NHR@FAU Course Program in Summer/Fall 2024

Symbolic picture for the article. The link opens the image in a large view.

We are happy to announce the NHR@FAU course program for summer and fall of 2024. Unless otherwise indicated, all courses include hands-on components.

  • Node-Level Performance Engineering. Four-day online course for HLRS Stuttgart in collaboration with ZIH Dresden, June 18-21.
    This course covers performance engineering approaches on the compute node level. Compute node architecture (CPUs and GPUs), performance bottlenecks, and performance optimization based on the Roofline model are covered in detail.
  • Introduction to the LIKWID Tool Suite. Full-day online course, July 23.
    The LIKWID tool suite is a collection of performance tools for topology exploration, thread/process pinning, hardware performance counting, and more.
  • Node-Level Performance Engineering. Three-day on-site course at NHR@FAU, September 2-4.
    This course covers performance engineering approaches on the compute node level. Compute node architecture (CPUs and GPUs), performance bottlenecks, and performance optimization based on the Roofline model are covered in detail.
  • Introduction to Parallel Programming with OpenMP. Three half-day online course, September 4-6.
    OpenMP is a standard for parallelizing shared-memory C/C++ and Fortran applications. It is supported by major compilers and provides a simple, low-entry barrier for thread-based parallelization. This course with hands-on exercises gives an introduction to the basic workings and constructs used for parallelizing applications with OpenMP, including thread and memory locality, tasking, SIMD, and accelerator offloading.
  • C++ for Beginners. Six-day online course, September 12/13, 19/20, 26/27.
    The focus of this course is on the introduction of the essential language features and the syntax of C++. Additionally, it introduces many C++ software development principles, concepts, idioms, and best practices, which enable programmers to create professional, high-quality code from the very beginning.
  • From Zero to Multi-Node GPU Programming. Three-day online course in collaboration with ZIH Dresden, September 18, September 25, October 2.
    The course covers fundamental tools and techniques for GPU-accelerated C/C++ applications with CUDA. The first day gives an introduction to CUDA programming on a single GPU, while days 2+3 dive into multi-GPU parallel programming one one node and multiple nodes, respectively. It is possible to register for all days separately. The course and the hands-on exercises are part of the NVIDIA DLI program.
  • Modern C++ Software Design. Three-day online course, September 30 – October 2.
    The focus of the training are the essential C++ software development principles, concepts, idioms, and best practices, which enable programmers to create professional, high-quality code. Considerable C++ programming practice is required to benefit from this course.
  • Fundamentals of Accelerated Computing with CUDA Python. Full-day online course, October 7.
    The course covers fundamental tools and techniques for GPU-accelerated Python applications with CUDA and Numba. The course and the hands-on exercises are part of the NVIDIA DLI program.
  • Core-Level Performance Engineering. Full-day online course, October 8.
    This course covers general core architecture for x86 and ARM processors, an introduction to (AT&T and AArch64) assembly code, and performance analysis and engineering using the Open Source Architecture Code Analyzer (OSACA) in combination with the Compiler Explorer. Attendees will work with these tools to analyze compiler-generated assembly kernels and assess their performance properties in detail.
  • Performance Analysis on GPUs with NVIDIA Tools. Half-day online course, October 9.
    This course introduces NVIDIA’s profiler as a tool to spot common performance bugs that arise when porting code to GPUs. Attendees will be able to follow along the demos and conduct their own experiments on the NHR@FAU GPU cluster.
  • Node-Level Performance Engineering. Three-day online course for LRZ Garching, December 3-5.
    This course covers performance engineering approaches on the compute node level. Compute node architecture (CPUs and GPUs), performance bottlenecks, and performance optimization based on the Roofline model are covered in detail.

Please click on the links for more information and registration. For a full overview, please have a look at: NHR@FAU Tutorials and Courses


Dr. Georg Hager

Head of Training & Support

Erlangen National High Performance Computing Center (NHR@FAU)
Training & Support Division