Improvement of BLASTp on the FPGA-Based High-Performance Computer RIVYERA

  • Lars Wienbrandt
  • Daniel Siebert
  • Manfred Schimmler
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7292)


NCBI BLASTp plays the major role of protein database searches already for years. However, with today’s growth of sequence database sizes, it becomes more inefficient with standard PC architectures. One solution to address this problem was already presented in our previous implementation, published in [16], taking advantages of the massive parallelization provided by the FPGA-based high-performance computer RIVYERA [3].

The analysis of bottlenecks in our BLASTp pipeline showed the urgent need to speed up the two-hit finder component, as well as the postprocessing on the PC. After a complete redesign of the two-hit finder and the insertion of a new “gapped extension” filter, we achieve a speedup of up to 376, compared to one thread of a fully utilized 2x Intel Xeon E5520 PC system at \(2.26\ensuremath{\mathrm{GHz}} \) running original NCBI BLASTp v. 2.2.25+. This is about two times the performance of our previous implementation.


Clock Cycle Query Sequence Basic Local Alignment Search Tool Previous Implementation Subject Sequence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
  3. 3.
    SciEngines GmbH,
  4. 4.
    Superfamily HMM library and genome assignments server,
  5. 5.
    Altschul, S.F., Gish, W., Miller, W., Myers, E.W., Lipman, D.J.: Basic Local Alignment Search Tool. Journal of Molecular Biology 215(3), 403–410 (1990)Google Scholar
  6. 6.
    Altschul, S.F., Madden, T.L., Schäffer, A.A., Zhang, J., Zhang, Z., Miller, W., Lipman, D.J.: Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Research 25, 3389–3402 (1997)CrossRefGoogle Scholar
  7. 7.
    Guo, X., Wang, H., Devabhaktuni, V.: Design of a FPGA-Based Parallel Architecture for BLAST Algorithm with Multi-hits Detection. In: Proceedings of ITNG 2011, pp. 689–694. IEEE Computer Society (2011)Google Scholar
  8. 8.
    Jacob, A., Lancaster, J., Buhler, J., Harris, B., Chamberlain, R.D.: Mercury BLASTp: Accelerating Protein Sequence Alignment. ACM Transactions on Reconfigurable Technology and Systems 1, 9:1–9:44 (2008)Google Scholar
  9. 9.
    Kasap, S., Benkrid, K., Liu, Y.: Design and Implementation of an FPGA-based Core for Gapped BLAST Sequence Alignment with the Two-Hit Method. Engineering Letters 16, 443–452 (2008)Google Scholar
  10. 10.
    Liu, W., Schmidt, B., Müller-Wittig, W.: CUDA-BLASTP: Accelerating BLASTP on CUDA-Enabled Graphics Hardware. IEEE/ACM Transactions on Computational Biology and Bioinformatics 8, 1678–1684 (2011)CrossRefGoogle Scholar
  11. 11.
    Mahram, A., Herbordt, M.C.: Fast and Accurate BLASTP: Acceleration with Multiphase FPGA-Based Prefiltering. In: Proceedings of ICS 2010, pp. 73–28 (2010)Google Scholar
  12. 12.
    Needleman, S.B., Wunsch, C.D.: A general method applicable to the search for similarities in the amino acid sequence of two proteins. Journal of Molecular Biology 48(3), 443–453 (1970)CrossRefGoogle Scholar
  13. 13.
    Schimmler, M., Wienbrandt, L., Gneysu, T., Bissel, J.: COPACOBANA: A Massively Parallel FPGA-Based Computer Architecture. In: Schmidt, B. (ed.) Bioinformatics – High Performance Parallel Computer Architectures, pp. 223–262. CRC Press (2010)Google Scholar
  14. 14.
    Smith, T.F., Waterman, M.S.: Identification of common molecular subsequences. Journal of Molecular Biology 147, 195–197 (1981)CrossRefGoogle Scholar
  15. 15.
    Sotiriades, E., Dollas, A.: A General Reconfigurable Architecture for the BLAST Algorithm. VLSI Signal Processing 48, 198–208 (2007)Google Scholar
  16. 16.
    Wienbrandt, L., Baumgart, S., Bissel, J., Schatz, F., Schimmler, M.: Massively parallel FPGA-based implementation of BLASTp with the two-hit method. In: ICCS 2011. Procedia Computer Science, vol. 1, pp. 1967–1976 (2011)Google Scholar
  17. 17.
    Wienbrandt, L., Baumgart, S., Bissel, J., Yeo, C.M.Y., Schimmler, M.: Using the reconfigurable massively parallel architecture COPACOBANA 5000 for applications in bioinformatics. In: ICCS 2010. Procedia Computer Science, vol. 1, pp. 1027–1034 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Lars Wienbrandt
    • 1
  • Daniel Siebert
    • 1
  • Manfred Schimmler
    • 1
  1. 1.Department of Computer ScienceChristian-Albrechts-University of KielKielGermany

Personalised recommendations