GWAS on GPUs: Streaming Data from HDD for Sustained Performance

  • Lucas Beyer
  • Paolo Bientinesi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8097)


In the context of genome-wide association studies (GWAS), one has to solve long sequences of generalized least-squares problems; such a task has two limiting factors: execution time –often in the range of days or weeks– and data management –data sets in the order of Terabytes. We present an algorithm that obviates both issues. By pipelining the computation, and thanks to a sophisticated transfer mechanism, we stream data from hard disk to main memory to GPUs and achieve sustained performance; with respect to a highly-optimized CPU implementation, our algorithm shows a speedup of 2.6x. Moreover, the approach lends itself to multiple GPUs and attains almost perfect scalability. When using 4 GPUs, we observe speedups of 9x over the aforementioned CPU implementation, and 488x over ProbABEL, a widespread biology library.


GWAS generalized least-squares computational biology out-of-core computation high-performance multiple GPUs data transfer multibuffering streaming big data 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Genome-Wide Association Studies,
  2. [2]
    Fabregat-Traver, D., Bientinesi, P.: Computing Petaflops over Terabytes of Data: The Case of Genome-Wide Association Studies (2012)Google Scholar
  3. [3]
    Catalog of Genome-Wide Association Studies,
  4. [4]
    Fabregat-Traver, D., Aulchenko, Y.S., Bientinesi, P.: Solving Sequences of Generalized Least-Squares Problems on Multi-threaded Architectures (2012)Google Scholar
  5. [5]
  6. [6]
    Aulchenko, Y.S., Struchalin, M.V., Van Duijn, C.M.: ProbABEL package for genome-wide association analysis of imputed data. BMC Bioinformatics 11, 134 (2010)CrossRefGoogle Scholar
  7. [7]
    Beyer, L.: Exploiting Graphics Accelerators for Computational BiologyGoogle Scholar
  8. [8]
    Volkov, V., Demmel, J.W.: Benchmarking GPUs to tune dense linear algebraGoogle Scholar
  9. [9]
    Quintana-Ortí, G., Igual, F.D., Marqués, M., Quintana-Ortí, E.S., Van de Geijn, R.A.: A run-time system for programming out-of-core matrix algorithms-by-tiles on multithreaded architectures.Google Scholar
  10. [10]
    Yung, L.S., Yang, C., Wan, X., Yu, W.: GBOOST: a GPU-based tool for detecting gene–gene interactions in genome–wide case control studiesGoogle Scholar
  11. [11]
    Lee, S., Kwon, M.-S., Huh, I.-S., Park, T.: CUDA-LR: CUDA-accelerated Logistic Regression Analysis Tool for Gene-Gene Interaction for Genome-Wide Association StudyGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Lucas Beyer
    • 1
  • Paolo Bientinesi
    • 1
  1. 1.Aachen Institute for advanced study in Computational Engineering ScienceRWTH Aachen UniversityGermany

Personalised recommendations