N8 HPC is now N8 CIR

N8 HPC has now become N8 Centre of Excellence for Computationally Intensive Research (N8 CIR) and this website is no longer updated.  To find out more about N8 CIR and it’s activities please visit the N8 CIR website.

The Next Phase of N8 HPC

The N8 HPC machine, Polaris, housed at the University of Leeds has now been switched off.  This means that no jobs can be run on N8 HPC.  The procurement of a new machine to be used by the Universities of Durham, Lancaster, Leeds and Manchester is underway and we should be able to update users soon regarding this.

Plans are also underway for the Centre of Excellence involving all 8 universities, which will focus on a set of research areas within which to share best practice and knowledge.  There will also be training and networking events for the 8 universities.

To keep up to date with developments over the next month, please follow us on Twitter or visit this website.

Polaris Machine Switch off

All N8 HPC users, PI deputies and PIs should have received regular emails warning that the N8 HPC machine, Polaris, will be switched off at noon on the 17th of July.  Please ensure that you have removed all your data as soon as possible.  After noon on the 17th July it will no longer be possible to run jobs on Polaris.

If you have any questions about removing your data, alternative HPC resources or the future of N8 HPC, please contact your local helpdesk.

N8 HPC Helps to Improve Animal Simulations

 Professor Bill Sellers from the School of Earth and Environmental Sciences, University of Manchester has used N8 HPC to improve the accuracy of computer-generated animal simulations.

The research, recently published by the Royal Society Open Science Journal, shows how simple changes to ‘machine learning’ algorithms can produce better looking, more accurate computer-generated animal simulations.  It will also help researchers investigate the ‘curious way’ that all primates walk and how this might be linked to stability whilst moving through the trees.

Professor Bill Sellers says: “Starting from an animal’s skeleton, computers using machine learning can now reconstruct how the animal could have moved. However, they don’t always do a good job”.

“But with some simple changes to the machine learning goals we can now create much more accurate simulations. We’ve now used this process to generate chimpanzee locomotion to explore why they walk the way they do”.

A full body CT scan of an adult male common chimpanzee was used to create a chimpanzee model.  This scan was then used to generate a skeletal model and a skin outline which was then used to define joint positions, muscle paths and limb contact points for the simulation.

Prof Sellers explains: “As technology has advanced and with musculoskeletal models becoming increasingly sophisticated, previous simulation models are becoming extremely unrealistic in relation to gait patterns so we have to adapt the way we think and research.”

The Future of N8 HPC

2018 will see a period of change within N8 HPC.  The current machine, Polaris is five years old, increasingly expensive to maintain and is comprised of dated hardware –  it is approaching end of life and is due to be switched off on the 17th July 2018.

The 8 member universities of N8 HPC have been in consultation for the past year as to how to proceed after this point.  Three universities (Lancaster, Manchester and York) are planning to jointly fund and procure a new cluster.  This will be hosted at Durham, who will receive 5% of available resources in return.  There will also be an investment in cloud-based resources by Manchester and Leeds.  (Sharing of resources will allow users from Lancaster and York access to cloud cycles and users from Leeds access to the new cluster.)

Users at Liverpool, Newcastle and Sheffield are advised to contact their local N8 HPC TMG representative to discuss resource availability.

All 8 universities will be contributing to a N8 HPC Centre of Excellence which will accelerate progress in areas of research that are of strategic importance to the N8 partners, including some that have not made heavy use of technology in the past.  Led by academics, each area will identify software tools, methodology, expertise etc that could benefit each research area.  A research roadmap will be developed for each selected theme, identifying key opportunities for us to accelerate progress, proposing a joint programme of work, and building a community of practice.

Further announcements will be made on the N8 HPC Users mailing list, website and Twitter feed, regarding removing your data from Polaris, queue shutdown, etc., which will be before the middle of July.

If you have any questions about your institution’s involvement in N8 HPC going forward, please contact your Steering Group member.

Login Form