Trainingskurs "Advanced Parallel Programming with MPI and OpenMP"
(Kurs-Nr. 98/2017 im Trainingsprogramm des Forschungszentrums)
Zielgruppe: | Supercomputernutzer, die ihre parallelen Anwendungen mit MPI oder OpenMP optimieren wollen und bereits Erfahrungen mit MPI und OpenMP haben |
Inhalt: | |
Teilnahmevoraussetzungen: | Kenntnisse in Unix, den Programmiersprachen C, C++ oder Fortran, und Erfahrung mit den Prinzipien von MPI mindestens im Umfang des Einführungskurses MPI und OpenMP, z.B.point-to-point message passing, datatypes, nonblocking communication, collective communication; Erfahrungen mit OpenMP 3.0 |
Agenda: | Agenda of Advanced MPI Course at JSC |
Sprache: | Der Kurs wird auf Englischgehalten. |
Dauer: | 3 Tage |
Termin: | 27. - 29. November 2017, 9.00 - 16.30 Uhr |
Ort: | Jülich Supercomputing Centre, Ausbildungsraum 1, Geb. 16.3, Raum 213a |
Teilnehmerzahl: | maximal 28 |
Referent: | Dr. Rolf Rabenseifner, HLRS Stuttgart (für MPI/OpenMP); Dr. Markus Geimer, Michael Knobloch, JSC (für die Tools-Session am 3. Tag) |
Ansprechpartner: | Thomas Breuer Telefon: +49 2461 61-96742 E-mail: t.breuer@fz-juelich.de |
Anmeldung: | Bitte melden Sie sich über das Anmeldeformular am HLRSan. Anmeldeschluss: 29. Oktober 2017 |
Kursmaterial |
The focus is on advanced programming with MPI and OpenMP. The course addresses participants who have already some experience with C/C++ or Fortran and MPI and OpenMP, the most popular programming models in high performance computing (HPC).
The course will teach newest methods in MPI-3.0/3.1 and OpenMP-4.5, which were developed for the efficient use of current HPC hardware. Topics with MPI are the group and communicator concept, process topologies, derived data types, the new MPI-3.0 Fortran language binding, one-sided communication and the new MPI-3.0 shared memory programming model within MPI. Topics with OpenMP are the OpenMP-4.0 extensions, as the vectorization directives, thread affinity and OpenMP places. (The GPU programming with OpenMP-4.0 directives is not part of this course.) The course also contains performance and best practice considerations, e.g., with hybrid MPI+OpenMP parallelisation. The course ends with a section presenting tools for parallel programming.
Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the taught constructs of the Message Passing Interface (MPI) and the shared memory directives of OpenMP. This course provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves. It is organized by JSC in collaboration with HLRS. (Content Level: 20% for beginners, 50% intermediate, 30% advanced).
see also announcement of this course at HLRS