Topic outline

  • HLRS logo

    Most HPC systems are clusters of shared memory nodes. To use such systems efficiently both memory consumption and communication time has to be optimized. Therefore, hybrid programming may combine the distributed memory parallelization on the node interconnect (e.g., with MPI) with the shared memory parallelization inside of each node (e.g., with OpenMP or MPI-3.0 shared memory). This course analyzes the strengths and weaknesses of several parallel programming models on clusters of SMP nodes. Multi-socket-multi-core systems in highly parallel environments are given special consideration. MPI-3.0 has introduced a new shared memory programming interface, which can be combined with inter-node MPI communication. It can be used for direct neighbor accesses similar to OpenMP or for direct halo copies, and enables new hybrid programming models. These models are compared with various hybrid MPI+OpenMP approaches and pure MPI. Numerous case studies and micro-benchmarks demonstrate the performance-related aspects of hybrid programming.

    Hands-on sessions are included on all days. Tools for hybrid programming such as thread/process placement support and performance analysis are presented in a "how-to" section. This course provides scientific training in Computational Science and, in addition, the scientific exchange of the participants among themselves.

    This course is a joint training event of EuroCC@GCS and EuroCC-Austria, the German and Austrian National Competence Centres for High-Performance Computing. It is organized by the HLRS in cooperation with the VSC Research Center, TU Wien and NHR@FAU.

    Agenda & Content

    1st day – 23 January 2024

    08:45   Join in
    09:00      Welcome
    09:03      Exascale Supercomputing is coming to Stuttgart: Hunter and Herder
                        Prof. Michael Resch (Director, HLRS)
    09:30      Hunter's hardware architecture and its programming models
                        Dr. Christian Simmendinger (HPE) and Igor Pasichnyk (AMD)
    10:15   Break
    10:30      Introduction to the general MPI+X course with exercises on existing Hawk cluster
    11:15      Programming Models
    11:20         - MPI + OpenMP
    11:50            Practical (how to compile and start)
    12:30   Lunch
    14:00         - continue: MPI + OpenMP
    14:45   Break
    15:00         - continue: MPI + OpenMP
    15:45            Practical (how to do pinning)
    16:15            Q & A
    16:30   End of first day

    2nd day – 24 January 2024

    08:45   Join in
    09:00         - continue: MPI + OpenMP
    09:00            Practical (hybrid through OpenMP parallelization)
    10:30   Break
    10:45         - Overlapping Communication and Computation
    11:15            Practical (taskloops)
    12:15         - MPI + OpenMP Conclusions
    12:30   Lunch
    14:00         - MPI + Accelerators
    15:00   Break
    15:15         - MPI + Accelerators (continued)
    16:15           Q & A
    16:30   End of second day

    3rd day – 25 January 2024

    08:45   Join in
    09:00      Programming Models (continued)
    09:05         - MPI + MPI-3.0 Shared Memory
    10:00   Break
    10:15         - MPI Memory Models and Synchronization
    11:00   Break
    11:15         - Pure MPI
    11:35         - Recap - MPI Virtual Topologies
    12:05         - Topology Optimization
    12:30   Lunch
    14:00         - Topology Optimization, continued
    14:10      Conclusions
    14:25            Practical (replicated data)
    15:45      Q & A, Feedback
    16:00            Q & A
    16:30   End of third day (course)

    Date: Tuesday, January 23, 2024, 08:45 - Thursday, January 25, 2024, 16:30
    Location:  HLRS, Room 0.439 / Rühle Saal, University of Stuttgart, Nobelstr. 19, D-70569 Stuttgart, Germany


    Rolf Rabenseifner (HLRS), Claudia Blaas-Schenner (VSC Team, TU Wien), Georg Hager (RRZE)

    Course material (here ☺):

  • Slides

  • Exercises

  • Miscellaneous information