The High-Performance Computing Center Stuttgart (HLRS) is hosting an online introductory course on OpenMP offloading with AMD GPUs on 22 October 2024.
OpenMP is a major option for accelerating or offloading computations on today's heterogeneous computer systems using GPUs. This course provides an introduction to AMD Instinct GPU and Accelerated Processing Unit (APU) architectures, laying the foundations of how GPUs work and can be used for offloading in OpenMP. It also covers new features of recent OpenMP versions and GPUs, such as the unified memory programming model, which makes writing HPC applications much easier for a wide range of GPU programming models. Additionally, tools for performance analysis and optimization will be presented.
This course is designed for beginners in GPU programming who have basic knowledge of parallelization with OpenMP and/or MPI on CPUs. After completing this course, you will have learned the basics and will be confident in porting your applications from a CPU-only system to systems with discrete GPU accelerators or APUs.
