Best practices in Python: CPU to GPU [online, CPUGPU]

Over the past decade, GPUs have taken a central role in several disciplines where huge amounts of data and intensive computing are required thanks to their significant parallel computing capacity.

Once an obscure art, programming on GPUs is now not that different from writing code for CPUs. It is sometimes even possible to run the same program on one or the other without changing the code.

This leads to the question: when is it advantageous to use a GPU versus one or more CPUs? And in cases where GPU is the right choice, how to get the most out of it and avoid wasting resources?

This workshop, focused on practical examples, will help you make informed choices while presenting you with good usage practices.

• Academic participant : 10$
• Non-academic participant : $200

• Be able to read small code examples

• CPU vs GPU: Overview
• Monitoring tools
• Code profiling tools

Lucas Nogueira, analyst in advanced research computing at Calcul Québec.

English

We will use the Zoom platform. Because this event is a practical workshop, it is very useful having a secondary screen where you would get the instructor window on one screen and your own window on your main screen.

We will use the Jupyter Lab interface. Make sure you have a modern Web browser like Google Chrome, Firefox, Edge or Safari.

For any question, please write to [email protected].

• The workshop is not recorded;
• The workshop could be canceled if the number of registrations is too low.

Host or Publisher Calcul Québec