Computing Services

The department behind IT services at the University of Bath

How much time do we have to get clean energy right?

  , , , ,

📥  High Performance Computing (HPC), Research

Adam Jackson won the 2013 High Performance Computing (HPC) Symposium poster competition. The poster: Ab initio thermodynamics for the design of energy materials shows the value of being able to use the Bath University Computing Services (BUCS) HPC Aquila service for his PhD research: Building-integrated functional coatings (supervisors Dr Aron Walsh, Professor Laurie Peter & Dr Darrell Patterson).

2013 HPC symposium poster winner

Background to Adam's work

There is a need for clean energy to be as plentiful and cheap as traditional, fossil fuel energy generation.   We want clean energy grid parity sooner rather than later.  One of the tools for speeding up this process is to use HPC technology.

Adam's research involves building a database of compounds which are used to form new photovoltaic materials (similar to a strip on a solar powered calculator) and testing what reaction conditions (mainly temperature and pressure variables), do the different materials work well under.  The advantages of using HPC to test from first principles rather than in a lab are numerous:

  • Computational testing results in a consistent data set
  • Time-consuming blind alleys can be avoided
  • Quicker identification of the more promising materials
  • Tests can be run in an idealised way

The value of HPC capability at the University of Bath

Adam's research takes place at the Centre for Sustainable Chemical Technologies, an important hub for sustainable chemistry in the UK.  Researchers from the Centre recognise the value of having access to a well-supported, local HPC service.  Support for the BUCS Aquila HPC service is led by Dr Steven Chapman.

Value of local HPC Aquila service

Different HPC facilities fulfil different needs for a researcher and this is highlighted in the computational details section of the poster.  Local services allow a user to run test over a number of days.  Researchers can test their code quickly on Aquila and can ask for support if they run into difficulties.  Using a locally managed facility allows researchers to build their knowledge and confidence in a supported environment before applying to national facilities.

Any limits?

The limit of any great piece of kit is having the right people to use it.  The Department of Mathematical Sciences highlighted the need for getting more people to use modern supercomputing facilities at the 2013 HPC symposium.  See details for the Scientific Computing course .

The University of Bath is lucky to have attracted researchers like Adam.  Adam is clear that being able to access the Aquila HPC service enables his important research.  HPC is a local facility that needs to be well resourced and invested in to allow the University of Bath to meet its research strategy aims.

Follow Bath University's HPC service on twitter at @BathHPC .


Will it rain on campus on Sunday?

  , , , ,

📥  High Performance Computing (HPC), Research

Will it ever be possible to improve the resolution of weather prediction to such an extent? Only time will tell, along with the success of using complex solvers tested on facilities like the University of Bath's Aquila HPC service.

Dr Eike Mueller won the prize for best presentation at the 2013 High Performance Computing (HPC) symposium at the University of Bath.  Since September 2011 Eike has been a PostDoc in the Department of Mathematical Sciences at the University of Bath where he works on a HPC driven NERC funded project for improving the accuracy of global weather and climate prediction models for the Met Office.

Dr Mueller receives prize at the 2013 University of Bath HPC symposium

Background to Eike Mueller's work

The UK Met Office provides global, 5 day weather forecasts.  Data is fed into a computational model, this data is sourced using a grid with reference points 25 km apart.  The aim is to increase the resolution of this forecast and use data from reference points 1 to 2 km apart.  This requires a rethink of the computational model being used.  Together with Professor Rob Scheichl, Eike is improving the performance of the solver for the global pressure correction equation, which is one of the computationally most important components of the model.

Rethinking computation models - how to make the most of Graphical Processing Units (GPU)

Traditionally users of the Aquila HPC service at the University of Bath run jobs over long periods of time, using a smaller percentage of the central processing power available from Aquila.  Bath University Computing Services (BUCS) works to make sure that all requests for using the service are run as efficiently as possible.

Dr Mueller's work is different from these more traditional jobs.  He is the first at the University of Bath to take advantage of the newly installed NVIDIA Fermi GPUs, which offers a total of 3,072 GPU cores.  In addition, his work requires using the majority of the Aquila's capacity for very short periods of time. He is using Aquila to develop and test the performance of algorithmic and parallel scalability of solvers for elliptic partial differential equations in weather and climate prediction on novel computer architecture (in this example GPUs).  Dr Steven Chapman from BUCS has provided support to assist Eike in getting the most out of the GPUs on the Aquila cluster.

What is next for Dr Mueller's work?

