[PhD Thesis] The Exploitation of Parallelism on Shared Memory Multiprocessors

  1. Lookup NU author(s)
Author(s)Stoker MA
Publication type Report
Series Title
Full text is not currently available for this publication.
With the arrival of many general purpose shared memory multiple processor (multiprocessor) computers into the commercial arena during the mid-1980's, a rift has opened between the raw processing power offered by the emerging hardware and the relative inability of its operating software to effectively deliver this power to potential users. This rift stems from the fact that, currently, no computational model with the capability to elegently express parallel activity is mature enough to be universally accepted, and used as the absis for programming languages to exploit the parallelism that multiprocessors offer. To add to this, there is a lack of software tools to assist programmers in the processes of designing and debugging parallel programs. Although much research has been done in the field of programming languages, no undisputed candidate for the most appropriate language for programming shared memory multiprocessors has yet been found. This thesis examines why this state of affairs has arisen and proposes programming language constructs, together with a programming methodology and environment, to close the ever widening hardware to software gap. The novel programming constructs described in this thesis are intended for use in imperative languages even though they made use of the synchronisation inherent in the dataflow model by using the semantics of single assignment when operating on shared data, so giving rise to the term shared values. As there are several distinct parallel programming paradigms, matching flavours of shared value are developed to permit the concise expression of these paradigms.
InstitutionComputing Laboratory, University of Newcastle upon Tyne
Place PublishedNewcastle upon Tyne
NotesBritish Lending Library DSC stock location number: DX172518
ActionsLink to this publication