vol.93, p.102620-13, Article 102620 |
issn | 0167-8191 1872-7336 |
language | eng |
recordid | cdi_hal_primary_oai_HAL_hal_02516947v1 |
source | Access via ScienceDirect (Elsevier) |
subjects | Computational fluid dynamics Engineering Sciences Fluids mechanics Large eddy simulation Mechanics Scalability Supersonic jet flow |
title | On the scalability of CFD tool for supersonic jet flow configurations |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T23%3A55%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=On%20the%20scalability%20of%20CFD%20tool%20for%20supersonic%20jet%20flow%20configurations&rft.jtitle=Parallel%20computing&rft.au=Junqueira-Junior,%20Carlos&rft.date=2020-05-01&rft.volume=93&rft.spage=102620&rft.epage=13&rft.pages=102620-13&rft.artnum=102620&rft.issn=0167-8191&rft.eissn=1872-7336&rft_id=info:doi/10.1016/j.parco.2020.102620&rft_dat=%3Celsevier_hal_p%3ES0167819120300132%3C/elsevier_hal_p%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_els_id=S0167819120300132&rfr_iscdi=true |