https://github.com/alan-turing-institute/hpc-landscape
https://github.com/alan-turing-institute/hpc-landscape
hut23 hut23-562
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/alan-turing-institute/hpc-landscape
- Owner: alan-turing-institute
- Created: 2024-02-16T12:48:53.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-28T14:45:33.000Z (about 2 months ago)
- Last Synced: 2025-02-28T20:18:12.640Z (about 2 months ago)
- Topics: hut23, hut23-562
- Language: Python
- Homepage:
- Size: 811 KB
- Stars: 2
- Watchers: 3
- Forks: 1
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# HPC Landscape
Walkthroughs, documentation and training material for making best use of the Turing’s HPC resouces.
## Overview
The Turing has access to a multitude of HPC resources. For example:
1. Azure - CPU and GPU instances, Azure ML.
2. Baskerville - Intel Xeon CPUs and Nvidia A100 GPUs
3. JADE2 - Intel Xeon CPUs and Nvidia V100 GPUs
4. Dawn - Intel Xeon CPUs and Intel Data Centre Max 1550 GPUs
5. Isambard-AI - Nvidia Grace Hopper superchips (ARM CPUs, H100 GPUs)
See the [Research Computing site](https://mathison.turing.ac.uk/page/3291) 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.
## Structure
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.
## Document generation
At present we rely on GitHub’s markdown capabilities to display content. In the future we may switch to using [Jupyter Book](https://jupyterbook.org/), [Hugo](https://gohugo.io/) or [Jekyll](https://jekyllrb.com/).
## Contributing
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.