PType system: A featherweight parallelizability detector

Abstract

Parallel programming is becoming an important cornerstone of general computing. In addition, type systems have significant impact on program analysis. In this paper, we demonstrate an automated type-based system that soundly detects parallelizability of sequential functional programs. Our type inference system discovers the parallelizability property of a sequential program in a modular fashion, by exploring a ring structure among the program's operators. It handles self-recursive functions with accumulating parameters, as well as a class of non-linear mutual-recursive functions. Programs whose types are inferred to be parallelizable can be automatically transformed to parallel code in a mutumorphic form - a succint model for parallel computation. Transforming into such a form is an important step towards constructing efficient data parallel programs.