A SequenceL interpreter using tuplespaces

Abstract

SequenceL is an implicitly parallelizing language that determines all the parallelisms in a computer program. This thesis is a preliminary investigation into a Tuple space based implementation of SequenceL. The results of the research are: • Tuple space was identified as a simple and straight forward approach to distributed evaluation of SequenceL programs. The tuple space concept matches closely with the SequenceL tableau, parts of which are distributed, evaluated and the result of the evaluation are gathered back. • A SequenceL interpreter and a communication architecture that communicates with a tuple space was developed. • The Gather Work Distribute cycle of the communication architecture was identified to be equivalent to the Consume Simplify Produce strategy followed by SequenceL. • Preliminary testing was conducted and certain enhancements were proposed and implemented.