Evaluation of Remote Memory Access Communication on the IBM Blue Gene/P Supercomputer

This paper evaluates the performance of remote memory access (RMA) communication and its capabilities on the blue gene/P supercomputer. This study includes the high performance implementation and performance of global arrays (GA) and its runtime system, aggregate remote memory copy interface (ARMCI). Our implementation of GA/ARMCI on blue gene/P is on top of the IBM deep computing messaging framework (DCMF), a communication runtime designed for the Blue Gene/P machine to easily support several programming paradigms such as message passing interface (MPI) and remote memory access (e.g. GA/ARMCI). The performance of DCMF, ARMCI, and GA are studied and compared to MPI performance.