Parallel GPU implementations of numerical methods for fluid dynamics

This article presents the application of parallel computing techniques using Graphic Processing Unit (GPU) in order to improve the computational efficiency of numerical methods applied to uid dynamics problems. In the last ten years, GPUs have emerged as a major paradigm for solving complex problem...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ezzatti, Pablo, Nesmachnow, Sergio
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2010
Materias:
Ciencias Informáticas
GPU computing
linear system solvers
fluid dynamics models
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/152630
http://39jaiio.sadio.org.ar/sites/default/files/39jaiio-hpc-01.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-152630
record_format dspace
spelling I19-R120-10915-1526302023-05-09T20:04:27Z http://sedici.unlp.edu.ar/handle/10915/152630 http://39jaiio.sadio.org.ar/sites/default/files/39jaiio-hpc-01.pdf issn:1851-9326 Parallel GPU implementations of numerical methods for fluid dynamics Ezzatti, Pablo Nesmachnow, Sergio 2010 2010 2023-05-09T13:36:19Z en Ciencias Informáticas GPU computing linear system solvers fluid dynamics models This article presents the application of parallel computing techniques using Graphic Processing Unit (GPU) in order to improve the computational efficiency of numerical methods applied to uid dynamics problems. In the last ten years, GPUs have emerged as a major paradigm for solving complex problems using parallel computing techniques. Fluid dynamics problems usually requires large execution times to perform simulations for realistic scenarios. In this work, two numerical models for fluid dynamics are presented, and parallel implementations on GPU for the Strongly Implicit Procedure and the Cyclic Reduction methods for solving linear systems are introduced. The experimental evaluation of the proposed methods demonstrates that a significant reduction on the computing times can be attained when solving linear systems with representative dimensions, and preliminary results show that the efficiency gains also propagate to the numerical models for fluid dynamics. Sociedad Argentina de Informática e Investigación Operativa Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 3181-3194
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
GPU computing
linear system solvers
fluid dynamics models
spellingShingle Ciencias Informáticas
GPU computing
linear system solvers
fluid dynamics models
Ezzatti, Pablo
Nesmachnow, Sergio
Parallel GPU implementations of numerical methods for fluid dynamics
topic_facet Ciencias Informáticas
GPU computing
linear system solvers
fluid dynamics models
description This article presents the application of parallel computing techniques using Graphic Processing Unit (GPU) in order to improve the computational efficiency of numerical methods applied to uid dynamics problems. In the last ten years, GPUs have emerged as a major paradigm for solving complex problems using parallel computing techniques. Fluid dynamics problems usually requires large execution times to perform simulations for realistic scenarios. In this work, two numerical models for fluid dynamics are presented, and parallel implementations on GPU for the Strongly Implicit Procedure and the Cyclic Reduction methods for solving linear systems are introduced. The experimental evaluation of the proposed methods demonstrates that a significant reduction on the computing times can be attained when solving linear systems with representative dimensions, and preliminary results show that the efficiency gains also propagate to the numerical models for fluid dynamics.
format Objeto de conferencia
Objeto de conferencia
author Ezzatti, Pablo
Nesmachnow, Sergio
author_facet Ezzatti, Pablo
Nesmachnow, Sergio
author_sort Ezzatti, Pablo
title Parallel GPU implementations of numerical methods for fluid dynamics
title_short Parallel GPU implementations of numerical methods for fluid dynamics
title_full Parallel GPU implementations of numerical methods for fluid dynamics
title_fullStr Parallel GPU implementations of numerical methods for fluid dynamics
title_full_unstemmed Parallel GPU implementations of numerical methods for fluid dynamics
title_sort parallel gpu implementations of numerical methods for fluid dynamics
publishDate 2010
url http://sedici.unlp.edu.ar/handle/10915/152630
http://39jaiio.sadio.org.ar/sites/default/files/39jaiio-hpc-01.pdf
work_keys_str_mv AT ezzattipablo parallelgpuimplementationsofnumericalmethodsforfluiddynamics
AT nesmachnowsergio parallelgpuimplementationsofnumericalmethodsforfluiddynamics
_version_ 1765660135745650688

Ejemplares similares