Directive-based GPU programming with OpenACC (Trainingskurs, online)
Dr. Andreas Herten
(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)
Raum 228
Anmeldung:
Bitte melden Sie sich bis zum 15. Oktober 2024 über das Anmeldeformular an.