Prioritization in Parallel Computing (extended abstract)
Authors:
L.V. Kale
Parallel Programming Laboratory, Department of Computer Science, University
of Illinois at Urbana-Champaign
US/Japan Workshop on Parallel Symbolic Computing, October 1992, Boston, MA. [Internal Report #93-16]
It is argued that scheduling is an important determinant of performance for many parallel symbolic computations, over and above the issues of dynamic load balancing and grainsize control. We propose associating unbounded levels of priorities with tasks and messages as the mechanism of choice for specifying scheduling strategies. We demonstrate how priorities can be used in parallelizing computations in different search domains, and show how priorities can be implemented effectively in parallel systems.