Adaptive Distributed Data Structure Management for Parallel CFD Applications

Handle URI:
http://hdl.handle.net/10754/597452
Title:
Adaptive Distributed Data Structure Management for Parallel CFD Applications
Authors:
Frisch, Jerome; Mundani, Ralf-Peter; Rank, Ernst
Abstract:
Computational fluid dynamics (CFD) simulations require a lot of computing resources in terms of CPU time and memory in order to compute with a reasonable physical accuracy. If only uniformly refined domains are applied, the amount of computing cells is growing rather fast if a certain small resolution is physically required. This can be remedied by applying adaptively refined grids. Unfortunately, due to the adaptive refinement procedures, errors are introduced which have to be taken into account. This paper is focussing on implementation details of the applied adaptive data structure management and a qualitative analysis of the introduced errors by analysing a Poisson problem on the given data structure, which has to be solved in every time step of a CFD analysis. Furthermore an adaptive CFD benchmark example is computed, showing the benefits of an adaptive refinement as well as measurements of parallel data distribution and performance. © 2013 IEEE.
Citation:
Frisch J, Mundani R-P, Rank E (2013) Adaptive Distributed Data Structure Management for Parallel CFD Applications. 2013 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing. Available: http://dx.doi.org/10.1109/SYNASC.2013.73.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2013 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing
KAUST Grant Number:
UK-c0020
Issue Date:
Sep-2013
DOI:
10.1109/SYNASC.2013.73
Type:
Conference Paper
Sponsors:
This publication is partially based on work supported byAward No. UK-c0020, made by King Abdullah University ofScience and Technology (KAUST). Furthermore, the authorswould like to cordially thank for the support and usage of theBlue Gene/P at Universitatea de Vest din Timi ̧soara (UVT)in Romania.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorFrisch, Jeromeen
dc.contributor.authorMundani, Ralf-Peteren
dc.contributor.authorRank, Ernsten
dc.date.accessioned2016-02-25T12:33:31Zen
dc.date.available2016-02-25T12:33:31Zen
dc.date.issued2013-09en
dc.identifier.citationFrisch J, Mundani R-P, Rank E (2013) Adaptive Distributed Data Structure Management for Parallel CFD Applications. 2013 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing. Available: http://dx.doi.org/10.1109/SYNASC.2013.73.en
dc.identifier.doi10.1109/SYNASC.2013.73en
dc.identifier.urihttp://hdl.handle.net/10754/597452en
dc.description.abstractComputational fluid dynamics (CFD) simulations require a lot of computing resources in terms of CPU time and memory in order to compute with a reasonable physical accuracy. If only uniformly refined domains are applied, the amount of computing cells is growing rather fast if a certain small resolution is physically required. This can be remedied by applying adaptively refined grids. Unfortunately, due to the adaptive refinement procedures, errors are introduced which have to be taken into account. This paper is focussing on implementation details of the applied adaptive data structure management and a qualitative analysis of the introduced errors by analysing a Poisson problem on the given data structure, which has to be solved in every time step of a CFD analysis. Furthermore an adaptive CFD benchmark example is computed, showing the benefits of an adaptive refinement as well as measurements of parallel data distribution and performance. © 2013 IEEE.en
dc.description.sponsorshipThis publication is partially based on work supported byAward No. UK-c0020, made by King Abdullah University ofScience and Technology (KAUST). Furthermore, the authorswould like to cordially thank for the support and usage of theBlue Gene/P at Universitatea de Vest din Timi ̧soara (UVT)in Romania.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectAdaptive data structureen
dc.subjectMessage passing paradigmen
dc.subjectMulti-grid-like solver concepten
dc.subjectParallel computationen
dc.titleAdaptive Distributed Data Structure Management for Parallel CFD Applicationsen
dc.typeConference Paperen
dc.identifier.journal2013 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computingen
dc.contributor.institutionTechnische Universitat Munchen, Munich, Germanyen
kaust.grant.numberUK-c0020en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.