The aim of this course is to give people with some programming experience an introduction into the parallel programming models MPI and OpenMP. It starts on beginners level but also includes advanced features of the current standards. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the constructs of the Message Passing Interface (MPI) and the shared memory directives of OpenMP.
The first two days are an introduction to MPI and OpenMP, which includes a deep introduction to nonblocking MPI communication, and also touches newer OpenMP-4.0 features, such as the vectorization directives, thread affinity and OpenMP places.
The last two days are dedicated to advanced methods in MPI, e.g., the group and communicator concept, process topologies, derived data types, and one-sided communication. This course also includes latest features of MPI-3.0/3.1, e.g., the new MPI-3.0 shared memory programming model within MPI, the new Fortran language binding, nonblocking collectives, and neighborhood communication. Hybrid MPI+OpenMP programming is also addressed, as well as the parallelization of implicit and explicit solvers, which also includes a short tutorial about PETSc.
Content level: 40% for beginners, 30% intermediate, 30% advanced.