Tier 2 HPC facilities¶
We have access to a number of 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, please contact us to see if your job is appropriate and to organise access.
Who can access these clusters?¶
QMUL Academics may apply to use a cluster free of charge if:
- they are performing predominantly EPSRC-funded research
- jobs are an appropriate size for the Tier 2 service (the QMUL Apocrita service is sufficient for many users) e.g. parallel jobs running over multiple nodes
- jobs are well-tested and known to run successfully
- the scope and size of the work is stated in advance as part of an application to use the cluster (or by using the initial 50,000 Core Hour allocation to determine specific resource requirements)
- the work fits the designated application areas for the cluster
- you notify us if you don't think you will be able to use the Core Hour allocation within the agreed time frame (so that the unused hours can be allocated to other users)
- Once your access has been agreed and set up, it is recommended that you connect to the Tier 2 resources through Apocrita. This is because access from the internet at large may be restricted to some of these resources. If you understand ssh client configuration the following example may be useful:
Host athena HostName athena.hpc-midlands-plus.ac.uk ProxyJump firstname.lastname@example.org User abc123
Typically, new projects will be granted 50,000 Core Hours for benchmarking and job sizing. After this, to obtain resource allocation for your project, you will need to provide a short description of your project, along with job sizes and a commitment to use the resources within the agreed time-frame.
QMUL receive an allocation to use within a given accounting period on each cluster, which is divided among the various projects according to their requirements. At the end of each accounting period the balances are reset.
A Core Hour is the amount of work done by a single processor core in one hour. For accounting purposes, you need to calculate the cumulative total over all cores that your job runs on. If your job runs for one hour on ten 24-core nodes, the CPU time used is 240 Core Hours. Part-used nodes are counted as using all of the cores, since jobs are granted exclusive access to nodes.
Additional Core Hour allocations can be requested by contacting email@example.com with your requirements. Please only request what you will realistically use within the reporting period - we can always top up your allocation later if required.
Thomas - Hub in Materials and Molecular Modelling¶
|Host Institution||Cores||Nodes||RAM/Node||Scheduler||Wallclock||Accounting period|
Thomas is funded by EP/P020194/1 and is designed for materials and molecular modelling. QMUL receive 4 Million Core Hours for each 3 month accounting period. Further information, including available software packages, is available on the UCL wiki. They also include some example job submission scripts.
Users are given 50GB of home space, and 200GB of scratch space. Maximum job size is 864 cores (36 nodes); typical job sizes are between 2-5 nodes.
To request an account on Thomas, please contact us and provide the following information:
- First name
- QMUL username
- Public SSH key (not the private key)
- Software Required
A public SSH key is required because Thomas does not accept password logins; existing SSH keys may be re-used (such as that used to access Apocrita). Instructions for how to generate an SSH key are available here.
Athena - HPC Midlands Plus¶
|Host Institution||Cores||Nodes||RAM/Node||Scheduler||Wallclock||Accounting Period|
Athena is funded by EP/P020232/1.
QMUL receive 7.4 Million Core Hours for each 6 month accounting period on Athena.
JADE - Joint Academic Data science Endeavour¶
|Host Institution||Nodes||GPUs per node||Scheduler||EPSRC Grant|
|Oxford||22 NVidia DGX-1||8 Nvidia P100||Slurm||EP/P020275/1|
JADE 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. More information is available in the JADE documentation
To request an account on JADE, please create an account providing an institutional email address, and the public portion of your ssh key. An email will be sent to you containing a password for SAFE which needs to be changed on first logging in. Once you have signed up, log on to SAFE and click on "Request Join Project". From the drop-down list choose JAD007 and enter the Project signup password which, for this Project, is jadqmul17, and click "Request".