OpenCL Workshop: June 21-22, 28-29
Note this course is spread over two weeks:
- Part 1 (two days): 21-22 June 2023
- Part 2 (two days): 28-29 June 2023
About this workshop:
Supercomputers make use of accelerators from a variety of different hardware vendors, using devices such as multi-core CPU’s, GPU’s and even FPGA’s. OpenCL is a way for your HPC application to make effective use of heterogeneous computing devices, and to avoid code refactoring for new HPC infrastructure.
Join Pawsey experts as we conduct a four-day workshop to explore, debug, and optimise OpenCL applications.
Agenda
Day 1
- Introduction to OpenCL
- How to build and run applications on Setonix with OpenCL and MPI
- Matrix multiplication with OpenCL – fully explained line by line
Day 2
- How to debug OpenCL applications and kernels
- Measure performance with OpenCL Events and open source tools
- Memory management
Day 3
- Coarse and fine-grained shared memory
- Strategies for building optimised OpenCL kernels
- Optimise IO performance with asynchronous operations
Day 4
- Programming challenge – choose your own adventure in working with OpenCL
– or –
- Bring your own code and receive feedback and assistance
Register here:
About your trainer: 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.