Deriving Parallel Codes via Invariants

Systematic parallelization of sequential programs remains a major challenge in parallel computing Traditional approaches using pro gram schemes tend to be narrower in scope as the properties which en able parallelism are di cult to capture via ad hoc schemes In CTH a systematic approach to parallelization based on the notion of preserv ing the context of recursive sub terms has been proposed This approach can be used to derive a class of divide and conquer algorithms In this paper we enhance the methodology by using invariants to guide the parallelization process The enhancement enables the parallelization of a class of recursive functions with conditional and tupled constructs which were not possible previously We further show how such invariants can be discovered and veri ed systematically and demonstrate the power of our methodology by deriving a parallel code for maximum segment product To the best of our knowledge this is the rst systematic parallelization for the maximum segment product problem