Energy efficient surfing [latchless pipelining technique]

Surfing is a latchless pipelining technique where the propagation delays of gates and other logic functions are modulated to produce event attractors. We describe a test chip that demonstrates a surfing pipeline ring and then introduce new circuits that dramatically reduce the energy overhead for surfing. Our test chip implements a twelve-stage, surfing ring that supports two independent waves of computation without latches or other storage elements. We have operated the chip for over 48 hours and more than 2.6/spl times/10/sup 15/ surfing events without an error. However, the energy consumption of the ring is unacceptable for scaling to larger applications. Thus, we introduce a new family of surfing circuits that use less energy than their domino counterparts and provide a factor of up to 1.75 improvement by the Et/sup 2/ metric. We demonstrate this new family with the design of a carry lookahead adder.

[1]  Eby G. Friedman,et al.  Domino logic with variable threshold voltage keeper , 2003, IEEE Trans. Very Large Scale Integr. Syst..

[2]  Ivan E. Sutherland,et al.  GasP: a minimal FIFO control , 2001, Proceedings Seventh International Symposium on Asynchronous Circuits and Systems. ASYNC 2001.

[3]  Solomon W. Golomb,et al.  Shift Register Sequences , 1981 .

[4]  H. T. Kung,et al.  A Regular Layout for Parallel Adders , 1982, IEEE Transactions on Computers.

[5]  Alain J. Martin,et al.  ET 2 : a metric for time and energy efficiency of computation , 2002 .

[6]  Tyler Thorp,et al.  Output prediction logic: a high-performance CMOS design technique , 2000, Proceedings 2000 International Conference on Computer Design.

[7]  Mark R. Greenstreet,et al.  A negative-overhead, self-timed pipeline , 2002, Proceedings Eighth International Symposium on Asynchronous Circuits and Systems.

[8]  W. Liu,et al.  Wave-pipelining: a tutorial and research survey , 1998, IEEE Trans. Very Large Scale Integr. Syst..

[9]  Christos P. Sotiriou,et al.  Controlling event spacing in self-timed rings , 2005, 11th IEEE International Symposium on Asynchronous Circuits and Systems.

[10]  Mark R. Greenstreet,et al.  An event spacing experiment , 2002, Proceedings Eighth International Symposium on Asynchronous Circuits and Systems.

[11]  Mark R. Greenstreet,et al.  Surfing: a robust form of wave pipelining using self-timed circuit techniques , 2003, Microprocess. Microsystems.

[12]  Rajiv V. Joshi,et al.  A 2-ns cycle, 3.8-ns access 512-kb CMOS ECL SRAM with a fully pipelined architecture , 1991 .

[13]  Ivan E. Sutherland,et al.  Predicting performance of micropipelines using Charlie diagrams , 1998, Proceedings Fourth International Symposium on Advanced Research in Asynchronous Circuits and Systems.

[14]  C. M. Lee,et al.  High-speed compact circuits with CMOS , 1982 .

[15]  David Harris,et al.  Logical effort of carry propagate adders , 2003, The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003.

[16]  L. Heller,et al.  Cascode voltage switch logic: A differential CMOS logic family , 1984, 1984 IEEE International Solid-State Circuits Conference. Digest of Technical Papers.