Directive-based GPU programming with OpenACC (PRACE training course, online)
Dr. Andreas Herten
(Course no. 1462022 in the training programme 2022 of Forschungszentrum Jülich)
This course will take place as an online event. The link to the streaming platform will be provided to the accepted registrants only.
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).
Some knowledge about Linux, e.g. make, command line editor, Linux shell (see for instance this overview), some experience in C
Scientists who want to use GPU systems with OpenACC
This course is given in English.
3 half days
26-28 October 2022, 09:00-13:00
Number of Participants:
minimum 5, maximum 28
Dr. Andreas Herten, Dr. Thorsten Hater, Dr. Kaveh Haghighi-Mood, JSC;
Jiri Kraus, Markus Hrywniak, NVIDIA
Dr. Andreas Herten
Head of ATML Accelerating Devices
- Institute for Advanced Simulation (IAS)
- Jülich Supercomputing Centre (JSC)
Please register until 9 October 2022 via the PRACE registration form.