DDMPs: self-timed super-pipelined data-driven multimedia processors

This paper describes the world's first commercial data-driven multimedia processors (DDMPs), developed jointly by Osaka University Kochi University of Technology, and Sharp Corporation. The data-driven principle underlying the structure of these processors was realized in a super-pipelined implementation, which was in turn based on a self-timed clocking scheme. This design made it possible to realize single chip DDMPs capable of executing tens of billions of signal processing operations per second with power consumption as low as 2 W. In terms of operations per watt, the processors exhibit threefold to tenfold improvement over conventional sequential digital signal processors (DSPs). The structure of this paper is as follows: 1) a brief introduction to the data-driven processing principle; 2) a detailed description of elementary modules for the realization of self-timed pipeline microprocessors; and 3) a description of the DDMP's developed thus far in the research project, which has continued for more than a decade. Also outlined here are the numerous advantages, in terms of both function and power consumption, of the self-timed pipeline over its synchronous counterparts. Commercially available DSP-oriented asynchronous data-driven processors and their practical applications to consumer appliances such as digital TV receivers are discussed; some programming examples are provided.

[1]  Takashi Nanya,et al.  TITAC-2: an asynchronous 32-bit microprocessor based on scalable-delay-insensitive model , 1997, Proceedings International Conference on Computer Design VLSI in Computers and Processors.

[2]  Souichi Miyata,et al.  The data-driven microprocessor , 1989, IEEE Micro.

[3]  Hiroaki Terada A New Processing Paradigm for Consumer Applications , 1996 .

[4]  Erik Brunvand,et al.  Fred: an architecture for a self-timed decoupled computer , 1996, Proceedings Second International Symposium on Advanced Research in Asynchronous Circuits and Systems.

[5]  Ian Watson,et al.  A Practical Data Flow Computer , 1982, Computer.

[6]  Toshiyuki Tamura,et al.  A 50MFLOPS Superpipelined Data-driven Microprocessor , 1991, 1991 IEEE International Solid-State Circuits Conference. Digest of Technical Papers.

[7]  Satoshi Matsumoto,et al.  VLSI design of a one-chip data-driven processor: Q-v1 , 1987, FJCC.

[8]  Tetsuya Takine,et al.  Flow-Thru Processing concept and its application to soft-computing , 1998 .

[9]  Hiroki Miura,et al.  Hardware Structure of a One-Chip Data Driven Processor: Q-p , 1987, ICPP.

[10]  Venkatesh Akella,et al.  Asynchronous Processor Survey , 1997, Computer.

[11]  T. Temma,et al.  Data flow processor chip for image processing , 1985, IEEE Transactions on Electron Devices.

[12]  Hiroaki Terada Superpipelined Dynamic Data-Driven VLSI Processors , 1995 .

[13]  Makoto Iwata,et al.  Direct generation of data-driven program for stream-oriented processing , 1997, Proceedings 1997 International Conference on Parallel Architectures and Compilation Techniques.

[14]  Hiroaki Terada,et al.  A 100-mega-access per second matching memory for a data-driven microprocessor , 1990 .

[15]  A. L. Davis,et al.  The architecture and system method of DDM1: A recursively structured Data Driven Machine , 1978, ISCA '78.

[16]  Steven M. Burns,et al.  The design of an asynchronous microprocessor , 1989, CARN.

[17]  Arvind,et al.  A critique of multiprocessing von Neumann style , 1983, ISCA '83.

[18]  Jim D. Garside,et al.  AMULET2e: an asynchronous embedded controller , 1997, Proceedings Third International Symposium on Advanced Research in Asynchronous Circuits and Systems.

[19]  Ivan E. Sutherland,et al.  The counterflow pipeline processor architecture , 1994, IEEE Design & Test of Computers.

[20]  Yuichi Ninomiya,et al.  An HDTV Broadcasting System Utilizing a Bandwidth Compression Technique-MUSE , 1987, IEEE Transactions on Broadcasting.

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

[22]  Ian Watson,et al.  The Manchester prototype dataflow computer , 1985, CACM.

[23]  Hiroaki Terada,et al.  A 40-MFLOPS 32-bit floating-point processor with elastic pipeline scheme , 1989 .

[24]  T. Mizutani,et al.  A new tungsten gate process for VLSI applications , 1984, IEEE Transactions on Electron Devices.

[25]  Raymond E Miller Switching theory , 1979 .

[26]  Takashi Nanya,et al.  TITAC: design of a quasi-delay-insensitive microprocessor , 1994, IEEE Design & Test of Computers.

[27]  T. Tamura,et al.  Self-timed clocking desing for a data-driven microprocessor , 1991 .