Summary and Schedule
This is a new lesson built with The Carpentries Workbench.
| Setup Instructions | Download files required for the lesson | |
| Duration: 00h 00m | 1. Introduction to HPC Systems |
What is a High Performance Computing cluster? What is the difference between an HPC cluster and the cloud? How can an HPC cluster help me with my research? What HPC clusters are available to me and how do I get access to them? |
| Duration: 00h 00m | 2. Accessing and Using HPC Resources |
How do I get an account to access Iridis? How is my connection to an HPC system secured? How can I connect to an HPC system? What ways are there to get data on to and from an HPC system? How should I manage my data on an HPC system? What software is available on an HPC system, and how do I access it? |
| Duration: 00h 05m | 3. Introduction to Job Scheduling |
What is a job scheduler and why is it needed? What is the difference between a login node and a compute node? How can I see the available resources and queues? What is a job submission script? How do I submit, monitor, and cancel a job? How (and when) should I use an interactive job? |
| Duration: 00h 05m | 4. Introduction to Programmatic Parallelism |
What is parallelisation and how does it improve performance? What are the different types of parallelisation? Why does synchronisation matter? |
| Duration: 00h 05m | 5. Landscape of HPC Technologies |
Which programming language should I use? What are the main ways we can parallelise a program on modern HPC systems? How do OpenMP and MPI differ in how they achieve parallelism? What role do GPUs play in HPC, and how do approaches like CUDA and OpenACC use them? |
| Duration: 00h 05m | 6. Measuring and improving parallel performance |
Why is it important for code to scale well on large HPC
systems? What can go wrong if we try to optimise too early in the development process? |
| Duration: 00h 05m | Finish |
The actual schedule may vary slightly depending on the topics and exercises chosen by the instructor.