GPU Computing 1 & 2
Who is this for?
Everyone interested in learning how to get high performance for Python codes
What will you learn?
- Get an introduction to parallel computing architectures
- Get an introduction to GPU programing in general terms
- Understand the limits and merits of GPU programming and its use with Python
- Implement code using different libraries for parallel programming on GPUs, including, Numba, and PyCUDA.
- Experience how to achieve high performance with Python using the supercomputing facilities at SURF
Why is this important?
Would you like to obtain the best performance from your Python codes and get good scalability even in a supercomputer?
In this course you will learn about parallel programming using Python, a language has become more and more popular among researchers for its simplicity and the availability of specific programming libraries.
In large compute systems it is essential to exploit heterogeneous architectures correctly, and here you will understand the different challenges and how to overcome them with different Python features for GPU platforms that have direct application for scientific computing.
How is the session structured?
Mixture of presenter led explanations and hands-on exercises. Users will have access to the National Supercomputer Snellius, therefore gaining experience with a state-of-the-art computing system, including the Nvidia A100 and H100 GPUs (see Snellius’ Hardware Specifications)
Prerequisite
Attending (or knowledge of the content) in: