Loading Events

Pawsey’s Advanced HIP Workshop – Conduct 1

24 October - 25 October 2023
9:00am - 2:30pm

The Heterogeneous Interface for Portability (HIP) provides a programming framework for harnessing the compute capabilities of multicore processors, such as the AMD Instinct MI250X GPU’s on Setonix.

As an extension to the beginner’s course, we will focus on some advanced topics with the aim of maximising your benefit from using HIP in a multi-GPU environment.

Agenda

24-25 October 2023

The following topics are designed to be taught over 2 days:

  • How to use HIP applications on Setonix.
  • Access memory spaces from the host and the kernel. 
  • Strategies to get the best performance from your kernels.                                                                                                                                                                                           
  • Optimise application performance with asynchronous IO.
  • Tips and techniques for porting applications from CUDA to HIP.
  • Programming challenge – choose your own adventure in programming with HIP!

Suggested Pre-requisites:

Register Here

2023-10-24-25 Advanced HIP Workshop Conduct 1

  • List your primary domain / research field.
  • For example, PhD, Masters, Researcher, etc.
    A Pawsey Friend receives occasional newsletters with Pawsey-related updates ranging from events, job opportunities, training, news and more.

About your trainer: Toby Potter

Dr. Toby Potter

Dr. Toby Potter is a computational physicist and proprietor of Pelagos Consulting and Education.

He has a keen interest in using computers to solve problems and showing others how to do the same. Toby was a Pawsey (then iVEC) intern in 2007 and went on to complete a doctorate in computational Astrophysics at UWA and a postdoc in computational geophysics at the Centre for Energy Geoscience (UWA).

Toby has experience in CUDA, HIP and OpenCL parallel processing frameworks and is the author of the workshop material.

At Pelagos Toby uses his background to translate mathematical ideas into software and makes challenging concepts easier for clients in industry, government, and academia.