Porting CFD Codes Towards Grids: A Case Study

  • Dana Petcu
  • Daniel Vizman
  • Marcin Paprzycki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3911)

Abstract

In this paper we discuss an application of a modified version of a graph partitioning-based heuristic load-balancing algorithm known as the Largest Task First with Minimum Finish Time and Available Communication Costs, which is a part of the EVAH package. The proposed modification takes into account the dynamic nature and heterogeneity of grid environments. The new algorithm is applied to facilitate load balance of a known CFD code used to model crystal growth.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cao, J., Spooner, D.P., Jarvis, S.A., Saini, S., Nudd, G.R.: Agent-based grid load balancing using performance-driven task scheduling. In: Procs. of IPDPS 2003, IEEE Computer Press, Los Alamitos (2003)Google Scholar
  2. 2.
    David, R., Genaud, S., Giersch, A., Schwarz, B., Violard, E.: Source code transformations strategies to load-balance grid applications. In: Parashar, M. (ed.) GRID 2002. LNCS, vol. 2536, pp. 82–87. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Djomehri, M.J., Biswas, R., Lopez-Benitez, N.: Load balancing strategies for multi-block overset grid applications, NAS-03-007, Available at www.nas.nasa.gov/News/Techreports/2003/PDF/nas-03-007.pdf
  4. 4.
    Ferziger, J.H., Perić, M.: Computational Methods for Fluid Dynamics. Springer, Heidelberg (1996)MATHGoogle Scholar
  5. 5.
    Gao, H., Schmidt, A., Gupta, A., Luksch, P.: Load balancing for spatial-grid based parallel numerical simulations on clusters of SMPs. In: Procs. Euro PDP 2003, pp. 75–82. IEEE Computer Press, Los Alamitos (2003)Google Scholar
  6. 6.
    Iliev, O., Scäfer, M.: A numerical study of the efficiency of SIMPLE-type algorithms in computing incompressible flows on streched grids. In: Griebel, M., Margenov, S., Yalamov, P. (eds.) Procs. LSSC 1999. Notes on Numerical Fluid Mechanics, Vieweg, vol. 73, pp. 207–214 (2000)Google Scholar
  7. 7.
    Lukanin, D., Kalaev, V., Zhmakin, A.: Parallel simulation of Czochralski crystal growth. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds.) PPAM 2004. LNCS, vol. 3019, pp. 469–474. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    Payli, R.U., Yilmaz, E., Ecer, A., Akay, H.U., Chien, S.: DLB – A dynamic load balancing tool for grid computing. In: Winter, G., Ecer, A., Satofuka, F.N., Fox, P. (eds.) Procs. Parallel CFD 2004, pp. 391–399. Elsevier, Amsterdam (2005)Google Scholar
  9. 9.
    Perić, M.: A finite volume method for the prediction of three-dimensional fluid flow in complex ducts, Ph.D. Thesis, University of London (1985)Google Scholar
  10. 10.
    Petcu, D., Vizman, D., Friedrich, J., Popescu, M.: Crystal growth simulation on clusters. In: Banicescu, I. (ed.) Procs. of HPC 2003, pp. 41–46. Simulation Councils Inc., San Diego (2003)Google Scholar
  11. 11.
    Sackinger, P.A., Brown, R.A., Brown, J.J.: A finite element method for analysis of fluid flow, heat transfer and free interfaces in Czochralski crystal growth. Internat. J. Numer. Methods in Fluids 9, 453–492 (1989)CrossRefGoogle Scholar
  12. 12.
    Stone, H.L.: Iterative solution of implicit approximations of multidimensional partial differential equations. SIAM J. Num. Anal. 5, 530–558 (1968)MATHCrossRefGoogle Scholar
  13. 13.
    Sun, D.: A Multiblock and Multigrid Technique for Simulations of Material Processing, Ph.D. Thesis, State University of New York (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Dana Petcu
    • 1
    • 2
  • Daniel Vizman
    • 3
  • Marcin Paprzycki
    • 4
  1. 1.Computer Science DepartmentWestern University 
  2. 2.Institute e-AustriaTimişoara
  3. 3.Physics DepartmentWestern University of TimişoaraRomania
  4. 4.Computer Sciecne InstituteSWPSWarsawPoland

Personalised recommendations