Hybrid combinators for distributed evaluation of functional programs

Abstract

This pater presents a strategy for automatically decomposing functional programs into new combinatiors with an optimal grain and distributing them on distributied-memory multicomputers. The program transformation technique proposed here accepts a lambda expression and generates program-derived combinators which are fine-tuned to have a right granularity for a given multiprocessor architectrue. The right granularity is decided by analyzing the weight for each program-derived combinator during translation. We call aprogram-derived combinator at just the right level of granularity the hybird combinator, whcih is composed of a fixed set of combinators suitable for spawning the parallel elements and partitioning them. The hybrid combinator provides an alternative method to the representation and synchronization of processes. This pater shows the parallel graph reduction process, where the hybrid combinators act as the controlling mechanisms by directing when and which subgraph is to be distributed.