CUBE: A scalable framework for large-scale industrial simulations

Writing high performance solvers for engineering applications is a delicate task. These codes are often developed on an application to application basis, highly optimized to solve a certain problem. Here, we present our work on developing a general simulation framework for efficient computation of t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jansson, Niclas, Bale, Rahul, Onishi, Keiji, Tsubokura, Makoto
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Jansson, Niclas
Bale, Rahul
Onishi, Keiji
Tsubokura, Makoto
description Writing high performance solvers for engineering applications is a delicate task. These codes are often developed on an application to application basis, highly optimized to solve a certain problem. Here, we present our work on developing a general simulation framework for efficient computation of time resolved approximations of complex industrial flow problems - Complex Unified Building cubE method (Cube). To address the challenges of emerging, modern supercomputers, suitable data structures and communication patterns are developed and incorporated into Cube. We use a Cartesian grid together with various immersed boundary methods to accurately capture moving, complex geometries. The asymmetric workload of the immersed boundary is balanced by a predictive dynamic load balancer, and a multithreaded halo-exchange algorithm is employed to efficiently overlap communication with computations. Our work also concerns efficient methods for handling the large amount of data produced by large-scale flow simulations, such as scalable parallel I/O, data compression and in-situ processing.
doi_str_mv 10.48550/arxiv.1808.04099
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1808_04099</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1808_04099</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-e09323ea3ca374d93120d87f8b8913d83ec89999f6490fef6a355a9f133438c33</originalsourceid><addsrcrecordid>eNotz81OwzAQBGBfOKDCA3DCL5Bgd51kl1uIyo9UiUs5R9tkjSycBtktP28PLcxlDiON9Cl1ZU3psKrMDaev8FFaNFgaZ4jOVdu93K1udavzwJG3UbRPPMnnnN60n5OOnF6lOI6iw2485H0KHHUO0yHyPsy7fKHOPMcsl_-9UJv71aZ7LNbPD09duy64bqgQQ7AEYRgYGjcS2KUZsfG4RbIwIsiA9BtfOzJefM1QVUzeAjjAAWChrv9uT4b-PYWJ03d_tPQnC_wA4xFDPw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>CUBE: A scalable framework for large-scale industrial simulations</title><source>arXiv.org</source><creator>Jansson, Niclas ; Bale, Rahul ; Onishi, Keiji ; Tsubokura, Makoto</creator><creatorcontrib>Jansson, Niclas ; Bale, Rahul ; Onishi, Keiji ; Tsubokura, Makoto</creatorcontrib><description>Writing high performance solvers for engineering applications is a delicate task. These codes are often developed on an application to application basis, highly optimized to solve a certain problem. Here, we present our work on developing a general simulation framework for efficient computation of time resolved approximations of complex industrial flow problems - Complex Unified Building cubE method (Cube). To address the challenges of emerging, modern supercomputers, suitable data structures and communication patterns are developed and incorporated into Cube. We use a Cartesian grid together with various immersed boundary methods to accurately capture moving, complex geometries. The asymmetric workload of the immersed boundary is balanced by a predictive dynamic load balancer, and a multithreaded halo-exchange algorithm is employed to efficiently overlap communication with computations. Our work also concerns efficient methods for handling the large amount of data produced by large-scale flow simulations, such as scalable parallel I/O, data compression and in-situ processing.</description><identifier>DOI: 10.48550/arxiv.1808.04099</identifier><language>eng</language><subject>Computer Science - Computational Engineering, Finance, and Science ; Physics - Fluid Dynamics</subject><creationdate>2018-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1808.04099$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1808.04099$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Jansson, Niclas</creatorcontrib><creatorcontrib>Bale, Rahul</creatorcontrib><creatorcontrib>Onishi, Keiji</creatorcontrib><creatorcontrib>Tsubokura, Makoto</creatorcontrib><title>CUBE: A scalable framework for large-scale industrial simulations</title><description>Writing high performance solvers for engineering applications is a delicate task. These codes