Year of Publication

1990

Season of Publication

Fall

Paper Type

Master's Thesis

College

College of Computing, Engineering & Construction

Degree Name

Master of Science in Computer and Information Sciences (MS)

Department

Computing

First Advisor

Dr. Susan R. Wallace

Second Advisor

Dr. Roger E. Eggen

Abstract

Linda is a new parallel programming language that is built around an interprocess communication model called generative communication that differs from previous models in specifying that shared data be added in tuple form to an environment called tuple space, where a tuple exists independently until some process chooses to use it. Interesting properties arise from the model, including space and time uncoupling as well as structured naming. We delineate the essential Linda operations, then discuss the properties of generative communication. We are particularly concerned with implementing Linda on top of two traditional parallel programming paradigms - process communication through globally shared memory via monitors, and process communication in local memory architectures through the use of message passing constructs. We discuss monitors and message passing, then follow with a description of the two Linda implementations.

Share

COinS