BCS MPI: a new approach in the software design for large-scale parallel computers

BCS MPI proposes a new approach to design the communication libraries for large scale parallel machines. The emphasis of BCS MPI is on the global coordination of the potentially large number of processes and in the reduction of the non determinism rather than in the traditional optimization of the local performance of a pair of communicating processes. BCS MPI delays the interprocessor communication in order to schedule globally the communication pattern and it is designed on top of a minimal set of collective communication primitives. In this paper we describe a prototype implementation of BCS MPI and its communication protocols. The experimental results, executed on a set of scientific applications representative of the ASCI workload, show that BCS MPI is only marginally slower than the production-level MPI, but much simpler to implement, debug and analyze