Skip to main content
IT Services

What is Apocrita?

Apocrita is a 350 node heterogeneous HPC Cluster running Centos 7 Linux managed by ITS Research at Queen Mary University of London, located in the Jisc Shared data centre in Slough.

The Apocrita system has been specifically designed to meet the needs of a wide variety of research in the areas of our three faculties: Humanities and Social Sciences, Science and Engineering, and Medicine and Dentistry.

For more information, please see the Apocrita docs site:

What is High Performance Computing?

Using an HPC cluster can substantially reduce the time taken to compute problems by running analyses in parallel or breaking them up into pieces. Both strategies allow for the problem to be worked on by many separate compute cores (CPUs) at the same time.

For more information, please see the Apocrita docs site:

How do I get an account on Apocrita?

You need to request an account here:

I have forgotten my password/locked myself out, how do I get it reset?

You can raise a ticket with ITS Research Support who will be able to reset it for you.

You can email them here:

Where can I find other support material for Apocrita?

Documentation for Apocrita can be found here:

You can also visit our Guided Tutorials and Introduction to Linux pages:

Please note: you will need your Apocrita username and password to access the Tutorials.

Is there a HPC Slack channel?

 Yes. If you have an or email address, you can create an account.

The HPC Slack Channel can be found here: #hpc

What public datasets can I access on Apocrita?

To prevent duplication of data and to save valuable research time we provide a local copy of some widely used public datasets.

You can see the available datasets here:

If you require any datasets that are not currently available, please contact us:

What nodes are available on Aprocrita?

Apocrita runs a variety of different job types, and the cluster is comprised of different node types and queues to accommodate this.

For more information on available node, please see the Apocrita docs site:

Can I purchase my own node for Aprocrita?

First, check to see if we have a suitable node on Apocrita that meets your requirements. Try running various jobs on the node to see how the node performs for your particular analysis.

You can see the available node here:

Use of Apocrita is free, but it is a shared service. If a research project is going to make intensive use of the cluster then we request that you add compute capacity as part of your grant application.

We can help you purchase a node for your research, please contact the ITS Research Consultants:

Can I access any external HPC clusters?

We have access to several Tier 2 clusters which are among the TOP500 list of the world's most powerful computer systems. If you are running multi-node parallel jobs you may benefit from access to these. Tier 2 HPC facilities include:

  • Young - Hub in Materials and Molecular Modelling - Young is funded by EP/P020194/1 and is designed for materials and molecular modelling. QMUL receive 4 Million CPU hours for each 3 month accounting period.
  • Sulis - HPC Midlands Plus - Sulis is funded by EP/P020232/1. QMUL receive 7.4 Million CPU hours for each 6 month accounting period on Sulis.
  • JADE2 - Joint Academic Data science Endeavour - JADE2 is a GPU cluster designed for machine learning and molecular dynamics applications. The Nvidia DGX-1 nodes run optimised versions of Caffe, Tensorflow, Theano and Torch for machine learning.

QMUL Academics may apply to use a cluster free of charge if they meet certain criteria.

For more information please see the Tier 2 pages:

How do I cite Apocrita in my research?

Published research should reference this facility using the following text:

This research utilised Queen Mary's Apocrita HPC facility, supported by QMUL Research-IT.

Can I request additional applications?

First check to see if we have the software you require, you can see the available applications here:

If it is not available then you can request the software to be installed here:

Back to top