Automatic parallelization and scheduling of programs on multiprocessors using CASCH

Abstract

The lack of a versatile software tool for parallel program development has been one of the major obstacles for exploiting the potential of high-performance architectures. In this paper, we describe an experimental software tool called CASCH (Computer Aided SCHeduling) for parallelizing and scheduling applications to parallel processors. CASCH transforms a sequential program to a parallel program with automatic scheduling, mapping, communication, and synchronization. The major strength of CASCH is its extensive library of scheduling and mapping algorithms representing a broad range of state-of-the-art work reported in the recent literature. These algorithms are applied for allocating a parallelized program to the processors, and thus the algorithms can be interactively analyzed, tested and compared using real data on a common platform with various performance objectives. CASCH is useful for both novice and expert programmers of parallel machines, and can serve as a teaching and learning aid for understanding scheduling and mapping algorithms.