Advertisement

Timing Issues of Operating Mode Switch in High Performance Reconfigurable Architectures

  • Rama Sangireddy
  • Huesung Kim
  • Arun K. Somani
Conference paper
  • 309 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2913)

Abstract

The concept of a reconfigurable coprocessor controlled by the general purpose processor, with the coprocessor acting as a specialized functional unit, has evolved to accelerate applications requiring higher computing power. The idea of Adaptive Balanced Computing (ABC) architecture has evolved, where a module of Reconfigurable Functional Cache (RFC) is configured with a selective core function in the application whenever a higher computing resources are required. Initial results have proved that the ABC architecture provides with speedups ranging from 1.04x to 5.0x depending on the application and the speedups in the range of 2.61x to 27.4x are observed for the core functions. This paper further explores the issues of management of RFC, where the impact of various schemes for configuration of core function into the RFC module is studied. This paper also gives a detailed analysis on the performance of ABC architecture for various configuration schemes, including the study of the effect of the percentage of the core function in an entire application over the management of RFC modules.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hauser, J.R., Wawrzynek, J.: Garp: a MIPS processor with a reconfigurable coprocessor. In: Proc. IEEE Symposium on Field-Programmable Custom Computing Machines, April 1997, pp. 12–21 (1997)Google Scholar
  2. 2.
    Ye, Z.A., Moshovos, A., Hauck, S., Banerjee, P.: CHIMAERA: a highperformance architecture with a tightly-coupled reconfigurable functional unit. In: Proc. 27th International Symposium on Computer Architecture, pp. 225–235 (2000)Google Scholar
  3. 3.
    DeHon, A.: DPGA-coupled microprocessors: commodity ICs for the early 21st Century. In: Proc. IEEE Workshop on FPGAs for Custom Computing Machines, pp. 31–39 (1994)Google Scholar
  4. 4.
    Razdan, R., Smith, M.D.: A High-Performance Microarchitecture With Hardware-Programmable Functional Units. In: Proc. 27th Annual International Symposium on Microarchitecture, MICRO-27, pp. 172–180 (1994)Google Scholar
  5. 5.
    Ranganathan, P., Adve, S., Jouppi, N.P.: Reconfigurable caches and their application to media processing. In: Proc. 27th International Symposium on Computer Architecture, pp. 214–224 (2000)Google Scholar
  6. 6.
    Kim, H., Somani, A.K., Tyagi, A.: A Reconfigurable Multi-function Computing Cache Architecture. In: Proc. FPGA 2000, February 2000, pp. 85–94 (2000)Google Scholar
  7. 7.
    Kim, H., Somani, A.K., Tyagi, A.: A reconfigurable multifunction computing cache architecture. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 9(4), 509–523 (2001)CrossRefGoogle Scholar
  8. 8.
    Kim, H.: Towards Adaptive Balanced Computing (ABC) Using Reconfigurable Functional Caches (RFCs)., Ph. D. Dissertation, Dept. of Electrical and Computer Engineering, Iowa State University (July 2001)Google Scholar
  9. 9.
    Lee, C., Potkonjak, M., Mangione-Smith, W.H.: MediaBench: a tool for evaluating and synthesizing multimedia and communications systems. In: Proc. Thirtieth Annual IEEE/ACM International Symposium on Microarchitecture, pp. 330–335 (1997)Google Scholar
  10. 10.
    Texas Instruments, “TMS320C6000 benchmarks” (2000), Available on, http://www.ti.com/sc/docs/products/dsp/c6000/62bench.htm
  11. 11.
    Burger, D., Austin, T.M.: The SimpleScalar Tool Set, Version 2.0. Computer Sciences Department Technical report # 1342, University of Wisconsin- Madison (June 1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Rama Sangireddy
    • 1
  • Huesung Kim
    • 1
  • Arun K. Somani
    • 1
  1. 1.Dependable Computing & Networking Laboratory, Department of Electrical and Computer EngineeringIowa State UniversityAmesUSA

Personalised recommendations