An asynchronous dataflow FPGA architecture

We discuss the design of a high-performance field programmable gate array (FPGA) architecture that efficiently prototypes asynchronous (clockless) logic. In this FPGA architecture, low-level application logic is described using asynchronous dataflow functions that obey a token-based compute model. We implement these dataflow functions using finely pipelined asynchronous circuits that achieve high computation rates. This asynchronous dataflow FPGA architecture maintains most of the performance benefits of a custom asynchronous design, while also providing postfabrication logic reconfigurability. We report results for two asynchronous dataflow FPGA designs that operate at up to 400 MHz in a typical TSMC 0.25 /spl mu/m CMOS process.

[1]  John Wawrzynek,et al.  The SFRA: a corner-turn FPGA architecture , 2004, FPGA '04.

[2]  D. L. How.  A self clocked FPGA for general purpose logic emulation , 1996, Proceedings of Custom Integrated Circuits Conference.

[3]  John Teifel,et al.  Static tokens: using dataflow to automate concurrent pipeline synthesis , 2004, 10th International Symposium on Asynchronous Circuits and Systems, 2004. Proceedings..

[4]  Alain J. Martin,et al.  An asynchronous pipelined lattice structure filter , 1994, Proceedings of 1994 IEEE Symposium on Advanced Research in Asynchronous Circuits and Systems.

[5]  Kiyoshi Oguri,et al.  PCA-1: a fully asynchronous, self-reconfigurable LSI , 2001, Proceedings Seventh International Symposium on Asynchronous Circuits and Systems. ASYNC 2001.

[6]  George Varghese,et al.  HSRA: high-speed, hierarchical synchronous reconfigurable array , 1999, FPGA '99.

[7]  Alain J. Martin.  The limitations to delay-insensitivity in asynchronous circuits , 1990 .

[8]  Andrew M Lines,et al.  Pipelined Asynchronous Circuits , 1998 .

[9]  Paul I. Pénzes,et al.  The design of an asynchronous MIPS R3000 microprocessor , 1997, Proceedings Seventeenth Conference on Advanced Research in VLSI.

[10]  R. Payne,et al.  Asynchronous FPGA architectures , 1996 .

[11]  C. Traver,et al.  Cell designs for self-timed FPGAs , 2001, Proceedings 14th Annual IEEE International ASIC/SOC Conference (IEEE Cat. No.01TH8558).

[12]  Alain J. Martin,et al.  Slack Elasticity in Concurrent Computing , 1998, MPC.

[13]  Rajit Manohar,et al.  Energy-efficient pipelines , 2002, Proceedings Eighth International Symposium on Asynchronous Circuits and Systems.

[14]  S. Kung,et al.  VLSI Array processors , 1985, IEEE ASSP Magazine.

[15]  Ted Eugene Williams,et al.  Self-timed rings and their application to division , 1992 .

[16]  Vaughn Betz,et al.  VPR: A new packing, placement and routing tool for FPGA research , 1997, FPL.

[17]  John Teifel,et al.  Highly pipelined asynchronous FPGAs , 2004, FPGA '04.

[18]  Carl Ebeling,et al.  An FPGA for implementing asynchronous circuits , 1994, IEEE Design & Test of Computers.

[19]  B. Von Herzen.  Signal processing at 250 MHz using high-performance FPGA's , 1998, IEEE Trans. Very Large Scale Integr. Syst..

[20]  Brian Von Herzen.  Signal processing at 250 MHz using high-performance FPGA's , 1997, FPGA '97.

[21]  Laurent Fesquet,et al.  Implementing Asynchronous Circuits on LUT Based FPGAs , 2002, FPL.

[22]  Malgorzata Marek-Sadowska,et al.  Interconnect pipelining in a throughput-intensive FPGA architecture , 2001, FPGA '01.