[ONLINE] Directive-based GPU programming with OpenACC @ JSC

Oct 26, 2022, 9:00 AM → Oct 28, 2022, 1:00 PM CET

Online course

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 9 October  2022, the maximal number of participants is limited. Applicants will be notified two weeks before the course, whether they are accepted for participation. The link to the course platform will be sent shortly before the course.

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 a.herten@fz-juelich.de

Onboarding README.md README.pdf

Wednesday, October 26

9:00 AM → 9:15 AM Welcome, Introduction

Speaker: Andreas Herten (staff@fz-juelich.de)

9:15 AM → 10:30 AM GPU Introduction

Speaker: Andreas Herten (staff@fz-juelich.de)

10:30 AM → 10:50 AM Break

10:50 AM → 1:00 PM OpenACC Introduction

Speaker: Andreas Herten (staff@fz-juelich.de)

Thursday, October 27

9:00 AM → 10:25 AM Debugging OpenACC

Speaker: Dr Thorsten Hater (JSC)

10:25 AM → 10:45 AM Break

10:45 AM → 12:15 PM Performance Optimization

Speaker: Markus Hrywniak (NVIDIA)

12:15 PM → 1:00 PM OpenACC Interoperability

Speaker: Dr Kaveh Haghighi Mood (staff@fz-juelich.de)

Friday, October 28

9:00 AM → 9:30 AM OpenACC Interoperability (Continued)

Speaker: Dr Kaveh Haghighi Mood (staff@fz-juelich.de)

9:30 AM → 1:00 PM Multi-GPU Programming

Speaker: Jiri Kraus (NVIDIA)

10:45 AM → 11:05 AM Break