Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

While reconfigurable computing promises to deliver incomparable performance, it is still a marginal technology due to the high cost of developing and upgrading applications. Hardware virtualization can be used to significantly reduce both these costs. In this paper we describe the benefits of hardware virtualization, and show how it can be achieved using a combination of pipeline reconfiguration and run-time scheduling of both configuration streams and data streams. The result is PipeRench, an architecture that supports robust compilation and provides forward compatibility. Our preliminary performance analysis predicts that PipeRench will outperform commercial FPGAs and DSPs in both overall performance and in performance per mm2.

REFERENCES

• 1: J. Babb, R. Tessier, and A. Agarwal. Virtual wires: Overcoming pin limitations in FPGA-based logic emulators. In D. A. Buell and K. L. Pocek, editors, Proceedings o! IEEB Workshop on FPGAs for Custom Computing Machines, pages 142-151, Nape, CA, April 1993.
• 2: Narasimha B. Bhaqt , Kamal Chaudary , Ernest S. Kuh, Performance-Oriented Fully Routable Dynamic Architecture for a Field, University of California at Berkeley, Berkeley, CA, 1993
• 3: A. DeHon. DPGA-coupled microprocessors: Commodity ICs for the early 21st century. In D. A. Buell and K. L. Pocek, editors, Proceedings of IEEB Workshop on FPGAs .for Custom Computing Machines, pages 31-39, Nape, CA, April 1994.
• 4: Brian Von Herzen, Signal processing at 250 MHz using high-performance FPGA's, Proceedings of the 1997 ACM fifth international symposium on Field-programmable gate arrays, p.62-68, February 09-11, 1997, Monterey, California, United States [doi>10.1145/258305.258313]
• 5: Texas Instruments. TMS3:~0C6201 digital signal processor, revision 2, 1997.
• 6: H.T. Kung. Why systolic architectures? In IEEE Computer, pages 37-45, Piscataway, NJ, January 1982.
• 7: Wayne Luk , Nabeel Shirazi , S. R. Guo , Peter Y. K. Cheung, Pipeline morphing and virtual pipelines, Proceedings of the 7th International Workshop on Field-Programmable Logic and Applications, p.111-120, September 01-03, 1997
• 8: B. Newgard. Signal processing with Xilinx FPQAs, September 1996. http://www .xilinx. com/appnotes/sd.xdsp, pdf.
• 9: J. Hose. Private communications, 1997.
• 10: H. Schmit, Incremental reconfiguration for pipelined applications, Proceedings of the 5th IEEE Symposium on FPGA-Based Custom Computing Machines, p.47, April 16-18, 1997
• 11: S. Trimberger. Field programmable gate array with built-in bitstream data expansion. U.S. Patent No. 5,426,379, June 1995.
• 12: S. Trimberger , D. Carberry , A. Johnson , J. Wong, A time-multiplexed FPGA, Proceedings of the 5th IEEE Symposium on FPGA-Based Custom Computing Machines, p.22, April 16-18, 1997

INDEX TERMS

Primary Classification:
  B. Hardware
  B.7 INTEGRATED CIRCUITS
      B.7.1 Types and Design Styles
          Subjects: Gate arrays

Additional Classification:
  B. Hardware
  B.7 INTEGRATED CIRCUITS
      B.7.2 Design Aids
          Subjects: Placement and routing; Layout

General Terms:
Algorithms, Design, Performance