Рет қаралды 575
!!! Get the material discussed in the course and any other relevant information from here: github.com/omlins/julia-gpu-c...
Dr. Samuel Omlin (Computational Scientist | Responsible for Julia computing, CSCS) hold for the second time together with the guest instructor Dr. Tim Besard (Creator and Lead developer of CUDA.jl, JuliaHub Inc.) the course "GPU Programming with Julia" at the Swiss National Supercomputing Centre (CSCS). This 2nd edition took place on-site at CSCS in Lugano from November 22 to 24, 2023.
The programming language Julia is being more and more adopted in High Performance Computing (HPC) due to its unique way to combine performance with simplicity and interactivity, enabling unprecedented productivity in HPC development. This course discusses both basic and advanced topics relevant for single and Multi-GPU computing with Julia. It focuses on the CUDA.jl package, which enables writing native Julia code for GPUs. This course combines lectures and hands-on sessions.
Part 1
00:00: Introduction to the course
03:23: Introduction to part 1 ( • 2023 - GPU with Julia ... )
04:59: Presentation of notebook 1-0: Introduction ( • 2023 - GPU with Julia ... )
24:19: Presentation of notebook 1-1: Array programming ( • 2023 - GPU with Julia ... )
43:18: Presentation of notebook 1-2: Application analysis and optimization ( • 2023 - GPU with Julia ... )
1:33:22: Presentation of notebook 1-3: Kernel programming ( • 2023 - GPU with Julia ... )
2:25:23: Presentation of notebook 1-4: Kernel analysis and optimization ( • 2023 - GPU with Julia ... )
3:19:16: Presentation of notebook 2-1: CUDA libraries ( • 2023 - GPU with Julia ... )
3:41:08: Presentation of notebook 2-2: Memory management ( • 2023 - GPU with Julia ... )
4:03:44: Presentation of notebook 2-3: Concurrent computing ( • 2023 - GPU with Julia ... )
Part 2
00:51: High-speed introduction/thoughts on GPU supercomputing ( • 2023 - GPU wth Julia p... )
08:38: Overview on course notebooks of part 1 ( • 2023 - GPU wth Julia p... )
11:08: Presentation of notebook 1: Memory copy and performance evaluation ( • 2023 - GPU wth Julia p... )
43:59: Walk through solutions of notebook 2: Application performance evaluation and optimization ( • 2023 - GPU wth Julia p... )
58:29: Presentation on sustainable HPC building block development in Julia ( • 2023 - GPU wth Julia p... )
1:27:56: Walk through solutions of notebook 3: Using shared memory ( • 2023 - GPU wth Julia p... )
1:37:35: Walk through solutions of notebook 4: Steering registers and using warp level functions ( • 2023 - GPU wth Julia p... )
1:57:02: Walk through solutions of notebook 5: Distributed parallelization ( • 2023 - GPU wth Julia p... )