• DocumentCode
    3040504
  • Title

    GStokes: A Grid-enabled Solver for the 3D Stokes/Navier-Stokes System on Hybrid Meshes

  • Author

    Langer, Ulrich ; Zulehner, Walter ; Yang, Huidong ; Baumgartner, Markus

  • Author_Institution
    Johannes Kepler Univ. Linz, Linz
  • fYear
    2007
  • fDate
    5-8 July 2007
  • Firstpage
    50
  • Lastpage
    50
  • Abstract
    Grid computing is a new framework for distributed computing that provides us a more advanced computing and memory resource sharing model for solving large scale computational problems. Under this environment, the challenging problem in computational fluid dynamics (CFD) can be resolved in an efficient way. However, the traditional solvers of partial differential equations (PDEs) using finite element method (FEM) are usually tight combinations of a mesh generator and a linear system solver, and thus not suitable for grid computing. In this paper, we present a newly designed grid-enabled client/server (CS) model for the 3D Stokes/Navier-Stokes problem on more complicated hybrid meshes. This paper mainly focuses on the construction of the client/server model under the grid environment, and how to apply it to the Stokes system.
  • Keywords
    Navier-Stokes equations; computational fluid dynamics; grid computing; resource allocation; 3D Stokes/Navier-Stokes System; GStokes:; computational fluid dynamics; finite element method; grid computing; grid-enabled client/server model; grid-enabled solver; hybrid meshes; linear system solver; partial differential equations; resource sharing model; Approximation methods; Computational fluid dynamics; Distributed computing; Europe; Finite element methods; Grid computing; Mesh generation; Robustness; Solid modeling; TCPIP;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Parallel and Distributed Computing, 2007. ISPDC '07. Sixth International Symposium on
  • Conference_Location
    Hagenberg
  • Print_ISBN
    0-7695-2917
  • Type

    conf

  • DOI
    10.1109/ISPDC.2007.26
  • Filename
    4271940