A Caltech Library Service

A Distributed Implementation Method for Parallel Programming

Martin, A. J. (1980) A Distributed Implementation Method for Parallel Programming. Computer Science Technical Memorandum, 1980.5045. California Institute of Technology , Pasadena, CA. (Unpublished)

PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


A method is described for implementing on a finite network of processing "cells", called the "implementation graph", programs whose potential parallelism is not fixed by the implementation but varies according to the input parameters. First, programming constructs are described permitting a computation, regarded as a dynamic structure called the "computation graph", to diffuse through the implementation graph. Second, the implementation problem of mapping an unbounded number of computation nodes on a finite number of cells is tackled. Processor allocation and message buffering completely disappear from the programmer's concerns. The mechanism proposed is considered a generalization of the stack mechanism.

Item Type:Report or Paper (Technical Report)
Additional Information:Appears in INFORMATION PROCESSING 80, S.H. Lavington (ed.) North-Holland Publishing Company. Acknowledgement is due to Edsger W. Dijkstra, C.S. Scholten, and the members of the Tuesday Afternoon Club for valuable comments and criticisms.
Group:Computer Science Technical Reports
Series Name:Computer Science Technical Memorandum
Issue or Number:1980.5045
Record Number:CaltechAUTHORS:20120418-114041991
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:30168
Deposited By: Kristin Buxton
Deposited On:18 Apr 2012 19:35
Last Modified:03 Oct 2019 03:48

Repository Staff Only: item control page