[Parallel Processing Implementation Using PVM For Image Processing Filtering Using Low And High Pass Filters]

by

Acknowledgement

I would take this opportunity to thank my research supervisor, family and friends for their support and guidance without which this research would not have been possible.

DECLARATION

I, [type your full first names and surname here], declare that the contents of this dissertation/thesis represent my own unaided work, and that the dissertation/thesis has not previously been submitted for academic examination towards any qualification. Furthermore, it represents my own opinions and not necessarily those of the University.

Signed __________________ Date _________________

Abstract

Structured parallel programs ought to be conceived as two separate and complementary entities: computation, which expresses the calculations in a procedural manner, and coordination, which abstracts the interaction and communication. By abstracting commonly used patterns of parallel computation, communication, and interaction, algorithmic skeletons enable programmers to code algorithms without specifying platform-dependent primitives. This article presents a literature review on algorithmic skeleton frameworks (ASkF), parallel software development environments furnishing a collection of parameterizable algorithmic skeletons, where the control flow, nesting, resource monitoring, and portability of the resulting parallel program is dictated by the ASkF as opposed to the programmer. Consequently, the ASkF can be positioned as high-level structured parallel programming enablers, as their systematic utilization permits the abstract description of programs and fosters portability by focusing on the description of the algorithmic structure rather than on its detailed implementation

Introduction

Parallel programming aims to capitalize on the simultaneous execution of different program sections, in order to improve the overall performance of such a program, and, eventually, that of the whole system. Despite major breakthroughs, parallel programming is still a highly demanding activity widely acknowledged to be more difficult than its sequential counterpart, where the use of efficient parallel programming models has long been coveted. These programming models must necessarily be performance-oriented, are expected to be defined in a scalable structured fashion, and provide guidance on the execution of their jobs in order to assist in the deployment of heterogeneous resources and policies.

Scope of the Study

Algorithmic skeletons commonly used patterns of parallel computation, communication, and interaction 1, 2. While computation constructs manage logic, arithmetic, and control flow operations, communication and interaction primitives coordinate inter- and intra-process data exchange, process creation, and synchronization. Skeletons provide top-down design, composition, and control inheritance throughout the program structure. Structured parallel programs are expressed by interweaving parameterized skeletons analogous to the way in which structured sequential programs are constructed.

Algorithmic skeleton frameworks (ASkF) furnish a set of algorithmic skeletons with generic parallel functionality, that are parameterized by the programmer to generate a specific parallel program. Analogous to common software libraries, skeletons are typically accessible through language syntactic extensions or well-defined application programming interfaces. However, the control flow, nesting, resource monitoring, and portability of the resulting parallel program is dictated by the ASkF as opposed to the programmer. Figure 1 shows the functioning of ASkF, where a programmer transforms a parallel algorithm into a program by selecting an algorithmic skeleton, or a nesting of them, through an API from a given skeleton repository in ...