Eike is currently extending the work he presented in his talk at the HPC Symposium to run his solver on the EMERALD cluster, the UK's biggest NVIDIA GPU-accelerated supercomputer. In the future he also plans to test the scalability of his code on the TITAN supercomputer, which is currently the second fastest computer in the world.  Having a local HPC facility allows him to test his work and solve any issues that result from the tests.

And the the weather on Sunday on campus?

P.S. BBC says it's going to be sunny!


HPC Symposium - Congratulations and Thank you!

  , , , ,

📥  High Performance Computing (HPC), Research

Over 70 attendees came together to share their work with academics from many disciplines at the High Performance Computing (HPC) Symposium, 4 June 2013. Thank you to everyone who made the second HPC Symposium at University of Bath a success.

Congratulations and Thank you!

Photo of attendees and key note speaker at HPC Symposium 2013@lone pair's astute tweet "Glasses, energy reduction, GPUs, openmp, CFD, DFT, openFOAM, weather, marine, solar, lithium, hard spheres and some nice cake" captures the diversity of the 15 academic papers and 9 poster presentations.

A huge thank you to Mike Giles, Professor of Scientific Computing at University of Oxford, for delivering the insightful keynote lecture, Future of HPC - trends, opportunities and challenges.  Congratulations to Dr Eike Mueller who won the prize for the best talk and to Adam Jackson who won the prize for the best poster.   We will be interviewing the winners to capture their knowledge of HPC and how it has helped in their research.

Can HPC help you in your research?

HPC is useful if you need to get through a massive amount of data (capacity computing) or need something with a lot of power to get things done in a reasonable amount of time (capability computing).

Contact your departmental HPC Champion or HPC Support if your academic research could benefit from:

  • solving real world problems where the number of variables are awesome (examples include social network modelling, health outcomes, meteorological simulations and molecular interaction simulations)
  • visualisation of complex modelling (for example processing tens of thousands of images an hour)

The 2013 programme includes links to all the papers presented at the symposium and shows the value of academic disciplines  working together.

Next steps

We’d be very interested in your feedback on the event and how you think it can be improved for next time.  We would also be interested to hear from you if would like a shorter, more informal session before next year's symposium.

Please use the user mailing list,, for general discussions on HPC use.


Post-Symposium Information

  , , , ,

📥  High Performance Computing (HPC), Research

The organisers would like to thank all the participants very much again for coming to the meeting on 4th June, we really hope you enjoyed the day. It was great to see such a large number of people, hearing about the interesting science that is being done with the Aquila HPC cluster and share ideas during both the formal and informal discussions.

In particular we would like to thank all talk- and poster presenters, the session chairs and the independent judges and everybody who participated in the discussions. We are very grateful to Prof Mike Giles for a very inspiring keynote lecture, James Davenport for the introduction in the morning and David Bird for guiding the discussion in the afternoon, and to everybody else who helped out during the day with catering, staffing the registration desk and making sure that everything went smoothly.

A photograph of all delegates can be found here: delegation photo.

We would like to congratulate once more Dr Eike Mueller, who won the prize for the best talk, and Adam Jackson, who won the prize for the best poster - well done!

Many of the presentations from the HPC Symposium are now available online, see the programme page for links to the presentations.

Also watch out for the news article which is soon to appear on the University webpage.

Given the success of yesterday's meeting and the lively discussion session in the afternoon, it would be great if we can build on the momentum to follow up from this. We would definitely like to hold another meeting next year, but if there is interest in this, we could also organise a shorter, informal discussion session sooner, i.e. within the next few months, with particular focus on the next generation Bath HPC system.

Also don't forget that there is a user mailing list on aquila ( which can be used for general discussions. If you have any other ideas on how to follow on from the symposium or how to improve it next year, please email us on

See you next year,

The Scientific Organising Committee

Dr Steven Chapman (Computing Services)
Dr Davide Tiana (Dept. of Chemistry)
Dr Eike Mueller (Dept. of Mathematical Sciences)

degegates-small eike-talk-small adam-poster-small


HPC at Bath is now on twitter

  , , ,

📥  High Performance Computing (HPC)

For all those who use twitter...

I have recently setup a twitter account for the HPC service, @BathHPC. If you have a twitter account please follow this account, I will try and use this for relevant discussion and news items.

To help advertise and entice discussions on the upcoming HPC symposium through twitter, please use hashtag #BathHPC2013.


HPC Symposium, all day Tuesday, 4th June

  , , , ,

📥  High Performance Computing (HPC), Research

The University of Bath is holding its 2nd Symposium on High Performance Computing (HPC) which will take place on all day on Tuesday, 4th June (lunch included). This symposium is for any staff and students who use or are interested in using the HPC service.

