Parallel graph-reduction with a shared memory multiprocessor system

Abstract

A tightly coupled multiprocessor system where each processor has direct access to a shared memory is studied. The system used for the experiments has only eight processors, but it supports the concurrent fetch and add operation, which is used extensively in the graph-reducer. A parallel graph-reduction technique is developed for such a system, and the measurement of its performance is made via some benchmark programs. As a byproduct, a new on-the-fly garbage collector which combines two different collection techniques has been developed. A new read-only graph-traversal technique for any number of concurrent processes independently traversing a shared graph has also been developed.<>