Advertisement

Parameterized Design and Evaluation of Bandwidth Compressor for Floating-Point Data Streams in FPGA-Based Custom Computing

  • Tomohiro Ueno
  • Yoshiaki Kono
  • Kentaro Sano
  • Satoru Yamamoto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7806)

Abstract

We are applying bandwidth compression to enhance performance of FPGA-based custom computing. This paper presents and evaluates hardware design of a bandwidth compressor and decompressor for a floating-point data stream of various bit width. We show their structures parameterized for a bit width of an input word. Through FPGA-based prototype implementation, we evaluate the resource utilization, frequency, and compression ratio. The expermental results show that the compressor and decompressor for 32-bit and 64-bit floating-point numbers achieve bandwidth reduction at a ratio of 3.1 and 1.8 for 2D data of fluid dynamics computation, while they require only small area and operate at higher than 200MHz.

Keywords

bandwidth compression floating-point data stream custom computing parameterized design 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    bzip2 (2010), http://www.bzip.org/
  2. 2.
    Burtscher, M., Ratanaworabhan, P.: FPC: a high-speed compressor for double-precision floating-point data. IEEE Trans. on Computers 58(1), 18–31 (2009)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Engelson, V., Fritzson, D., Fritzson, P.: Lossless compression of high-volume numerical data from simulations. In: Proceedings of Data Compression Conference (DCC), pp. 574–586 (September 2000)Google Scholar
  4. 4.
    Franaszek, P.A., Lastras-Montaño, L.A., Peng, S., Robinson, J.T.: Data compression with restricted parsings. In: Proc. of the Data Compression Conf. (2006)Google Scholar
  5. 5.
    Healy, D., Mitchell, O.: Digital video bandwidth compression using block truncation coding. IEEE Trans. on Communications COM-29(12), 1809–1817 (1981)CrossRefGoogle Scholar
  6. 6.
    Ibarria, L., Lindstrom, P., Rossignac, J., Szymczak, A.: Out-of-core compression and decompression of large n-dimensional scalar fields. In: Proceedings of Eurographics, vol. 22(3), pp. 343–348 (September 2003)Google Scholar
  7. 7.
    Isenburg, M., Lindstrom, P., Snoeyink, J.: Lossless compression of predicted floating-point geometry. Computer-Aided Design 37(8), 869–877 (2005)zbMATHCrossRefGoogle Scholar
  8. 8.
    Katahira, K., Sano, K., Yamamoto, S.: FPGA-based lossless compressors of floating-point data streams to enhance memory bandwidth. In: Proceedings of the International Conference on Application-specific Systems, Architectures and Processors, pp. 246–253 (July 2010)Google Scholar
  9. 9.
    Kono, Y., Sano, K., Yamamoto, S.: Scalability analysis of tightly-coupled FPGA-cluster for lattice boltzmann computation. In: Proc. of the 22nd Intl. Conf. on Field-Programmable Logic and Applications, pp. 120–127 (August 2012)Google Scholar
  10. 10.
    Lim, J.S., Oppenheim, A.V.: Enhancement and bandwidth compression of noisy speech. In: Proceedings of the IEEE, vol. 67(12), pp. 1586–1604 (December 1979)Google Scholar
  11. 11.
    Lindstrom, P., Isenburg, M.: Fast and efficient compression of floating-point data. IEEE Transactions on Visual and Computer Graphics 12(5), 1245–1250 (2006)CrossRefGoogle Scholar
  12. 12.
    Ratanaworabhan, P., Ke, J., Burtscher, M.: Fast lossless compression of scientific floating-point data. In: Proceedings of Data Compression Conference, pp. 133–142 (March 2006)Google Scholar
  13. 13.
    Sano, K., Hatsuda, Y., Yamamoto, S.: Scalable streaming-array of simple soft-processors for stencil computations with constant memory-bandwidth. In: Proceedings of the IEEE Symposium on Field-Programmable Custom Computing Machines, pp. 234–241 (May 2011)Google Scholar
  14. 14.
    Sano, K., Katahira, K., Yamamoto, S.: Segment-parallel predictor for FPGA-based hardware compressor and decompressor of floating-point data streams to enhance memory i/o bandwidth. In: Proceedings of the Data Compression Conference, pp. 416–425 (March 2010)Google Scholar
  15. 15.
    Sukhwani, B., Abali, B., Brezzo, B., Asaad, S.: High-throughput, lossless data compression on FPGAs. In: 2011 IEEE 19th Annual International Symposium on Field-Programmable Custom Computing Machines, pp. 113–116 (May 2011)Google Scholar
  16. 16.
    Terasic Technologies, http://www.terasic.com
  17. 17.
    The GNU MPFR Library, http://www.mpfr.org
  18. 18.
    Tomari, H., Inaba, M., Hiraki, K.: Compressing floating-point number stream for numerical applications. In: 2010 First International Conference on Networking and Computing, pp. 112–119 (November 2010)Google Scholar
  19. 19.
    Tremaine, R.B., Franaszek, P.A., Robinson, J.T., Schulz, C.O., Smith, T.B., Wazlowski, M.E., Bland, P.M.: Ibm memory expansion technology (mxt). IBM Journal of Research and Development 45(2), 271–285 (2001)CrossRefGoogle Scholar
  20. 20.
    Ueno, T., Kono, Y., Sano, K., Yamamoto, S.: FPGA-based implementation of compact compressor and decompressor of floating-point data-stream for bandwidth reduction. In: Proceedings of the 2012 International Conference on Engineering of Reconfigurable Systems and Algorithms (ERSA 2012) (July 2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Tomohiro Ueno
    • 1
  • Yoshiaki Kono
    • 1
  • Kentaro Sano
    • 1
  • Satoru Yamamoto
    • 1
  1. 1.Graduate School of Information SciencesTohoku UniversityAoba-kuJapan

Personalised recommendations