Directive-based GPU programming with OpenACC (Trainingskurs, online)

Anfang
29.10.2024 08:00 Uhr
Ende
31.10.2024 12:00 Uhr
Veranstaltungsort
online

(Kurs-Nr. 1202024 im Trainingsprogramm 2024 des Forschungszentrums Jülich)

Der Kurs findet als Online-Veranstaltung statt. Der Link zur Online-Plattform wird nur den registrierten Teilnehmer:innen bekannt gegeben.

Inhalt:

GPU-accelerated computing drives current scientific research. Writing fast numeric algorithms for GPUs offers high application performance by offloading compute-intensive portions of the code to the GPU. The course will cover basic aspects of GPU architectures and programming. Focus is on the usage of the directive-based OpenACC programming model which allows for portable application development. Examples of increasing complexity will be used to demonstrate optimization and tuning of scientific applications.

Topics covered will include:

  • Introduction to GPU/Parallel computing
  • Programming model OpenACC
  • Interoperability of OpenACC with GPU libraries (like cuBLAS and cuFFT) and CUDA
  • Multi-GPU Programming with MPI and OpenACC
  • Tools for debugging and profiling
  • Performance optimization

The course consists of lectures and interactive hands-on sessions in C or Fortran (the attendee’s choice).

Contents level

in hours

in %

Beginner's contents:

0

0 %

Intermediate contents:

6

50 %

Advanced contents:

6

50 %

Community-targeted contents:

0

0 %

If you are interested in GPU Programming with OpenACC, please also have a look at the respective modules of the CUDA Course at the beginning of the year:
GPU Programming with CUDA - Basics
GPU Programming - Advanced Topics

Voraussetzungen:

Some knowledge about Linux, e.g. make, command line editor, Linux shell (see for instance this overview), some experience in C

Zielgruppe:

Scientists who want to use GPU systems with OpenACC

Sprache:

Der Kurs wird auf Englisch gehalten.

Dauer:

4 halbe Tage

Zeit:

29. Oktober-1. November 2024, 09:00-13:00 Uhr

Ort:

online

Teilnehmerzahl:

mindesten 5, maximal 28

Referenten:

Dr. Andreas Herten, Dr. Thorsten Hater, Dr. Kaveh Haghighi-Mood, Dr. Jan Meinke, JSC;
Jiri Kraus, Markus Hrywniak, NVIDIA

Kontakt:

Dr. Andreas Herten

Co-Lead of division Novel System Architecture design, head of ATML Accelerating Devices PI in Helmholtz Information Program 1, Topics 1 and 2

  • Institute for Advanced Simulation (IAS)
  • Jülich Supercomputing Centre (JSC)
Gebäude 16.3 /
Raum 228
+49 2461/61-1825
E-Mail

Anmeldung:

Bitte melden Sie sich bis zum 15. Oktober 2024 über das Anmeldeformular an.

Letzte Änderung: 02.09.2024