- https://www.nat-esm.de/services/trainings/events/directive-based-gpu-programming-with-openacc
- Directive-based GPU programming with OpenACC
- 2024-10-29T09:00:00+01:00
- 2024-11-01T13:00:00+01:00
- The course will cover basic aspects of GPU architectures and programming.
Oct 29, 2024
09:00 AM
to
Nov 01, 2024
01:00 PM
(Europe/Berlin / UTC100)
Online
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
Prerequisities:
Some knowledge about Linux, e.g. make, command line editor, Linux shell (see for instance this overview), some experience in C
Target group:
Scientists who want to use GPU systems with OpenACC