AI Technology Workshop Series: Fundamentals of Accelerated Computing with Modern CUDA C++

Course Description

Welcome to our immersive AI technology workshop series. During these sessions you will be introduced to new and established AI tools that will help you create and manipulate content in new and powerful ways. Each session is led by an industry expert who will guide you through the material and share its real-world implications

GPU acceleration is essential for high-performance computing, artificial intelligence, and scientific applications. This hands-on workshop introduces the fundamentals of GPU programming using modern CUDA C++, enabling participants to accelerate existing C++ applications and develop efficient parallel algorithms. Students will explore GPU architecture, CPU-GPU execution and memory models, and parallel programming using NVIDIA CUDA Core Libraries, including Thrust and CUB. Through practical exercises, they will learn to optimize data movement, leverage asynchronous execution and CUDA streams, and implement custom GPU kernels. The workshop emphasizes modern C++ programming techniques, performance profiling, and practical optimization strategies using NVIDIA development tools.

Learning Outcomes At the conclusion of the workshop, you should be able to

• Accelerate C++ applications using CUDA, GPU architecture, and parallel libraries.
• Optimize GPU performance using asynchronous execution, memory management, and profiling tools.
• Develop efficient CUDA kernels using threads, shared memory, synchronization, and atomic operations.