are often developed on an application to application basis, highly optimized to solve a certain problem. Here, we present our work on developing a general simulation framework for efficient computation of time resolved approximations of complex industrial flow problems - Complex Unified Building cubE method (Cube). To address the challenges of emerging, modern supercomputers, suitable data structures and communication patterns are developed and incorporated into Cube. We use a Cartesian grid together with various immersed boundary methods to accurately capture moving, complex geometries. The asymmetric workload of the immersed boundary is balanced by a predictive dynamic load balancer, and a multithreaded halo-exchange algorithm is employed to efficiently overlap communication with computations. Our work also concerns efficient methods for handling the large amount of data produced by large-scale flow simulations, such as scalable parallel I/O, data compression and in-situ processing.</description><subject>Computer Science - Computational Engineering, Finance, and Science</subject><subject>Physics - Fluid Dynamics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81OwzAQBGBfOKDCA3DCL5Bgd51kl1uIyo9UiUs5R9tkjSycBtktP28PLcxlDiON9Cl1ZU3psKrMDaev8FFaNFgaZ4jOVdu93K1udavzwJG3UbRPPMnnnN60n5OOnF6lOI6iw2485H0KHHUO0yHyPsy7fKHOPMcsl_-9UJv71aZ7LNbPD09duy64bqgQQ7AEYRgYGjcS2KUZsfG4RbIwIsiA9BtfOzJefM1QVUzeAjjAAWChrv9uT4b-PYWJ03d_tPQnC_wA4xFDPw</recordid><startdate>20180813</startdate><enddate>20180813</enddate><creator>Jansson, Niclas</creator><creator>Bale, Rahul</creator><creator>Onishi, Keiji</creator><creator>Tsubokura, Makoto</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20180813</creationdate><title>CUBE: A scalable framework for large-scale industrial simulations</title><author>Jansson, Niclas ; Bale, Rahul ; Onishi, Keiji ; Tsubokura, Makoto</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-e09323ea3ca374d93120d87f8b8913d83ec89999f6490fef6a355a9f133438c33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Computational Engineering, Finance, and Science</topic><topic>Physics - Fluid Dynamics</topic><toplevel>online_resources</toplevel><creatorcontrib>Jansson, Niclas</creatorcontrib><creatorcontrib>Bale, Rahul</creatorcontrib><creatorcontrib>Onishi, Keiji</creatorcontrib><creatorcontrib>Tsubokura, Makoto</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jansson, Niclas</au><au>Bale, Rahul</au><au>Onishi, Keiji</au><au>Tsubokura, Makoto</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>CUBE: A scalable framework for large-scale industrial simulations</atitle><date>2018-08-13</date><risdate>2018</risdate><abstract>Writing high performance solvers for engineering applications is a delicate task. These codes are often developed on an application to application basis, highly optimized to solve a certain problem. Here, we present our work on developing a general simulation framework for efficient computation of time resolved approximations of complex industrial flow problems - Complex Unified Building cubE method (Cube). To address the challenges of emerging, modern supercomputers, suitable data structures and communication patterns are developed and incorporated into Cube. We use a Cartesian grid together with various immersed boundary methods to accurately capture moving, complex geometries. The asymmetric workload of the immersed boundary is balanced by a predictive dynamic load balancer, and a multithreaded halo-exchange algorithm is employed to efficiently overlap communication with computations. Our work also concerns efficient methods for handling the large amount of data produced by large-scale flow simulations, such as scalable parallel I/O, data compression and in-situ processing.</abstract><doi>10.48550/arxiv.1808.04099</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1808.04099
ispartof
issn
language eng
recordid cdi_arxiv_primary_1808_04099
source arXiv.org
subjects Computer Science - Computational Engineering, Finance, and Science
Physics - Fluid Dynamics
title CUBE: A scalable framework for large-scale industrial simulations
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T16%3A17%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=CUBE:%20A%20scalable%20framework%20for%20large-scale%20industrial%20simulations&rft.au=Jansson,%20Niclas&rft.date=2018-08-13&rft_id=info:doi/10.48550/arxiv.1808.04099&rft_dat=%3Carxiv_GOX%3E1808_04099%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true