Performance Evaluation of Parallel Sparse Matrix–Vector Products on SGI Altix3700

  • Hisashi Kotakemori
  • Hidehiko Hasegawa
  • Tamito Kajiyama
  • Akira Nukada
  • Reiji Suda
  • Akira Nishida
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4315)

Abstract

The present paper discusses scalable implementations of sparse matrix-vector products, which are crucial for high performance solutions of large-scale linear equations, on a cc-NUMA machine SGI Altix3700. Three storage formats for sparse matrices are evaluated, and scalability is attained by implementations considering the page allocation mechanism of the NUMA machine. Influences of the cache/memory bus architectures on the optimum choice of the storage format are examined, and scalable converters between storage formats shown to facilitate exploitation of storage formats of higher performance.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barrett, R., et al.: Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods. SIAM, Philadelphia (1994)Google Scholar
  2. 2.
    Duff, I., Grimes, R., Lewis, J.: Sparse matrix test problems. ACM Trans. Math. Soft. 15, 1–14 (1989)MATHCrossRefGoogle Scholar
  3. 3.
    Saad, Y.: SPARSKIT: a basic took kit for sparse matrix computations, version 2, (June 1994), http://www.cs.umn.edu/~saad/software/SPARSKIT/sparskit.html
  4. 4.
    Kincaid, D., Oppe, T., Respess, J., Young, D.: ITPACKV2C User’s Guide, Report CNA191. The University of Texas at Austin (1984)Google Scholar
  5. 5.
    Saad, Y.: Krylov subspace methods on supercomputers. SIAM J. Sci. Stat. Comput. 10, 1200–1232 (1989)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
  7. 7.
    Dongarra, J., Eijkhout, V., Kalhan, A.: Reverse communication interface for linear algebra templates for iterative methods. Technical Report UT-CS-95-291, University of Tennessee (May 1995)Google Scholar
  8. 8.
    Balay, S., Buschelman, K., Eijkhout, V., Gropp, W., Kaushik, D., Knepley, M., McInnes, L., Smith, B., Zhang, H.: PETSc users manual. Technical Report ANL-95/11, Argonne National Laboratory (August 2004)Google Scholar
  9. 9.
    Tuminaro, R.S., Heroux, M., Hutchinson, S.A., Shadid, J.N.: Official Aztec user’s guide, version 2.1. Technical Report SAND99-8801J, Sandia National Laboratories (November 1999)Google Scholar
  10. 10.
    Toledo, S.: Improving the memory-system performance of sparse-matrix vector multiplication. IBM Journal of Research and Development 41(6), 711–725 (1997)CrossRefGoogle Scholar
  11. 11.
    Pinar, A., Heath, M.T.: Improving Performance of Sparse Matrix-Vector Multiplication. Supercomputing 99 (1999)Google Scholar
  12. 12.
    Im, E.J.: Optimizing the performance of sparse matrix-vector multiplication. Ph.D. thesis, University of California (May 2000)Google Scholar
  13. 13.
    Demmel, J., Dongarra, J., Eijkhout, V., Fuentes, E., Petitet, A., Vuduc, R., Whaley, R.C., Yelick, K.: Self adapting linear algebra algorithms and software. Proceedings of the IEEE: Special Issue on Program Generation, Optimization, and Adaptation 93(2), 293–312 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Hisashi Kotakemori
    • 1
  • Hidehiko Hasegawa
    • 2
  • Tamito Kajiyama
    • 1
  • Akira Nukada
    • 1
  • Reiji Suda
    • 1
  • Akira Nishida
    • 1
  1. 1.CREST, Japan Science and Technology Agency Graduate School of Information Science and TechnologyUniversity of TokyoTokyoJapan
  2. 2.CREST, Japan Science and Technology Agency Graduate School of Library, Information and Media StudiesUniversity of TsukubaTsukubaJapan

Personalised recommendations