Advertisement

Design Space Exploration for Configurable Architectures and the Role of Modeling, High-Level Program Analysis and Learning Techniques

  • Pedro C. Diniz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3133)

Abstract

Reconfigurable computing architectures promise to substantially increase the performance of computations through the customization of data-path and storage structures best suited to the specific needs of each computation. The need to synthesize, either fully or partially, the structure of the target architecture while simultaneously attempting to optimize the mapping of the computation to that architecture creates a vast design space exploration (DSE) challenge. In this paper we describe current approaches to this DSE problem using program analysis, estimation, modeling and empirical optimization techniques. We also describe a unified approach for this DSE challenge in which these techniques can be complemented with history- and learning-based approaches.

Keywords

Clock Cycle Sample Kernel Program Transformation Design Space Exploration Memory Operation 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cronquist, D., et al.: Specifying and Compiling Applications for RaPiD. In. In: Proc. IEEE Symp. on FPGAs for Custom Computing Machines (FCCM 1998), pp.116–125 (1998)Google Scholar
  2. 2.
    XPP Technologies, Inc.: The XPP White Paper. Release 2.1.1 edn. (2002) Google Scholar
  3. 3.
    Hauser, J., Wawrzynek, J.: Garp: A MIPS Processor with a Reconfigurable Coprocessor. In: Proc. of the IEEE Symp. on FPGAs for Custom Computing Machines (1997)Google Scholar
  4. 4.
    Kulkarni, D., Najjar, W., Rinker, R., Kurdah, F.: Fast Area Estimation to Support Compiler Optimizations in FPGA-based Reconfigurable Systems. In: IEEE Symp. on Field-Programmable Custom Computing Machines, FCCM (2002)Google Scholar
  5. 5.
    Nayak, H.M., Choudhary, A., Banerjee, P.: Accurate Area and Delay Estimators for FPGAs. In: Proc. of the 2002 Design Automation and Test in Europe Conference and Exhibition (DATE 2002), IEEE Computer Society Press, Los Alamitos (2002)Google Scholar
  6. 6.
    Liao, J., Wong, W.F., Mitra, T.: A Model for the Hardware Realization of Loops. In: Y. K. Cheung, P., Constantinides, G.A. (eds.) FPL 2003. LNCS, vol. 2778, pp. 334–344. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  7. 7.
    Derrien, S., Rajoupadyhe, S.: Loop tiling for reconfigurable accelerators. In: Brebner, G., Woods, R. (eds.) FPL 2001. LNCS, vol. 2147, p. 398. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    So, B., Hall, M., Diniz, P.: A Compiler Approach to Fast Hardware Design Space Exploration for FPGA Systems. In: Proc. of the 2002 ACM Conference on Programming Language Design and Implementation (PLDI 2002), ACM, New York (2002)Google Scholar
  9. 9.
    Kathail, V., Aditya, S., Schreiber, R., Rau, B., Cronquist, D., Sivaraman, M.: PICO: Automatically designing custom computers. IEEE Computer (2002)Google Scholar
  10. 10.
    Bakshi, A., Prasanna, V., Ledeczi, A.: MILAN: A Model Based Integrated Simulation Framework for Design of Embedded Systems. In: Proc. of the 2001 ACMWorkshop on Languages, Compilers, and Tools for Embedded Systems, LCTES 2001 (2001)Google Scholar
  11. 11.
    Halambi, A., et al.: EXPRESSION: A Language for Architecture Exploration through Compiler/Simulator Retargetability. In: Proc. of the Conf, on Design Automation and Test Europe, DATE 1999 (1999)Google Scholar
  12. 12.
    So, B., Hall, M.: Increasing the applicability of scalar replacement. In: Duesterwald, E. (ed.) CC 2004. LNCS, vol. 2985, pp. 185–201. Springer, Heidelberg (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Pedro C. Diniz
    • 1
  1. 1.Information Sciences InstituteUniversity of Southern CaliforniaMarina del ReyUSA

Personalised recommendations