Introduction to Hybrid Programming in HPC
    @ LRZ (Garching near Munich, Germany),
    January 28-29, 2019

    Description:

    Most HPC systems are clusters of shared memory nodes. Such SMP nodes can be small multi-core CPUs up to large many-core CPUs. Parallel 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 both 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.

    The course is a PRACE Advanced Training Center event. It is organized by LRZ in cooperation with HLRS, RRZE, and VSC (Vienna Scientific Cluster).

    Agenda & Content (preliminary):

    1st day:

    09:30   Registration
    10:00      Welcome
    10:05      Motivation
    10:15      Introduction
    10:45      Programming Models
    10:45       - Pure MPI
    11:15   Coffee Break
    11:35       - Topology Optimization
    12:00         Practical (application aware Cartesian topology)
    13:00   Lunch
    14:00       - MPI + MPI-3.0 Shared Memory
    14:45         Practical (replicated data)
    15:30   Coffee break
    15:50       - MPI Memory Models and Synchronization
    16:50         Practical (substituting pt-to-pt by shared memory)
    17:30         Practical (substituting barrier synchronization by pt-to-pt)
    18:00   End

    Social Event (self paying)

    2nd day:

    09:00      Programming Models (continued)
    09:00       - MPI + OpenMP
    10:00         Practical (how to compile and start)
    10:30   Coffee Break
    10:50       - Example with Jacobi Solver
    11:00         Practical (hybrid through OpenMP parallelization)
    13:00   Lunch
    14:00       - Overlapping Communication and Computation
    14:20         Practical (taskloops)
    15:00   Coffee Break
    15:20       - MPI + OpenMP Conclusions
    15:30       - MPI + Accelerators
    15:45      Tools
    16:00      Conclusions
    16:15      Q & A
    16:30   End

    Prerequisites:

    Basic MPI and OpenMP knowledge as presented in the LRZ course "Parallel programming of High Performance Systems" or in our VSC Training Courses on MPI and OpenMP.
    For the hands-on sessions you should know Unix/Linux and either C/C++ or Fortran in particular.

    Lecturers:

    Georg Hager (RRZE / HPC, Uni. Erlangen), Rolf Rabenseifner (HLRS, Uni. Stuttgart),
    Claudia Blaas-Schenner and Irene Reichl (VSC Team, TU Wien)

    Language:

    English

    Date, Time, and Location:

    28.01.2019 9:30 - 29.01.2019 16:30

    Leibniz-Rechenzentrum der Bayerischen Akademie der Wissenschaften, Boltzmannstra├če 1, 85748 Garching near Munich, Germany, Kursraum 2 (H.U.010).

    Registration:

    Registration via Opens external link in new windowevents.prace-ri.eu/event/807/registration/register

    Registration deadline is Monday, January 14, 2019. The maximum number of registrants is 36.

    Fee:

    This course is a PRACE Advanced Training Center event.

    Therefore, the course is free of charge for all participants from the EU or from PRACE-member-countries.

    Further Information - see course pages at:

    LRZ: Opens external link in new windowwww.lrz.de/services/compute/courses/2019-01-28_hhyp1w18

    HLRS: Opens external link in new windowwww.hlrs.de/training/2019/HY-G

    PRACE: Opens external link in new windowevents.prace-ri.eu/e/LRZ-2019-HHYP1W18

    Local Organizer and Contact:

    Volker Weinberg, weinberg(at)lrz.de

     

    Training events (further courses) at:

    VSC: Opens external link in new windowvsc.ac.at/training

    HLRS: Opens external link in new windowwww.hlrs.de/training

    LRZ: Opens external link in new windowwww.lrz.de/services/compute/courses/

    PRACE: Opens external link in new windowevents.prace-ri.eu or Opens external link in new windowwww.training.prace-ri.eu