Tutorial content

The tutorial material covers three main topics:

1. Introduction to CUDA Python with Numba

   • Begin working with the Numba compiler and CUDA programming in Python

   • Use Numba decorators to GPU-accelerate numerical Python functions

   • Optimize host-to-device and device-to-host memory transfers

2. CUDA kernels in Python with Numba

   • Learn CUDA’s parallel thread hierarchy and how to extend parallel program possibilities

   • Launch massively parallel custom CUDA kernels on the GPU

   • Utilize CUDA atomic operations to avoid race conditions during parallel execution

3. Multi-dimensional grids and shared memory for CUDA Python with Numba

   • Learn support for GPU-accelerated Monte Carlo methods

   • Learn multidimensional grid creation and how to work in parallel on 2D matrices

   • Leverage on-device shared memory to promote memory coalescing while reshaping 2D matrices

(Note: due to this being only a half-day tutorial, it is unlikely that this third topic will be covered during the tutorial session. However, the material will be available for self-study thereafter.)