On the Performance of an Algebraic Multigrid Solver on Multicore Clusters
Allison Baker (Lawrence Livermore National Laboratory)
Martin Schulz (Lawrence Livermore National Laboratory)
Ulrike Yang (Lawrence Livermore National Laboratory)
Algebraic multigrid (AMG) solvers have proven to be extremely efficient on distributed-memory architectures. However, when executed on modern multicore cluster architectures, we face new challenges that can significantly harm AMG’s performance. We discuss our experiences on such an architecture and present a set of techniques that help users to overcome the associated problems, including thread and process pinning and correct memory associations. We have implemented most of the techniques in a MultiCore SUPport library (MCSup), which helps to map OpenMP applications to multicore machines. We present results using both an MPI-only and a hybrid MPI/OpenMP model.
Parallel and Distributed Computing, Numerical Algorithms for CS&E, Performance Analysis