The specification of a new Manchester Dataflow machine

ABSTRACT

The Present Manchester Dataflow Machine is constructed using standard TTL technology and is not designed with raw processing power in mind. This paper discusses the issues raised in the redesign of the machine using supercomputer technology. The resulting machine structure is presented in some detail, together with the initial results of simulation which indicate that a performance of hundreds of megaflops appears readily achievable.

REFERENCES

• 1: Barahona P.M.C.C., "Performance Evaluation of a Multi-Ring Dataflow Machine", Technical Report UMCS-84-10-2, Department of Computer Science, University of Manchester, 1984.
• 2: John Beetem , Monty Denneau , Don Weingarten, The GF11 supercomputer, Proceedings of the 12th annual international symposium on Computer architecture, p.108-115, June 17-19, 1985, Boston, Massachusetts, United States
• 3: Bohm A.P.W., Gurd J.R. and Teo Y.M.,"The Effect of Iterative Instructions in Dataflow Computers", in preparation.
• 4: A. P. W. Böhm , Y. M. Teo, Resource management in a multi-ring dataflow machine, Proceedings of the conference on CONPAR 88, p.566-577, October 1989, UMIST, Manchester, United Kingdom
• 5: Bohm A.P.W. and Teo Y.M., "The Heterogeneous Multi-Ring Dataflow Machine Simulator", Technical Report UMCS-88-6-3, Department of Computer Science, University of Manchester, 1988.
• 6: Brobst S.A., "Organisation of an instruction Scheduling and Token Storage Unit in a Tagged Token Dataflow Machine", Proceedings ICPP 87, pp. 40-45.
• 7: John Francis Foley, A hardware simulator for a multi-ring dataflow machine, 1986
• 8: J. R Gurd , C. C Kirkham , I. Watson, The Manchester prototype dataflow computer, Communications of the ACM, v.28 n.1, p.34-52, Jan. 1985 [doi>10.1145/2465.2468]
• 9: Gurd J.R. Kirkham C.C. and Bohm A.P.W., "The Manchester Dataflow Computing System", In Experimental Parallel Computing Architecture, ed. Dongarra J.J., North Holland, Amsterdam, 1987, pp. 177-219.
• 10: Gurd J. and Watson I., "A Practical Dataflow Computer", IEEE COMPUTER, Vol. 15, No. 2, February 1982, pp. 51-57.
• 11: Kai Hwang , Faye A. Briggs, Computer Architecture and Parallel Processing, McGraw-Hill, Inc., New York, NY, 1990
• 12: K. Hawakami , J. R. Gurd, A scalable dataflow structure store, Proceedings of the 13th annual international symposium on Computer architecture, p.243-250, June 02-05, 1986, Tokyo, Japan
• 13: Ruggiero C.A., "Throttle Mechanisms for the Manchester Dataflow Machine", Technical Report UMCS-87-8-1, Department of Computer Science, University of Manchester, 1988.
• 14: Carlos A. Ruggiero , John Sargeant, Control of parallelism in the Manchester Dataflow Machine, Proceedings of the Functional Programming Languages and Computer Architecture, p.1-15, September 14-16, 1987
• 15: Sargeant J., "Efficient Stored Structures for Dataflow Computing", Technical Report UMCS-85-8- 2, Department of Computer Science, University of Manchester, 1988.
• 16: T. Shimada , K. Hiraki , K. Nishida , S. Sekiguchi, Evaluation of a prototype data flow processor of the SIGMA-1 for scientific computations, Proceedings of the 13th annual international symposium on Computer architecture, p.226-234, June 02-05, 1986, Tokyo, Japan
• 17: Teo Y.M., "Performance Evaluation of a Heterogeneous Multi-Ring Dataflow Machine", Technical Report UMCS-87-12-2, Department of Computer Science, University of Manchester, 1987.
• 18: Watson I. and Gurd J.R., "A Prototype Dataflow Computer with Token Labelling", AFIPS Conference Proceedings, Vol. 48, 1979 National Computer Conference, pp. 623-628.
• 19: Wu C. and Feng T., "On a Class of Multistage Interconnection Networks", IEEE Transactions on Computers, Vol. C-29, No. 8, August 1980, pp. 694-702.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.5 COMPUTER SYSTEM IMPLEMENTATION

Additional Classification:
  B. Hardware
  B.3 MEMORY STRUCTURES

  C. Computer Systems Organization

General Terms:
Design, Experimentation, Measurement, Performance, Theory