Using OpenMP with GPUs
GPUs are powerful devices, but not trivial to use. If you want to discover how to offload the execution of your code to GPUs, and leverage the parallelism available on GPUs, then this hands-on workshop is for you.
You can join in-person OR virtually. This is a free workshop. Please register only if you plan to attend.
Please join at 12:45pm (AWST) to ensure you can access the system. The class starts promptly at 1:15pm.
Date: 8 December 2023, 12:45pm – 4:15pm
Location: Pawsey Supercomputing Research Centre, Kensington
What will I learn in this 3-hour, hands-on workshop?
This workshop is a gentle introduction to OpenMP for GPUs: the reference in the High-Performance Computing world for shared memory programming over the last 25+ years, which has recently become a viable solution for GPU offloading. This workshop will address how to:
- offload the execution of my code to a GPU.
- move the data to and from the GPU.
- let the data on the GPU to avoid extra, costly, memory transfers.
- enable parallelism on the GPU.
- use multiple GPUs.
- leverage asynchronous execution.
How about a more technical look at the agenda?
- Motivation: why use OpenMP with GPUs?
- Offloading (target construct)
- data mapping (map clause and target data construct)
- data environment (target enter data and target exit data constructs)
- multi-level parallelism (teams and distribute constructs and dist_schedule clause)
- multi-GPUs (device clause)
- asynchronous (depend clause)
Pre-requisites:
- You must be familiar with at least one of the following languages:
- C/C++ (Refresher videos) or
- Fortran
- You do not need to have taken the first workshop. Find more information at: Introduction to OpenMP for CPUs
Meet your Trainer!
Dr. Ludovic Capelli is a teaching fellow at EPCC, the High-Performance Institute of the University of Edinburgh, UK. His efforts are exclusively dedicated to the education of HPC, being part of the teaching team for both on-campus and online versions of the MSc in HPC and MSc in HPC with Data Science at EPCC. He focusses primarily on two major HPC technologies: OpenMP and MPI, being a member of the OpenMP language committee and the MPI forum, as well as the course organiser for the “Advanced Message-Passing Programming” module at EPCC.
Registrations have closed