Optimizing Charm++ over MPI

Charm++ may employ any of a myriad network-specific APIs for handling communication, which are usually promoted as being faster than its catch-all MPI module. Such a performance difference not only causes development effort to be spent on tuning vendor-specific APIs but also discourages hybrid Charm++/MPI applications. We investigate this disparity across several machines and applications, ranging from small InfiniBand clusters to Blue Gene/Q supercomputers and from synthetic benchmarks to large-scale biochemistry codes. We demonstrate the use of one feature from the recent MPI-3 standard to bridge this gap where applicable, and we discuss what can be done today.