A Microbenchmark Suite for Mixed-Mode OpenMP/MPI

With the current prevalence of multi-core processors in HPC architectures, mixed-mode programming, using both MPI and OpenMP in the same application, is becoming increasingly important. However, no low-level synthetic benchmarks exist to test the performance of this programming model. We have designed and implemented a set of microbenchmarks for mixed-mode programming, including both point-to-point and collective communication patterns. These microbenchmarks have been run on a number of current HPC architectures: the results show some interesting performance differences between the architectures and highlight some possible inefficiencies in the implementation of MPI on multi-core systems.