If you would like to attend, please register before Friday 17th May by sending an email to and let us know of any special dietary requirements. See the Registration section below for more information.

The main aim of the symposium is to provide a forum for users of the University's HPC service, aka Aquila, and it will be an excellent opportunity to network and exchange ideas. Hopefully the experience and the people you meet will help you with your own research in the future.

If you are a researcher engaged in HPC themed scientific research and you wish to give a talk about your research or present a poster please submit an abstract by Friday 10th May 2013. Please see talks and posters section below for more information.

The following activities are planned for the day:

  • A keynote lecture by Prof. Mike Giles (University of Oxford), one of the UK's leading experts on using GPUs for Scientific Computing
  • Talks and posters by users of the HPC facility
  • A prize will be given for the best talk (iPad Mini) and the best poster (iPod Nano) presented
  • A discussion session on the future of HPC in Bath
  • A buffet lunch will be provided along with refreshments and lots of opportunities to network

The symposium will be held in 4 West room 1.2, further details can be found on the webpage:

Feel free to print out and display the poster in your department, a .pdf version of the poster is available at

There is no registration fee, but we need to collect a list of attendees and know numbers in advance to organise catering. If you are interested in attending, please register before Friday 17th May by sending an email to and let us know if you have any special dietary requirements.

If you are planning to submit an abstract please could you indicate in your registration email whether your would like to give a talk or present a poster and could you include the title of your contribution.

Talks and posters
Contributions in the form of talks and posters are vital for the success of the symposium and there will be prizes for the best talk and poster. If you are currently using the University's HPC facility for your research, we strongly encourage you to share your experiences with others at the meeting. You can also present your research if you are not currently using the HPC facility, but are working on a computationally intensive problem which might benefit from using HPC.

The following topics will be covered (list not exhaustive)...

- HPC driven research in all disciplines
- Experiences with tools and libraries
- Parallel code development and scalability
- Algorithms
- Novel architectures: GPUs and Xeon Phi

Talk are scheduled to be 15 minutes (including questions).

If you plan to present a talk or poster, please submit your abstract in LaTeX or Microsoft Word format and send your .tex source file or the word template in an email to by the abstract submission deadline of Friday 10th May. The LaTeX and Word templates can be found on the website; please remember to rename the file with your username e.g. abstract_sac44.doc.

The best abstracts will be selected and a list of talks and posters will be announced on May 17th.

We are looking forward to seeing you on the 4th June,

the Scientific Organising Committee,

Dr Davide Tiana (Chemistry)
Dr Steven Chapman (Computing Services)
Dr Eike Mueller (Maths)


Scheduler maintenance -- update - 9/10/2012

  , , , , ,

📥  High Performance Computing (HPC)

Adaptive Computing have spent three 11-hour days assisting me with the installation and configuration of the new scheduling system on the Aquila HPC facility. During these days we have made a lot of progress and resolved several unforeseen issues. However there is some additional work remaining which largely involves systematically testing different queuing scenarios to ensure that the configuration is stable and is correctly scheduling the jobs.

Below is a summary of the work which has been accomplished over the last three days.

  • Moab v7.1.1 and Torque v4.1.1 have been installed on a dedicated server
  • the Aquila headnodes have been transformed into login/submit nodes
  • Torque v4.1.1 has been updated on all of the nodes and have been pointed to the new torque server
  • openMPI v1.6.1 has been recompiled to support the new version of torque
  • testing environment has been created to test the moab configuration
  • the workflow of moab configuration is largely completed

The majority of the moab configuration file reflects the outline to the scheduler I sent out in a previous email, we still have some of the more trivial elements to implement. The majority of the remaining works involves rigorously and systematically testing the various elements to the moab config file and some tuning; this will cover:

  • job preemption for development and course users
  • jobs which require license features
  • priority ordering
  • fairshare priority weighting
  • access control hacking
  • correct allocation of resources for types of jobs

This testing will be performed over the new few working days and during this time will have direct access to the support team and senior consultants from Adaptive Computing to assist me with any complications which arise. We anticipate that this work on the queue scheduler will be complete on Wednesday 10th October. Over the next few days I will be updating the HPC wiki pages with notes on how to use the new queuing system.

During this work a couple of the nodes have started to report issues. We currently have four nodes in a non-operational state. I'll be investigating these at a later date.

We thank you for your patience and are sorry for any inconvenience this extended maintenance and upgrade has caused.