On automatic loop data-mapping for distributed-memory multiprocessors

In this paper we present a unified approach for compiling programs for Distributed-Memory Multiprocessors (DMM). Parallelization of sequential programs for DMM is much more difficult to achieve than for shared memory systems due to the exclusive local memory of each Virtual Processor (VP). The approach presented distributes computations among VPs of the system and maps data onto their private memories. It tries to obtain maximum parallelism out of DO loops while minimizing interprocessor communication. The method presented, which is named Graph Traverse Scheduling (GTS), is considered in this paper for single-nested loops including one or several recurrences. In the parallel code generated, dependences included in a hamiltonian recurrence that involves all the statements of the loop are enforced by the sequential execution of the computation assigned to each VP. Other dependences not included in the hamiltonian recurrence and involving data mapped onto different VPs will need explicit communication and synchronization.Peer ReviewedPostprint (author's final draft