Skip to main content
Springer Nature Link
Log in

On the Design, Development, and Analysis of Optimized Matrix-Vector Multiplication Routines for Coprocessors

  • Conference paper
  • First Online:
High Performance Computing (ISC High Performance 2015)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 9137))

Included in the following conference series:

Abstract

The manycore paradigm shift, and the resulting change in modern computer architectures, has made the development of optimal numerical routines extremely challenging. In this work, we target the development of numerical algorithms and implementations for Xeon Phi coprocessor architecture designs. In particular, we examine and optimize the general and symmetric matrix-vector multiplication routines (gemv/symv), which are some of the most heavily used linear algebra kernels in many important engineering and physics applications. We describe a successful approach on how to address the challenges for this problem, starting with our algorithm design, performance analysis and programing model and moving to kernel optimization. Our goal, by targeting low-level and easy to understand fundamental kernels, is to develop new optimization strategies that can be effective elsewhere for use on manycore coprocessors, and to show significant performance improvements compared to existing state-of-the-art implementations. Therefore, in addition to the new optimization strategies, analysis, and optimal performance results, we finally present the significance of using these routines/strategies to accelerate higher-level numerical algorithms for the eigenvalue problem (EVP) and the singular value decomposition (SVD) that by themselves are foundational for many important applications.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. CUDA Cublas Library. https://developer.nvidia.com/cublas

  2. MAGMA. http://icl.cs.utk.edu/magma/

  3. Abdelfattah, A., Keyes, D., Ltaief, H.: Systematic approach in optimizing numerical memory-bound kernels on GPU. In: Caragiannis, I., et al. (eds.) Euro-Par Workshops 2012. LNCS, vol. 7640, pp. 207–216. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  4. Agullo, E., Augonnet, C., Dongarra, J., Ltaief, H., Namyst, R., Thibault, S.,Tomov, S.: Faster, cheaper, better - a hybridization methodology to develop linear algebra software for GPUs.In: Mei, W., Hwu, W. (eds.) GPU Computing Gems, vol. 2. Morgan Kaufmann, September 2010

    Google Scholar 

  5. Anderson, E., Bai, Z., Bischof, C., Blackford, S.L., Demmel, J.W., Dongarra, J.J., Croz, J.D., Greenbaum, A., Hammarling, S., McKenney, A., Sorensen, D.C.: LAPACK User’s Guide, 3rd edn. Society for Industrial and Applied Mathematics, Philadelphia (1999)

    Book  MATH  Google Scholar 

  6. Anderson, M.J., Sheffield, D., Keutzer, K.: A predictive model for solving small linear algebra problems in gpu registers. In: IEEE 26th International Parallel Distributed Processing Symposium (IPDPS) (2012)

    Google Scholar 

  7. Bosilca, G., Bouteiller, A., Danalis, A., Hérault, T., Lemarinier, P., Dongarra, J.: DAGuE: a generic distributed DAG engine for high performance computing. Parallel Comput. 38(1–2), 37–51 (2012)

    Article  Google Scholar 

  8. Buttari, A., Langou, J., Kurzak, J., Dongarra, J.: A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput. 35(1), 38–53 (2009)

    Article  MathSciNet  Google Scholar 

  9. Chan, E., Quintana-Orti, E.S., Quintana-Orti, G., van de Geijn, R.: Supermatrix out-of-order scheduling of matrix operations for smp and multi-core architectures. In: Proceedings of the Nineteenth Annual ACM Symposium on Parallel Algorithms and Architectures, SPAA 2007, pp. 116–125. ACM, New York (2007)

    Google Scholar 

  10. Dong, T., Haidar, A., Luszczek, P., Harris, A., Tomov, S., Dongarra, J.: LU Factorization of small matrices: accelerating batched DGETRF on the GPU. In: Proceedings of 16th IEEE International Conference on High Performance and Communications (HPCC 2014), August 2014

    Google Scholar 

  11. Dong, T., Haidar, A., Tomov, S., Dongarra, J.: A fast batched Cholesky factorization on a GPU. In: Proceedings of 2014 International Conference on Parallel Processing (ICPP-2014), September 2014

    Google Scholar 

  12. Dong, T., Dobrev, V., Kolev, T., Rieben, R., Tomov, S., Dongarra, J.: A step towards energy efficient computing: Redesigning a hydrodynamic application on CPU-GPU. In: IEEE 28th International Parallel Distributed Processing Symposium (IPDPS) (2014)

    Google Scholar 

  13. Dongarra, J., Du Croz, J., Duff, I., Hammarling, S.: Algorithm 679: a set of level 3 basic linear algebra subprograms. ACM Trans. Math. Soft. 16(1), 18–28 (1990)

    Article  MATH  Google Scholar 

  14. Dongarra, J., Gates, M., Haidar, A., Jia, Y., Kabir, K., Luszczek, P., Tomov, S.: Portable HPC programming on intel many-integrated-core hardware with MAGMA port to Xeon Phi. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Waśniewski, J. (eds.) PPAM 2013, Part I. LNCS, vol. 8384, pp. 571–581. Springer, Heidelberg (2014)

    Chapter  Google Scholar 

  15. Dongarra, J.J., Sorensen, D.C., Hammarling, S.J.: Block reduction of matrices to condensed forms for eigenvalue computations. J. Comput. Appl. Math. 27(1–2), 215–227 (1989). Special Issue on Parallel Algorithms for Numerical Linear Algebra

