Better parallel architectures via emulations

  • Arnold L. Rosenberg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 678)


As the processors and communication subsystems of parallel architectures become progressively faster, it is becoming increasingly costeffective to build simple architectures that achieve complex behavior by emulating more complicated ones. We support this thesis by describing work by the author and collaborators [10] on algorithmically implementing, for pure SIMD bit-serial processor arrays, a multigauging capability that would be prohibitively expensive to implement in hardware.


Parallel Architecture Complete Binary Tree Communication Subsystem Parallel Prefix Gauge Size 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    F.S. Annexstein, M. Baumsiag, A.L. Rosenberg (1990): Group action graphs and parallel architectures. SIAM J. Comput. 19, 544–569.Google Scholar
  2. 2.
    M. Baumslag and F.S. Annexstein (1991): A unified approach to global permutation routing on parallel networks. Math. Syst. Th. 24, 233–251.Google Scholar
  3. 3.
    S.N. Bhatt, F.R.K. Chung, J.-W. Hong, F.T. Leighton, B. Obrenić, A.L. Rosenberg, E.J. Schwabe (1991): Optimal emulations by butterfly-like networks. J. ACM, to appear.Google Scholar
  4. 4.
    G.E. Blelloch (1989): Scans as primitive parallel operations. IEEE Trans. Comp. 38, 1526–1538.Google Scholar
  5. 5.
    D.S. Greenberg, L.S. Heath and A.L. Rosenberg (1990): Optimal embeddings of butterfly-like graphs in the hypercube. Math. Syst. Th. 23, 61–77.Google Scholar
  6. 6.
    S.I. Kartashev and S.P. Kartashev (1979): A multicomputer system with dynamic architecture. IEEE Trans. Comp., C-28, 704–721.Google Scholar
  7. 7.
    R. Koch, F.T. Leighton, B. Maggs, S. Rao, A.L. Rosenberg, E.J Schwabe (1990): Work-preserving emulations of fixed-connection networks. Submitted for publication; see also, 21st ACM Symp. on Theory of Computing, 227–240.Google Scholar
  8. 8.
    R.E. Ladner and M.J. Fischer (1980): Parallel prefix computation. J. ACM 27, 831–838.Google Scholar
  9. 9.
    F.T. Leighton (1992): Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes. Morgan Kaufmann, San Mateo, Calif.Google Scholar
  10. 10.
    B. Obrenić, M.C. Herbordt, A.L. Rosenberg, C.C. Weems, F.S. Annexstein, M. Baumslag (1991): Using emulations to construct high-performance virtual parallel architectures. Tech. Rpt. 91-40, Univ. Massachusetts. See also, Achieving multigauge behavior in bit-serial SIMD architectures via emulation. 3rd IEEE Symp. on Frontiers of Massively Parallel Computation (1990) 186–195.Google Scholar
  11. 11.
    T.D. de Rose, L. Snyder, C. Yang (1987): Near-optimal speedup of graphics algorithms using multigauge parallel computers. Intl. Conf. on Parallel Processing, 289–294.Google Scholar
  12. 12.
    M.R. Samatham and D.K. Pradhan (1989): The deBruijn multiprocessor network: a versatile parallel processing and sorting network for VLSI. IEEE Trans. Comp. 38, 567–581.Google Scholar
  13. 13.
    J.T. Schwartz (1980): Ultracomputers. ACM Trans. Prog. Lang. 2, 484–521.Google Scholar
  14. 14.
    L. Snyder (1985): An inquiry into the benefits of multigauge parallel computation. Intl. Conf. on Parallel Processing, 488–492.Google Scholar
  15. 15.
    L. Snyder and C. Yang (1988): The principles of multigauging architectures. Typescript, Univ. Washington.Google Scholar
  16. 16.
    C.C. Weems, S.P. Levitan, A.R. Hanson, E.M. Riseman, D.B. Shu, J.G. Nash (1987): The Image Understand Architecture. Intl. J. Computer Vision 2, 251–282.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Arnold L. Rosenberg
    • 1
  1. 1.Department of Computer ScienceUniversity of MassachusettsAmherst

Personalised recommendations