Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Simulation and improvement of the processing subsystem of the Manchester dataflow computer

Abstract

The Manchester dataflow computer is a famous dynamic dataflow computer. It is centralized in architecture and simple in organization. Its overhead for communication and scheduling is very small. Its efficiency comes down, when processing elements in the processing subsystem increase. Several articles evaluated its performance and presented improved methods. The authors studied its processing subsystem and carried out the simulation. The simulation results show that the efficiency of the processing subsystem drops dramatically when average instruction execution microcycles become less and the maximum instruction execution rate is nearly attained. Two improved methods are presented to overcome the disadvantage. The improved processing subsystem with a cheap distributor made up of a bus and a two-level fixed priority circuit possesses almost full efficiency no matter whether the average instruction execution microcycles number is large or small and even if the maximum instruction execution rate is approached.

This is a preview of subscription content, log in to check access.

References

  1. [1]

    da Silva J R D, Woods J V. Design of a processing subsystem for the Manchester data-flow computer. InIEE PROC., 1981, 128(5): 218–224.

  2. [2]

    Gurd J Ret al. The Manchester prototype dataflow computer.Communications of the ACM, 1985, 28(1): 34–52.

  3. [3]

    Partnaik L M,et al. Design and performance evaluation, of EXMAN: An EXtended MANchester data flow computer.IEEE Trans. on Computers, 1986, C-35(3): 229–243.

  4. [4]

    Ghosal Dipak, Bhuyan Laxmi N. Performance evaluation of a dataflow architecture.IEEE Trans. on Computers, 1990, C-39(5): 615–627.

  5. [5]

    Lai Zhiyong, Zheng Shouqi. A ring-type dataflow computer with automatic load balancing. InProceedings of the 92’s Computer Architecture National Conference, Changsha, China, Sep. 1992, 10–16. (in Chinese)

  6. [6]

    Culler David E, Papadopoulos Gregory M. The explicit token store.Journal of Parallel and Distributed Computing, 1990, 10(3): 289–308.

  7. [7]

    Grafe V G, Hoch J E. The Epsilon-2 multiprocessor system.Journal of Parallel and Distributed Computing, 1990, 10(3): 309–318.

  8. [8]

    SAKAI Shuichiet al. An architecture of a dataflow single chip processor. InThe 16th Annual International Symposium on Computer Architecture, 1989, 46–53.

  9. [9]

    James Hickset al. Performance studies of Id on the Monsoon dataflow systems.Journal of Parallel and Distributed Computing, 1993, 18(3): 273–300.

Download references

Author information

Correspondence to Zhiyong Lai.

Additional information

Lai Zhiyong received his B.E. and M.E. degrees in computer science and engineering from Xi’an Jiaotong University in 1982 and 1984 respectively. He has been working toward the Ph.D. degree in Computer Science and Engineering Department of Xi’an Jiaotong University. His main interests include computer architecture, paralell processing and computerized accounting.

Zheng Shouqi received his B.E. degree in electrical engieering from Shanghai Jiaotong University in 1949. He is currently a Professor in Computer Science and Engineering Department of Xi’an Jiaotong University. His main interests include computer architecture and artificial intelligence.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Lai, Z., Zheng, S. Simulation and improvement of the processing subsystem of the Manchester dataflow computer. J. of Comput. Sci. & Technol. 10, 557–563 (1995). https://doi.org/10.1007/BF02943513

Download citation

Keywords

  • Dataflow computer
  • processing subsystem
  • distributor
  • efficiency
  • maximum instruction execution rate