    Article  MATH  MathSciNet  Google Scholar 

  16. Fuller, S.H., Millett, I. (eds.): The Future of Computing Performance: Game Over or Next Level?. The National Academies Press, Washington (2011)

    Google Scholar 

  17. Haidar, A., Cao, C., Yarkhan, A., Luszczek, P., Tomov, S., Kabir, K., Dongarra, J.: Unified development for mixed multi-gpu and multi-coprocessor environments using a lightweight runtime environment. In: Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium, IPDPS 2014, pp. 491–500. IEEE Computer Society, Washington, DC (2014)

    Google Scholar 

  18. Haidar, A., Dong, T., Luszczek, P., Tomov, S., Dongarra, J.: Batched matrix computations on hardware accelerators based on GPUs. Int. J. High Perform. Comput. Appl. February 2015. doi:10.1177/1094342014567546

  19. Haidar, A., Dongarra, J., Kabir, K., Gates, M., Luszczek, P., Tomov, S., Jia, Y.: Hpc programming on intel many-integrated-core hardware with magma port to xeon phi. Scientific Programming, 23, January 2015

    Google Scholar 

  20. Haidar, A., Luszczek, P., Tomov, S., Dongarra, J.: Towards batched linear solvers on accelerated hardware platforms. In: Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2015. ACM, San Francisco, February 2015

    Google Scholar 

  21. Im, E.-J., Yelick, K., Vuduc, R.: Sparsity: Optimization framework for sparse matrix kernels. Int. J. High Perform. Comput. Appl. 18(1), 135–158 (2004)

    Article  Google Scholar 

  22. Intel. Math kernel library. https://software.intel.com/en-us/en-us/intel-mkl/

  23. John McCalpin. STREAM: Sustainable Memory Bandwidth in High Performance Computers. (http://www.cs.virginia.edu/stream/)

  24. Messer, O.E.B., Harris, J.A., Parete-Koon, S., Chertkow, M.A.: Multicore and accelerator development for a leadership-class stellar astrophysics code. In: Manninen, P., Öster, P. (eds.) PARA. LNCS, vol. 7782, pp. 92–106. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  25. Molero, J.M., Garzón, E.M., García, I., Quintana-Ortí, E.S., Plaza, A.: Poster: a batched Cholesky solver for local RX anomaly detection on GPUs, PUMPS (2013)

    Google Scholar 

  26. Nath, R., Tomov, S., Dong, T., Dongarra, J.: Optimizing symmetric dense matrix-vector multiplication on GPUs. In: Proceedings of International Conference for High Performance Computing. Networking, Storage and Analysis, Nov 2011

    Google Scholar 

  27. Tomov, S., Dongarra, J., Baboulin, M.: Towards dense linear algebra for hybrid gpu accelerated manycore systems. Parellel Comput. Syst. Appl. 36(5–6), 232–240 (2010)

    Article  MATH  Google Scholar 

  28. Tomov, S., Nath, R., Ltaief, H., Dongarra, J.: Dense linear algebra solvers for multicore with GPU accelerators. In: Proceedings of the 2010 IEEE International Parallel & Distributed Processing Symposium, IPDPS 2010, pp. 1–8. IEEE Computer Society, Atlanta, 19–23 April 2010. http://dx.doi.org/10.1109/IPDPSW.2010.5470941. doi:10.1109/IPDPSW.2010.5470941

  29. Tomov, S., Nath, R., Dongarra, J.: Accelerating the reduction to upper Hessenberg, tridiagonal, and bidiagonal forms through hybrid GPU-based computing. Parallel Comput. 36(12), 645–654 (2010)

    Article  MATH  MathSciNet  Google Scholar 

  30. Volkov, V., Demmel, J.: Benchmarking GPUs to tune dense linear algebra.In: Supercomputing 2008. IEEE (2008)

    Google Scholar 

  31. Yeralan, S.N., Davis, T.A., Ranka, S.: Sparse mulitfrontal QR on the GPU. Technical report, University of Florida Technical Report (2013)

    Google Scholar 

Download references

Acknowledgments

This material is based upon work supported by the National Science Foundation under Grant No. ACI-1339822, the Department of Energy, and Intel. The results were obtained in part with the financial support of the Russian Scientific Fund, Agreement N14-11-00190.

Author information

Authors and Affiliations

  1. University of Tennessee Knoxville, Knoxville, USA

    Khairul Kabir, Azzam Haidar, Stanimire Tomov & Jack Dongarra

  2. Oak Ridge National Laboratory, Oak Ridge, USA

    Jack Dongarra

  3. University of Manchester, Manchester, UK

    Jack Dongarra

Authors
  1. Khairul Kabir
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Azzam Haidar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Stanimire Tomov
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jack Dongarra
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Azzam Haidar .

Editor information

Editors and Affiliations

  1. Deutsches Klimarechenzentrum (DKRZ), Hamburg, Germany

    Julian M. Kunkel

  2. Deutsches Klimarechenzentrum (DKRZ), Hamburg, Germany

    Thomas Ludwig

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Kabir, K., Haidar, A., Tomov, S., Dongarra, J. (2015). On the Design, Development, and Analysis of Optimized Matrix-Vector Multiplication Routines for Coprocessors. In: Kunkel, J., Ludwig, T. (eds) High Performance Computing. ISC High Performance 2015. Lecture Notes in Computer Science(), vol 9137. Springer, Cham. https://doi.org/10.1007/978-3-319-20119-1_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-20119-1_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-20118-4

  • Online ISBN: 978-3-319-20119-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics