Advertisement

HiFlow3: A Hardware-Aware Parallel Finite Element Package

  • H. Anzt
  • W. Augustin
  • M. Baumann
  • T. Gengenbach
  • T. Hahn
  • A. Helfrich-Schkarbanenko
  • V. Heuveline
  • E. Ketelaer
  • D. Lukarski
  • A. Nestler
  • S. Ritterbusch
  • S. Ronnas
  • M. Schick
  • M. Schmidtobreick
  • C. Subramanian
  • J.-P. Weiss
  • F. Wilhelm
  • M. Wlotzka
Conference paper

Abstract

The goal of this paper is to describe the hardware-aware parallel C++ finite element package HiFlow3. HiFlow3 aims at providing a powerful platform for simulating processes modelled by partial differential equations. Our vision is to solve boundary value problems in an appropriate way by coupling numerical simulations with modern software design and state-of-the-art hardware technologies. The main functionalities for mapping the mathematical model into parallel software are implemented in the three core modules Mesh, DoF/FEM and Linear Algebra (LA). Parallelism is realized on two levels. The modules provide efficient MPI-based distributed data structures to achieve performance on large HPC systems but also on stand-alone workstations. Additionally, the hardware-aware cross-platform approach in the LA module accelerates the solution process by exploiting the computing power from emerging technologies like multi-core CPUs and GPUs. In this context performance evaluation on different hardware-architectures will be demonstrated.

Keywords

Parallel finite element software High performance computing Numerical simulation Hardware-aware computing GPGPU 

Notes

Acknowledgements

The Shared Research Group 16-1 received financial support by the Concept for the Future of Karlsruhe Institute of Technology in the framework of the German Excellence Initiative and the industrial collaboration partner Hewlett-Packard. The United Airways project thanks the Städtisches Klinikum Karlsruhe for providing us with CT-data for the simulations of medical processes.

References

  1. 1.
  2. 2.
    Baron, L., Gengenbach, T., Henn, T., Heppt, W., Heuveline, V., Kratzke, J., Krause, M.J.: United airways: numerical simulation of the human respiratory system. http://www.united-airways.eu (2011)
  3. 3.
    Buchty, R., Heuveline, V., Karl, W., Weiss, J.P.: A Survey on Hardware-aware and Heterogeneous Computing on Multicore Processors and Accelerators. EMCL Preprint Series. KIT, Karlsruhe (2009)Google Scholar
  4. 4.
    Heuveline, V., et al.: HiFlow3 – A Flexible and Hardware-Aware Parallel Finite Element Package. EMCL Preprint Series. KIT, Karlsruhe (2010)Google Scholar
  5. 5.
    Heuveline, V., Lukarski, D., Weiss, J.P.: Scalable multi-coloring preconditioning for multi-core CPUs and GPUs. In: UCHPC’10, Euro-Par 2010 Parallel Processing Workshops, vol. 6586, pp. 389–397. Springer/LNCS, Heidelberg (2010)Google Scholar
  6. 6.
    Heuveline, V., Subramanian, C., Lukarski, D., Weiss, J.P.: A multi-platform linear algebra toolbox for finite element solvers on heterogeneous clusters. In: PPAAC’10, IEEE Cluster 2010 Workshops. Heraklion, Crete, Greece (2010).Google Scholar
  7. 7.
    Heuveline, V., Lukarski, D., Trost, N., Weiss, J.P.: Parallel Smoothers for Matrix-Based Multigrid Methods on Unstructured Meshes Using Multicore CPUs and GPUs. EMCL Preprint Series. KIT, Karlsruhe (2011)Google Scholar
  8. 8.
    Heuveline, V., Lukarski, D., Weiss, J.P.: Enhanced Parallel ILU(p)-Based Preconditioners for Multi-core CPUs and GPUs – The Power(q)-Pattern Method. EMCL Preprint Series. KIT, Karlsruhe (2011)Google Scholar
  9. 9.
    Heuveline, V., Subramanian, C., Lukarski, D., Weiss, J.P.: Parallel preconditioning and modular finite element solvers on hybrid CPU-GPU systems. In: Proceedings of ParEng 2011, Paper 36. Civil-Comp Press, Stirlingshire (2011)Google Scholar
  10. 10.
    Karypis, G., Kumar, V.: A fast and highly quality multilevel scheme for partitioning irregular graphs. SIAM J. Sci. Comput. 20(1), 359–392 (1999)Google Scholar
  11. 11.
    Logg, A.: Efficient representation of computational meshes. Int. J. Comput. Sci. Eng. 4(4), 283–295 (2009)Google Scholar
  12. 12.
    MPI Forum: MPI: a message-passing interface standard. Version 2.2. Available at: http://www.mpi-forum.org (2009)
  13. 13.
    Ronnas, S., Gengenbach, T., Ketelaer, E., Heuveline, V.: Design and Implementation of Distributed Meshes in HiFlow3. In: Proceedings of CiHPC 2010, Schwetzingen. Proceedings of CiHPC 2011. (accepted)Google Scholar
  14. 14.
    Schieweck, F.: A General Transfer Operator for Arbitrary Finite Element Spaces. Magdeburg University, Magdeburg (2000)Google Scholar
  15. 15.
    VTK – The Visualization Toolkit: http://www.vtk.org/

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • H. Anzt
    • 1
  • W. Augustin
    • 1
  • M. Baumann
    • 1
  • T. Gengenbach
    • 1
  • T. Hahn
    • 1
  • A. Helfrich-Schkarbanenko
    • 1
  • V. Heuveline
    • 1
  • E. Ketelaer
    • 1
  • D. Lukarski
    • 1
  • A. Nestler
    • 1
  • S. Ritterbusch
    • 1
  • S. Ronnas
    • 1
  • M. Schick
    • 1
  • M. Schmidtobreick
    • 1
  • C. Subramanian
    • 1
  • J.-P. Weiss
    • 1
  • F. Wilhelm
    • 1
  • M. Wlotzka
    • 1
  1. 1.Engineering Mathematics and Computing Lab (EMCL)Karlsruhe Institute of Technology (KIT)KarlsruheGermany

Personalised recommendations