Publication Date

Spring 2011

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Robert Chun

Second Advisor

Soon Tee Teoh

Third Advisor

Snehal Patel

Abstract

It is generally believed for the past several years that parallel programming is the future of computing technology due to its incredible speed and vastly superior performance as compared to classic linear programming. However, how sure are we that this is the case? Despite its aforesaid average superiority, usually parallel-program implementations run in single-processor machines, making the parallelism almost virtual. In this case, does parallel programming still remain superior?
The purpose of this document is to research and analyze the performance, in both storage and speed, of three parallel-programming language libraries: OpenMP, OpenMPI and PThreads, along with a few other hybrids obtained by combining two of these three libraries. These analyses will be applied to three classical multi-process synchronization problems: Dining Philosophers, Producers-Consumers and Sleeping Barbers.

Share

COinS