Pipelining and Clocking of High Performance Synchronous Digital Systems

This chapter discusses the effects of pipelining on the performance of high speed synchronous digital systems. In particular, the tradeoff between clock frequency and latency is described in terms of the circuit characteristics of a pipelined data path [1,2]. The design of the clock distribution network synchronizing the signal flow between each data path can significantly affect system performance. Timing characteristics of the clock distribution network are described in terms of how system performance can be either enhanced or degraded. A design paradigm relating latency and clock frequency as a function of the level of pipelining is developed for studying the performance of a synchronous system. This perspective permits the development of design equations for constrained and unconstrained design problems which describe these performance parameters in terms of the delays of the logic, interconnect, and registers, the nature of the clock distribution network, and the number of logic stages.

[1]  R. J. Bayruns,et al.  Delay analysis of Si NMOS Gbit/s logic circuits , 1984 .

[2]  Eby G. Friedman,et al.  Clock frequency and latency in synchronous digital systems , 1991, IEEE Trans. Signal Process..

[3]  Christer Svensson,et al.  A scalable synchronous system , 1988, 1988., IEEE International Symposium on Circuits and Systems.

[4]  Eby G. Friedman,et al.  Design and analysis of a hierarchical clock distribution system for synchronous standard cell/macrocell VLSI , 1986 .

[5]  C.M. Lee,et al.  An algorithm for CMOS timing and area optimization , 1984, IEEE Journal of Solid-State Circuits.

[6]  Hendrikus J. M. Veendrick,et al.  Short-circuit dissipation of static CMOS circuitry and its impact on the design of buffer circuits , 1984 .

[7]  Steven D. Kugelmass,et al.  A probabilistic model for clock skew , 1988, [1988] Proceedings. International Conference on Systolic Arrays.

[8]  Parameswaran Ramanathan,et al.  A clock distribution scheme for nonsymmetric VLSI circuits , 1989, 1989 IEEE International Conference on Computer-Aided Design. Digest of Technical Papers.

[9]  Stephen H. Unger,et al.  Clocking Schemes for High-Speed Digital Systems , 1986, IEEE Transactions on Computers.

[10]  Eby G. Friedman,et al.  Pipelining of high performance synchronous digital systems , 1991 .

[11]  Lance A. Glasser,et al.  Delay and Power Optimization in VLSI Circuits , 1984, 21st Design Automation Conference Proceedings.

[12]  Mehdi Hatamian.  Understanding Clock Skew in Synchronous Systems , 1988 .

[13]  M. Hatamian,et al.  Parallel bit-level pipelined VLSI designs for high-speed signal processing , 1987, Proceedings of the IEEE.

[14]  Charles E. Leiserson,et al.  Optimizing synchronous systems , 1981, 22nd Annual Symposium on Foundations of Computer Science (sfcs 1981).

[15]  J.D. Meindl,et al.  Optimal interconnection circuits for VLSI , 1985, IEEE Transactions on Electron Devices.

[16]  John L. Wyatt,et al.  Fast On-Chip Delay Estimation For Cell-Based Emitter Coupled Logic , 1988, Other Conferences.

[17]  Leonard W. Cotten.  Circuit implementation of high-speed pipeline systems , 1965, AFIPS '65 (Fall, part I).

[18]  Peter R. Cappello,et al.  Completely-pipelined architectures for digital signal processing , 1983 .

[19]  Carol Valentina Gura.  Analysis of Clock Skew in Distributed Resistive-Capacitive Interconnects , 1987 .

[20]  E.T. Lewis,et al.  Optimization of device area and overall delay for CMOS VLSI designs , 1984, Proceedings of the IEEE.

[21]  S. A. Huss,et al.  Signal delay calculation for integrated CMOS circuits , 1987 .

[22]  Peter R. Cappello,et al.  Optimal choice of intermediate latching to maximize throughput in VLSI circuits , 1984 .

[23]  D. Deschacht,et al.  Explicit formulation of delays in CMOS VLSI , 1987 .

[24]  B. Archie Bowen,et al.  Synthesis of efficient pipelined architectures for implementing DSP operations , 1985, IEEE Trans. Acoust. Speech Signal Process..

[25]  Eby G. Friedman,et al.  Clock distribution design in VLSI circuits-An overview , 1993, 1993 IEEE International Symposium on Circuits and Systems.

[26]  Dejan Mijuskovic.  Clock distribution in application specific integrated circuits , 1987 .

[27]  I. N. Parker.  VLSI architecture , 1986 .

[28]  Nicholas C. Rumin,et al.  Automatic determination of optimal clocking parameters in synchronous MOS VLSI circuits , 1988 .

[29]  Mehdi Hatamian,et al.  Fundamental interconnection issues , 1987, AT&T Technical Journal.

[30]  K.D. Wagner,et al.  Clock system design , 1988, IEEE Design & Test of Computers.

[31]  L.W. Linholm,et al.  An optimized output stage for MOS integrated circuits , 1975, IEEE Journal of Solid-State Circuits.

[32]  J. Meindl,et al.  Optimal interconnect circuits for VLSI , 1984, 1984 IEEE International Solid-State Circuits Conference. Digest of Technical Papers.

[33]  Sudhir Ahuja,et al.  Effective Pipelining of Digital Systems , 1978, IEEE Transactions on Computers.

[34]  Mark A. Franklin,et al.  Asynchronous and Clocked Control Structures for VSLI Based Interconnection Networks , 1983, IEEE Transactions on Computers.

[35]  Richard C. Jaeger,et al.  Comments on "An optimized output stage for MOS integrated circuits" [with reply] , 1975 .

[36]  Peter R. Cappello,et al.  Bit-level fixed-flow architectures for signal processing , 1982 .

[37]  Akira Kanuma,et al.  CMOS circuit optimization , 1983 .

[38]  Parker,et al.  Design for Testability—A Survey , 1982, IEEE Transactions on Computers.

[39]  F. Anceau.  A synchronous approach for clocking VLSI systems , 1982, IEEE Journal of Solid-State Circuits.