Automatic Storage Management for Parallel Programs

This article deals with automatic parallelization of static control programs. During the parallelization process the removal of memory related dependences is usually performed by translating the original program into single assignment form. This total data expansion has a very high memory cost. We present a technique of partial data expansion which leaves untouched the performances of the parallelization process, with the help of algebra techniques given by the polytope model. Keywords : Automatic Parallelization, Memory Management, Array Dataflow Analysis, Scheduling. 1 Introduction This article deals with automatic parallelization in the polytope model. This method can be applied provided that source programs have static control, i.e. are limited to do loops and assignment to array with affine subscripts. The first step is the extraction of exact dependences by array data flow analysis. All memory related dependences, which are due to reuse of data, are deleted by a total data exp..