Parallel AI Planning on the SCC

We present in this paper a parallelized version of an existing Artificial Intelligence automated planner, implemented with standard programming models and tools (hybrid OpenMP/MPI). We then evaluate this planner with respect to its sequential version through extensive experiments over a wide range of academic benchmarks, on two different target architectures: a small standard cluster and the research processor SCC (“Single-chip Cloud Computer”) developed by Intel Labs and made available to the research community through the MARC program (“Many-core Applications Research Community”). We obtain interesting speedups (super-linear in some cases) on both architectures. Interestingly enough, these experiments also reveal different behaviors between the cluster and the SCC.