This course will take place as an online event. The link to the streaming platform will be provided to the registrants only.

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 a GPU.

The course will cover aspects of GPU architectures and programming. Focus is on the usage of the parallel programming language CUDA C++, which allows maximum control of NVIDIA GPU hardware. Examples of increasing complexity are used to demonstrate optimization and tuning of scientific applications.

The foundations of GPU programming are covered in a dedicated Basic Course which include an introduction to GPU/parallel computing, programming with CUDA, GPU libraries, tools for debugging and profiling, and performance optimizations. Please see the CUDA Basics course for registration.

This advanced course consists of modules providing more in-depth coverage of multi-GPU programming, modern CUDA concepts, CUDA Fortran, and portable programming models such as OpenACC and C++ parallel STL algorithms. The advanced modules will be taught from 7-11 July 2025.

Note: The GPU Programming with CUDA course is held in two parts. This is the second course, which contains individual modules to allow for fine-grained selection of topics of relevance.

Contents of Part 1: Basics of GPU Programming with CUDA
Date: 31. March - 4 April 2025, on-site at JSC (see separate announcement)
The agenda of the basic course are given here for completeness. For registration, please see dedicated website.

A) Introduction to GPUs and GPU Computing
B) Programming Model CUDA
C) Tools for Debugging and Profiling
D) GPU Libraries (like cuBLAS, cuFFT)
E) Introduction to Multi-GPU Programming

Contents of Part 2: Advanced GPU Programming
Date: 7-11 July 2025 (this announcement)

A) Advanced Multi-GPU Programming with MPI
B) Advanced Multi-GPU Programming with NCCL and NVSHMEM
C) Advanced and Modern CUDA Concepts (Cooperative Groups, CUB Primitives, Modern C++ Programming)
D) CUDA Fortran
E) GPU Programming with Abstractions (OpenACC, Standard Language Programming (pSTL))

Attendees are invited to pick and choose the parts of the advanced course (A - E) they want to attend. The advanced modules are mostly freestanding. Participants either need to attend the basics course or prove equivalent knowledge of GPU programming in order to participate in the advanced course.

Programmers interested primarily in OpenACC may skip parts D and E of Basics of GPU Programming with CUDA and still choose part E from Advanced GPU Programming. Participation in the full Basics of GPU Programming with CUDA course, however, is recommended.