A four-day online course on the AMD Instinct GPU architecture and its ROCm ecosystem, including the tools to develop or port HPC or AI applications to AMD GPUs, will be organized by High-Performance Computing Center Stuttgart (HLRS), in cooperation with AMD and Max Planck Computing and Data Facility (MPCDF), from 21 to 24 April 2026. This course will help participants to learn how to use and program the Accelerated Processing Units (APUs) in HLRS's system Hunter. Participants will be introduced to the programming models for discrete GPUs and APUs.
The new unified memory programming model makes writing HPC applications much easier for a wide range of GPU programming models. The training will cover how to use pragma-based languages such as OpenMP, the basic GPU programming language HIP, and the performance portable language Kokkos. In addition, there will be presentations on other important topics such as GPU-aware MPI and Affinity. The AMD tool suite, including the debugger and the profiling tools, will also be covered. A short introduction will be given on using GPUs with Python and container workflows, in particular for AI workflows.
Participants will learn about the many GPU programming languages for AMD GPUs, understand how to get performance scaling, gain knowledge about the AMD programming tools, get an introduction to the AMD Machine learning software, and learn about profiling and debugging.
