The control mechanism for the Myrias parallel computer system

ABSTRACT

This paper presents an overview of the issues involved in the design of the control mechanism used by the Myrias parallel computer system to manage the execution of parallel programs. The following issues are discussed: initial task distribution, dynamic load leveling, hierarchical caching, task synchronization, memory management, and scalability. Some of the more important points are illustrated using performance measurements obtained by running a test program on the Myrias Research Corporation prototype system.

REFERENCES

• 1: Harold J. Raveché , Duncan, H. Lawrie , Alvin M. Despain, A national computing initiative: the agenda for leadership, Society for Industrial and Applied Mathematics, Philadelphia, PA, 1987
• 2: 2. A. M. Kobos, R. E. VanKooten and M. A. Walker, The Myrias Parallel Computer System, in Algorithms and Applications on Vector and Parallel Computers, H. J. J. Riele, T. J. Dekker and H. A. Vorst (ed.), Elsevier Science Publishers B.V., North-Holland, 1987.
• 3: 3. UMI Research Press, 1981.
• 4: 4. IEEE Software 2, 4 (July 1985), pp. 30.
• 5: 5. IEEE Software 2, 4 (July 1985), pp. 39.
• 6: 6. C. G. Broughton, Myrias Parallel Fortran, Extensions to and Interpretations of ANSI X3.9 -1978 FORTRAN 77, internal publication.
• 7: 7. D. Reble, R. VanKooten and J. R. Zorbas, On the Scalability of Parallel Computers, to be published.
• 8: 8. in Hypercube Multiprocessors 1986, M. T. Heath (ed.), Siam, Philadelphia, 1986, pp. 244.
• 9: 9. Addison-Wesley, Revised 1st Edition 1984.
• 10: 10. R. E. Foster, C. Thomson and D. Wilson, Parallel Programming Without Tears, to be published as a technical report, Myrias Research Corporation, December 1987.
• 11: 11. Experience Scaling the Myrias System to Hundreds of Processors, Proceedings of the Third International Conference on Supercomputing and Second World Supercomputers Exhibition, Boston, May 15 - 20 1988.
• 12: 12. K. A. Bobey, Performance Monitoring for the Myrias Parallel Computer System, Proceedings of the Third International Conference on Supercomputing and Second World Supercomputers Exhibition, Boston, May 15 - 20 1988.

INDEX TERMS

Primary Classification:
  F. Theory of Computation
  F.1 COMPUTATION BY ABSTRACT DEVICES
      F.1.2 Modes of Computation
          Subjects: Parallelism and concurrency

Additional Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
      C.1.2 Multiple Data Stream Architectures (Multiprocessors)
          Subjects: Parallel processors**

  F. Theory of Computation
  F.2 ANALYSIS OF ALGORITHMS AND PROBLEM COMPLEXITY
      F.2.2 Nonnumerical Algorithms and Problems
          Subjects: Sequencing and scheduling

General Terms:
Design, Measurement, Performance, Theory