HPC meets interactive Data Science and Machine Learning

Carme (/ˈkɑːrmiː/ KAR-mee; Greek: Κάρμη) is a Jupiter moon, also giving the name for a Cluster of Jupiter moons (the carme group).

or in our case…

an open source framework to manage resources for multiple users running interactive jobs on a Cluster of (GPU) compute nodes.

Presentations

Marketing Slides

CARME slides (11/2022)

Core Idea

We combine established open source ML and DS tools with HPC backends and use therefore

• Singularity containers
• Anaconda environments
• web–based GUI frontends e.g. Code-Server and JupyterLab
• completely web frontend based
  (OS independent, no installation on user side needed)
• HPC job management and schedulers (SLURM)
• HPC data I/O technologies like Fraunhofer’s BeeGFS
• HPC maintenance and monitoring tools

Job submission scheme

Key Features

• Open source
  • we use only open source components that allow commercial usage
  • Carme is open source, allowing commercial usage
• Seamless integration with available HPC tools
  • Job scheduling via SLURM
  • Native LDAP support for user authentication
  • Integrate existing distributed file systems like BeeGFS
• Access via web-interface
  • OS independent (only web browser needed)
  • requires 2FA
  • Full user information (running jobs, cluster usage, news / messages)
  • Start/Stop jobs within the web-interface
• Interactive jobs
  • Flexible access to accelerators
  • Access via web driven GUIs like code server or JupyterLab
  • Job specific monitoring information in the web-interface
    (GPU/FPGA/CPU utilization, memory usage, access to TensorBoard)
• Distributed multi-node and/or multi-gpu jobs
  • Easy and intuitive job scheduling
  • Directly use GPI, GPI-Space, MPI, HP-DLF and Horovod within the jobs
• Full control about accounting and resource management
  • Job scheduling according to user/project specific roles
  • Compute resources are user/project exclusive
• User maintained, containerized environments
  • Singularity containers
    (runs as normal user, GPU, Ethernet and Infiniband support)
  • Anaconda Environments
    (easy updates, project / user specific environments)
  • Built-in matching between GPU driver and ML/DL tools

Roadmap

• 04/2024: ISC 2024 release
  • Improvements
    • Code improvements for the multi-type accelerators.
  • Planed features
    • One-line installation script
    • DevOps tools implementation (e.g. MLflow)
    • User documentation advanced options (e.g. parallel computation)
    • Mail notifications that are in sync with our JS notifications in the frontend
    • Batch job support

Releases

• 04/2018: Carme prototype at ITWM

• 03/2019: r0.3.0 (first public release)

• 07/2019: r0.4.0

• 11/2019: r0.5.0

• 12/2019: r0.6.0

• 07/2020: r0.7.0

• 11/2020: r0.8.0

• 08/2021: r0.9.0

• 05/2022: r0.9.5

• 09/2022: r0.9.6

• 08/2023: r0.9.7

• 12/2023: r0.9.8 (latest)

Documentation

Visit our documentation.

Who is behind Carme?

Carme is developed by the Competence Center for High Performance Computing at Fraunhofer ITWM.

Contact

→ christian.ortiz@itwm.fraunhofer.de

Sponsors

The development of Carme is financed by research grants from