High Productivity Languages for Parallel Programming Compared to MPI

Two new high productivity parallel programming languages, Chapel (Cray) and X10 (IBM), are compared to the message passing interface (MPI) parallel programming environment. The study qualitatively compares language features used to develop a prototype publication/subscription system. Our results show that the global partitioned address space (GPAS) and support for other parallel processing abstractions, employed by each of the new languages, increases productivity and reduces time to solution for parallel program development.