Walkthroughs, documentation and training material for making best use of the Turing’s HPC resouces.
The Turing has access to a multitude of HPC resources. For example:
- Azure - CPU and GPU instances, Azure ML.
- Baskerville - Intel Xeon CPUs and Nvidia A100 GPUs
- JADE2 - Intel Xeon CPUs and Nvidia V100 GPUs
- Dawn - Intel Xeon CPUs and Intel Data Centre Max 1550 GPUs
- Isambard-AI - Nvidia Grace Hopper superchips (ARM CPUs, H100 GPUs)
See the Research Computing site on Mathison for a full list of available computing resources.
This repository collects together useful walkthroughs developed in-house at the Turing to make use of these HPC resources more manageable and effective.
The repository is structured by compute resource. Some material may be relevant to multiple systems and where this is the case we’ve tried to make this clear.
At present we rely on GitHub’s markdown capabilities to display content. In the future we may switch to using Jupyter Book, Hugo or Jekyll.
We welcome contributions. If you’d like to contribute, please submit a pull request to the repository in the normal way. This will be reviewed by the Research Computing Platforms team prior to merging.