Introduction to cluster computing at the NBI

The HPC facilities at the NBI provide a fantastic resource for computational biology. The course will introduce you to these facilities and provide hands on experience in how to use them.

During the course you will learn:

• Some background on what the HPC facilities are and how they differ from a desktop computer
• How to connect to the HPC cluster, and move your data back and forth
• How to launch programs, monitor them and interpret their output
• Where to go to get more information and help

Some basic familiarity with the Linux/Unix command line shell is necessary for the course. For example, the experience provided by the Introduction to Linux training would be ideal.

Contents

• An example of cluster use
  • Connect to the cluster
  • Get the data set
  • Decompress the FASTA file
  • Building a database
  • Generating a query
  • Getting the results
• Downloading data
  • Cluster home directory
  • I need more storage space
  • Exercises
• Connecting to the cluster
  • From Windows
  • From Mac/Linux
  • Exercises
• Working interactively
  • Exercises
• Finding software
  • Find out about available software
  • Loading software
  • Exercises
• Editing files
  • Exercises
• Creating and submitting slurm jobs
  • Job control files
  • Job submission
  • Job control files in more detail
  • Exercises
• Listing partitions
  • Exercise
• Inspecting resources used
  • Exercises
• How busy is the cluster?
  • squeue
  • snoderes
  • Exercises
• Cancelling a running job
  • Exercises
• Further reading