published_or_final_version / Computer Science / Master / Master of Philosophy

Thesis (M. Phil.)--University of Hong Kong, 1994. / Includes bibliographical references (leaves 63-64).

The primary motivation behind building multiprocessors is to cost-effectively improve system performance. Debugging and performance analysis of parallel programs, however, are complex tasks and the lack of tools to observe the behaviour of a program running on a multicomputer network, limits the programmers ability to efficiently debug and optimize parallel programs. In this thesis we investigate the use of different graphical representations of parallel programs running on a network of transputers as a tool for performance analysis. Postmortem traces collected from the program execution by the underlying monitor enables us to graphically reconstruct the states of the system that were true at run time. We show how the performance analyst can get an accurate view of the behaviour of the parallel program during execution by using a basic set of visualization tools. The challenge is to determine the types of graphical displays that are most useful for presenting the behaviour and performance of a parallel program. Problems in graphically visualization of parallel program executions are: efficiently managing of potentially large volumes of performance data, ensuring consistency among the tool-components, correctly responding to any combinations of user events, meeting the desirable system requirements of extensibility and maintainability. / Science, Faculty of / Computer Science, Department of / Graduate

No description available.

Research Report submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, towards a partial fulfilment of the requirements for the degree of Master of Science Johannesburg 1991 / This report describes and evaluates an implementation of the Linda tuple space abstraction on Transputer networks. There is evidence that suggests a need for a new programming methodology to support Transputer-based applications, and Linda, as an attractive and elegant alternative to existing methodologies, has great potential for this role. The research focuses on the implementation of a particular tuple space model, intermediate uniform distribution, on Transputer meshes. The objective of the research is to ascertain the extent of the communication overheads inherent in the implementation and hence evaluate the feasibility of the approach. The overheads are measured relative to message passing performance on native Transputer networks, and are shown to be significant. It is concluded that although the specific tuple space model is not ideally suited to Transputer-based systems and the implementation, as it stands, is too inefficient to be of practical use, the approach requires further exploration in order to exhaust its full research potential. / MT2017

No description available.

No description available.

Repetitive low level image processing transformations can be performed at high speeds by SIMD arrays, DSP and dedicated VLSI devices. These strategies cannot be adppted with more complex and time consuming data dependent algorithms. A flexible and programmable component must be used, and the use of many such devices in parallel, using dynamic load balancing techniques, is necessary to enable acceptable execution performance to be obtained. The transputer is a powerful new microprocessor with unique on chip communications facilities. Together with the new parallel programming language, occam, the transputer was specifically designed for parallel processing applications. Large transputer networks can be used for computationally intensive applications. This work has investigated the use of transputers for performing image processing algorithms of all three levels of complexity. Techniques were devised and implemented for the execution of low, medium and high levels of image processing algorithms on a multi-transputer network. A software architecture using SUPPLY and DEMAND processes was designed, and dynamic work load balancing was achieved, operating on a ternary tree network of up to 32 transputers. Some 80 image processing algorithms were successfully implemented within the software architecture. In particular, the more complex operation of Feature Extraction was achieved using the multi-transputer system. The Features extracted, involving Convex Hull, Convex Hull Deficiencies, Areas and Perimeters, and Shape Factors were used to build a Feature Vector. The use of this Feature Vector in Scene Interpretation, to realise Learn and Recognise functions has been investigated. The results of the work clearly show that while the system proposed is not as effective at executing repetitive, data intensive transformations as methods mentioned earlier, it can execute more complex Feature Extraction and Scene Interpretation algorithms efficiently. An Efficiency of 85% was achieved for Convex Hull formation, using 32 transputers.

A dissertation submitted to the Faculty of Engineering, University of the Witwatersrand, Johannesburg, in fulfilment of the requirements for the degree of Master of Science in Engineering / The MC2/64 system is a configureable multi-user transputer- based system which was designed using a modular approach. The MC2/64 consists of MC2 Clusters which are connected using a modified Clos network. The MC2 Clusters were designed and realised as completely configurable modules using and extending an algorithm based on Eulerian cycles through a requested graph. This dissertation discusses the configuration algorithm and the extensions made to the algorithm for the MC2 Clusters. The total MC2/64 system is not completely configurable as a MC2 Cluster releases only a limited number of links for inter-cluster connections. This dissertation analyses the configurability of MC2/64, but also presents algorithms which enhance the usability of the system from the user's point of view. The design and the implementation of the network control software are also submitted as topics in this dissertation. The network control software must allow multiple users to use the system, but without them influencing each other's transputer domains. This dissertation therefore seeks to give an overview of network control problems and the solutions implemented in current MC2/64 systems. The results of the research done for this dissertation will hopefully aid in the design of future MC2 systems which will provide South Africa with much needed, low cost, high performance computing power. / Andrew Chakane 2018

No description available.