A Combined Communication and Synchronization Optimization Algorithm for One-Way Communication

As against the conventional send/receive model, the one-way communication is a new paradigm which decouples message transmission and synchronization. This opens up new opportunities not only to further optimize communication but also to minimize synchronization costs. In this paper, we present a generalized technique which makes use of global dataflow framework to optimize communication and synchronization in the context of one way communication model. The uniqueness of our approach stems from the fact that it can take all types of HPF-like alignments and distributions into account and is more powerful than any existing algorithm for eliminating redundant synchronization messages. Preliminary results with several example programs demonstrate that our approach is successful in minimizing the number of data and synchronization messages.