Complete parallelization of computations: integration of data partitioning and functional parallelism for dynamic data structures

摘要

This paper presents a parallel programming system which: supports complete parallelization of array-oriented computations through a coherent integration of data partitioning parallelization and functional decomposition based parallelization; and implements a declarative representation of operations over distributed dynamic arrays. The conceptual framework for this integration is a generalized dependence graph model of parallel computation. The properties of the programming system are illustrated by an example: a red/black parallel solver for linear systems.