Charmed HPC¶
Charmed HPC is a platform for managing high-performance computing clusters. It automates the lifecycle of essential cluster software and processes, such as workload management, shared storage, GPU access, and high-bandwidth networking. This allows operations teams and systems administrators to focus on running workloads rather than maintaining infrastructure.
In this documentation¶
Learn more about Charmed HPC: Getting Started tutorial, Underlying projects
Workload management: Deploy Slurm, Manage Slurm, Clean up Slurm, Grafana Dashboards
Storage and Resources: Deploy shared filesystem, GPUs, GRES, Interconnects
Security and Identity: Deploy identity provider, Hardening guidelines, Cryptography
Performance: High availability, Benchmarks
How this documentation is organized¶
This documentation uses the Diátaxis documentation structure.
The Tutorial takes you step-by-step through building a small Charmed HPC cluster, submitting batch jobs, and using container images.
How-to guides assume you have basic familiarity with Charmed HPC. They cover key operations for deploy, integration, management, and usage.
Reference provides technical information such as underlying projects and dependencies, monitoring, and performance benchmarks.
Explanation includes topic overviews, background and context, and detailed discussions of key concepts.
Project and community¶
Charmed HPC is an Ubuntu community project. It’s an open source project that warmly welcomes community contributions, suggestions, fixes, and constructive feedback.
Get involved
Governance and policies
Thinking about using Charmed HPC for your next project? Get in touch!