Advertisement

An Error Correction Solver for Linear Systems: Evaluation of Mixed Precision Implementations

  • Hartwig Anzt
  • Vincent Heuveline
  • Björn Rocker
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6449)

Abstract

This paper proposes an error correction method for solving linear systems of equations and the evaluation of an implementation using mixed precision techniques.

While different technologies are available, graphic processing units (GPUs) have been established as particularly powerful coprocessors in recent years. For this reason, our error correction approach is focused on a CUDA implementation executing the error correction solver on the GPU.

Benchmarks are performed both for artificially created matrices with preset characteristics as well as matrices obtained from finite element discretizations of fluid flow problems.

Keywords

Mixed Precision Iterative Refinement Method Computational Fluid Dynamics (CFD) Large Sparse Linear Systems Hardware-aware Computing GPGPU 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Microprocessor Standards Committee of the IEEE Computer Society: IEEE Standard for Floating-Point Arithmetic (2008)Google Scholar
  2. 2.
    Saad, Y.: Iterative Methods for Sparse Linear Systems. Society for Industrial and Applied Mathematics, Philadelphia (2003)CrossRefzbMATHGoogle Scholar
  3. 3.
    van der Vorst, H.A.: Iterative Krylov Methods for Large Linear Systems. Cambridge University Press, Cambridge (2003)CrossRefzbMATHGoogle Scholar
  4. 4.
    Higham, N.J.: Accuracy and Stability of Numerical Algorithms. Society for Industrial and Applied Mathematics, Philadelphia (1996)zbMATHGoogle Scholar
  5. 5.
    Dongarra, J.J., Duff, I.S., Sorensen, D.C., van der Vorst, H.A.: Numerical Linear Algebra for High-Performance Computers. Society for Industrial and Applied Mathematics, Philadelphia (1998)CrossRefzbMATHGoogle Scholar
  6. 6.
    Demmel, J.W.: Applied Numerical Linear Algebra. Society for Industrial and Applied Mathematics, Philadelphia (1997)CrossRefzbMATHGoogle Scholar
  7. 7.
    Bai, Z., Demmel, J., Dongarra, J.J., Ruhe, A., van der Vorst, H.: Templates for the Solution of Algebraic Eigenvalue Problems. Society for Industrial and Applied Mathematics, Philadelphia (2000)CrossRefzbMATHGoogle Scholar
  8. 8.
    Göddeke, D., Strzodka, R., Turek, S.: Performance and accuracy of hardware–oriented native–, emulated– and mixed–precision solvers in FEM simulations. Fakultät für Mathematik, TU Dortmund (2007)Google Scholar
  9. 9.
    Buttari, A., Dongarra, J., Langou, J., Langou, J., Luszcek, P., Kurzak, J.: Mixed Precision Iterative Refinement Techniques for the Solution of Dense Linear Systems (2007)Google Scholar
  10. 10.
    Baboulin, M., Buttari, A., Dongarra, J., Langou, J., Langou, J., Luszcek, P., Kurzak, J., Tomov, S.: Accelerating Scientific Computations with Mixed Precision Algorithms (2008)Google Scholar
  11. 11.
    Strzodka, R., Göddeke, D.: Pipelined Mixed Precision Algorithms on FPGAs for Fast and Accurate PDE Solvers from Low Precision Components. In: IEEE Proceedings on Field–Programmable Custom Computing Machines (FCCM 2006). IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  12. 12.
    Göddeke, D., Strzodka, R.: Performance and accuracy of hardware–oriented native–, emulated– and mixed–precision solvers in FEM simulations (Part 2: Double Precision GPUs). Fakultät für Mathematik, TU Dortmund (2008)Google Scholar
  13. 13.
    NVIDIA CUDA Compute Unified Device Architecture Programming Guide. NVIDIA Corporation. edit. 2.3.1 (2009)Google Scholar
  14. 14.
    NVIDIA CUDA CUBLAS Library Programming Guide. NVIDIA Corporation. edit. 1.0 (2007)Google Scholar
  15. 15.
    Technical Brief NVIDIA GeForce GTX 200 GPU Architectural Overview. NVIDIA Corporation (2008)Google Scholar
  16. 16.
    InstitutsCluster User Guide. Universität Karlsruhe (TH), Steinbuch Centre for Computing. edit. 0.92 (2008)Google Scholar
  17. 17.
    Heuveline, V., Rocker, B., Ronnas, S.: Numerical Simulation on the SiCortex Supercomputer Platform: a Preliminary Evaluation. EMCL Preprint Series (2009)Google Scholar
  18. 18.
    BLAS LAPACK User’s Guide. Fujitsu (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Hartwig Anzt
    • 1
  • Vincent Heuveline
    • 1
  • Björn Rocker
    • 1
  1. 1.Institute for Applied and Numerical Mathematics 4Karlsruhe Institute of Technology (KIT)KarlsruheGermany

Personalised recommendations