HPC Cluster at INFN Padova User Guide

This guide describes how the HPC Cluster at INFN Padova is configured and can be used.

It is not intended to explain in detail how SLURM can be used.

Note

This documentation is under development.

Who can use the INFN Padova HPC cluster

The INFN Padova HPC cluster has been funded by the Terabit PNRR project and therefore it can be used for use cases relevant for the project (that must be approved by the relevant bodies).

Available unused resources can be used opportunistically in low priority mode by local INFN Padova users.

Contents

• Getting started
  • Apply for an account
  • Login to the user inteface
  • Manage your application software
  • Submit a batch job
  • Debug your job
  • Run an interactive job
  • Manage containerized applications
  • More information
  • Getting help
• Overview of the INFN Padova HPC Cluster
  • Available SLURM partitions
  • Available QoS
• Storage in the HPC cluster
  • Home directory
  • Shared scratch directory (experimental)
  • Job scratch directory
  • Guidelines
• Application software
  • Application software through CVMFS
  • Application software throgh Environment modules
    • Create your own application module
    • Use environment modules with SLURM
    • Other information
  • Create a new virtual environment with Conda
    • Create the virtual environment
    • Activate the virtual environment
    • Install packages in the virtual environment
    • Deactivate the virtual environment
    • Delete the virtual environment
    • Use Conda virtual environment with SLURM
• Using GPUs
• Running MPI jobs
  • Compiling
  • Submitting a MPI SLURM job
• Accessing the cluster using a web interface (experimental)
  • Graphical Desktop
  • Jupyter Notebook