Programming Parallel Computers

Abstract

This paper is from a keynote address to the IEEE International Conference on Computer Languages, October 9, 1988. Keynote addresses are expected to be provocative (and perhaps even entertaining), but not necessarily scholarly. The reader should be warned that this talk was prepared with these expectations in mind.Parallel computers offer the potential of great speed at low cost. The promise of parallelism is limited by the ability to program parallel machines effectively. This paper explores the opportunities and the problems of parallel computing. Technological and economic trends are studied with a view towards determining where the field of parallel computing is going. An approach to parallel programming, called UNITY, is described. UNITY was developed by Jay Misra and myself, and is described in [Chandy]. Extensions to UNITY are discussed; these extensions were motivated by discussions with Chuck Seitz