Description
This lesson provides an introduction to using Cirrus for users who:
- have already used other HPC systems; and
- want to use pre-installed simulation/modelling packages rather than compiling their own.
The lesson aims to answer the following questions:
- What hardware is available on Cirrus?
- What does it consist of (login nodes, compute nodes, file systems, backup)?
- How does this impact me as a user?
- How can I access Cirrus interactively and transfer data?
- What does the Cirrus software environment look like and how do I access software?
- How do I write job submission scripts and submit them to the Cirrus scheduler?
- How can I be a good Cirrus citizen?
- How can I check what resources I am using and look at historical usage?
- What are the next steps for me using Cirrus and how can I get more help?
General Information
When: 8 July 2024. Add to your Google Calendar.
Requirements: Participants must have a working laptop or desktop computer with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.) that they have administrative privileges on. They should have access to a terminal (Mac and Linux users should have a terminal installed by default; Windows users should get either MobaXterm. They are also required to abide by the Cirrus Terms and Conditions of Access.
Accessibility: Materials will be provided in advance of the lesson and large-print handouts are available if needed by notifying the organizers in advance. If we can help making learning easier for you (e.g. sign-language interpreters, lactation facilities) please get in touch (using contact details below) and we will attempt to provide them.
GPU queue reservations: The organisers of this course have reserved GPU nodes specifically for this course. To run on the GPU reservation, you will need to use the following Slurm variables:
#!/bin/bash
#SBATCH --job-name=my_mpi_job
#SBATCH --time=0:10:0
#SBATCH --account=ic084
#SBATCH --partition=gpu
#SBATCH --qos=reservation
#SBATCH --reservation=<reservation_id>
# Instructions to be run by Slurm
You will need to replace <reservation_id> with the appropriate ID:
| Reservation date and time | Reservation ID |
|---|---|
| 13:30-16:00 on 8th July | ic084_1263984 |
| 09:00-19:00 on 9th July | ic084_1263955 |
| 09:00-19:00 on 10th July | ic084_1264032 |
| 08:30-19:00 on 11th July | ic084_1263958 |
| 09:00-16:00 on 12th July | ic084_1263951 |
Contact: Please email support@cirrus.ac.uk for more information.
Prerequisites
You should have used remote HPC facilities before. In particular, you should be happy with connecting using SSH, know what a batch scheduling system is and be familiar with using the Linux command line. You should also be happy editing plain text files in a remote terminal (or, alternatively, editing them on your local system and copying them to the remote HPC system using
scp).