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).

This course will take place as an online event. The link to the online platform will be provided to the registrants only.

Prerequisites: Some knowledge about Linux, e.g. make, command line editor, Linux shell (see for instance this overview), a little experience in C/Fortran

Application
Registrations are only considered until 2 November 2020, the maximal number of participants is limited. Applicants will be notified, whether they are accepted for participitation.

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

Contact
For any questions concerning the course please send an e-mail to [email protected]
https://events.prace-ri.eu/event/1075/