Automatic localization for distributed-memory multiprocessors using a shared-memory compilation framework

In this paper, we outline an approach for compiling for distributed-memory multiprocessors that is inherited from compiler technologies for shared-memory multiprocessors. We believe that this approach to compiling for distributed-memory machines is promising because it is a logical extension of the shared-memory parallel programming model, a model that is easier for programmers to work with, and that has been studied in great detail as a target for parallelizing and optimizing compilers. In particular, the paper focuses on the localization step, and presents optimal localization algorithms for a single global DOALL, and for special-case structures of multiple global DOALLs.