Abstract
Parallel graph reduction is a promising model for new generation computer because of its amenability to both programming and parallel computing. In this paper, an initial design for a parallel graph reduction model, PGR model, is presented, which employs eager evaluation strategy to exploit conservative parallelism and provides with primitives and associated tags of nodes to synchronize concurrent tasks. Moreover, a direct operational description of graph reduction in terms of high level instructions (primitives) is given to obtain a virtual machine, called PGRVM.
Similar content being viewed by others
References
C.Clack and S. L. Peyton Jones, Strictness Analysis—A Practical Approach, LNCS 201, Sept. 1985.
J. Darlington and M. J. Reeve, ALICE: A Multiprocessor Reduction Machine, Proc. Conf. ACM Fun. Prog. Lang. and Comp. Arch., 1981.
Guo Yike, and Du **aoliet al., Design Considerations of a Distributed Parallel Reduction Machine, ICCA’87.
R. Halstead, Concurrent Lisp Machine, Technical Report, MIT, 1987.
P. Hudak, Para — functional Programming,Computer, Aug. 1986.
P. Hudak and B. Goldberg, Distributed Execution of Functional Programs Using Serial Combinator, Proc. of 1985 Int’l Conf. on Parallel Processing.
R. M. Keller and F. C. H. Lin, Simulated Performance of A Reduction Based Multiprocessor,Computer, July 1984.
S. L. Peyton Jones. GRIP — A Parallel Graph Reduction Machine, Internal Note 1665, Dept. of Computer Science, UCL, Nov. 1985.
D. Turner, A New Implementation Technique for Applicative Languages, Software—practice and experience, Jan. 1979.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wang, D., Zheng, W., Du, X. et al. On the execution mechanisms of parallel graph reduction. J. of Comput. Sci. & Technol. 5, 333–346 (1990). https://doi.org/10.1007/BF02945286
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02945286