e-Infrastructure South Consortium - Centre for Innovation
Lead Research Organisation:
University of Oxford
Department Name: Oxford e-Research Centre
Abstract
The e-Infrastructure South consortium comprises four of the UK's leading Universities in the area of high-performance computing (HPC) who, collaborating with the e-Science Centre at RAL, will create this new regional Centre of Innovation. The five partners in the Centre are the University of Bristol, the University College London, the University of Southampton, the University of Oxford, and the STFC: Rutherford Appleton Laboratory (RAL).
The Centre for Innovation will provide a shared infrastructure for the development of data driven applications, simulation and software; science and enterprise drivers for the continuing development of that infrastructure and software; a training centre to create the next generation scientists, engineers, social scientists and other research computing practitioners and to maintain a skilled workforce. It will offer both traditional large-scale high-performance computing capacity and leading-edge GPU-based facilities.
Through the Centre of Innovation, e-Infrastructure South will stimulate new academic-industrial collaborations, creating new opportunities for economic growth and enabling advances in science and engineering. The creation of a regional computational facility opens opportunities for innovation and collaboration that would be difficult to deliver through existing facilities and with the existing disparate knowledge base.
The Centre will support research partnerships that will allow industrial and academic investigation and exploitation in the existing research areas of:
- Modelling the Earth's Climate, oceans and atmosphere, and the atmospheres of other planets.
- Epidemiological analysis of large datasets to understand the efficacy of drug regimes.
- Modelling and imaging of multi-scale interactions (e.g. how does a cell/organ work at the molecular/cellular level) in biological systems and drug transport through membranes.
- Mapping medical conditions in the general populations to catalogues, such as the human genome.
- Complex engineering systems, such as aircraft and ships, fluid flow and turbulence.
- Simulating 3G & 4G communications networks.
- Development of nanotechnologies for fuel cells and new pharmaceuticals, and to design and test new industrial processes.
- Understanding transportation and informing policy through social simulation.
- Innovating in energy systems, developing new modes of energy and the management thereof.
- Understanding, modelling and visualizing causality.
- Discovery of new drugs by molecular modelling techniques.
- Development of new tools for the processing and management of medical images.
- Modelling of advanced functional materials including those used in catalytic and energy technologies
The Centre for Innovation will provide a shared infrastructure for the development of data driven applications, simulation and software; science and enterprise drivers for the continuing development of that infrastructure and software; a training centre to create the next generation scientists, engineers, social scientists and other research computing practitioners and to maintain a skilled workforce. It will offer both traditional large-scale high-performance computing capacity and leading-edge GPU-based facilities.
Through the Centre of Innovation, e-Infrastructure South will stimulate new academic-industrial collaborations, creating new opportunities for economic growth and enabling advances in science and engineering. The creation of a regional computational facility opens opportunities for innovation and collaboration that would be difficult to deliver through existing facilities and with the existing disparate knowledge base.
The Centre will support research partnerships that will allow industrial and academic investigation and exploitation in the existing research areas of:
- Modelling the Earth's Climate, oceans and atmosphere, and the atmospheres of other planets.
- Epidemiological analysis of large datasets to understand the efficacy of drug regimes.
- Modelling and imaging of multi-scale interactions (e.g. how does a cell/organ work at the molecular/cellular level) in biological systems and drug transport through membranes.
- Mapping medical conditions in the general populations to catalogues, such as the human genome.
- Complex engineering systems, such as aircraft and ships, fluid flow and turbulence.
- Simulating 3G & 4G communications networks.
- Development of nanotechnologies for fuel cells and new pharmaceuticals, and to design and test new industrial processes.
- Understanding transportation and informing policy through social simulation.
- Innovating in energy systems, developing new modes of energy and the management thereof.
- Understanding, modelling and visualizing causality.
- Discovery of new drugs by molecular modelling techniques.
- Development of new tools for the processing and management of medical images.
- Modelling of advanced functional materials including those used in catalytic and energy technologies
Planned Impact
The Centre will have direct socio and economic impact through:
- a collaborative approach to industry and academic provision for data intensive research and simulation
- the continuing up-skilling of the workforce
- increased capability of simulation on social, scientific and engineering challenges
- new technology and capability to deal with the tsunami of data that faces researchers, businesses and government alike.
The computational and data demands on academia and industry alike are every increasing however it is often highly impractical and uneconomic for institutions and organisations to build the required e-Infrastructure. The Centre for Innovation will provide that infrastructure, in terms of facilities, software and skills support. It will also provide a template for other UK regional e-infrastructure and will work to increase the UK's international profile. The provision of multiple systems that offer Tier 2 capability within the region will allow new science through existing software, migration of existing software to next generation systems, and development of new many-core algorithms to allow sustainability of codes on future generation systems.
The consortium will initially benefit the following primary sectors: 1) Aerospace, Aviation, Marine and Maritime, 2) Advanced materials, 3) Engineering and 4) Biosciences. These four sectors are best placed to take early advantage of new regional HPC facilities. Candidates for additional sectors include the creative industries and financial services. The e-Infrastructure consortium industrial collaborators include technology companies, IBM, Intel, NVIDIA, Fujitsu, Microsoft, Gnodal and NAG Ltd and industry partners reliant on such research infrastructure such as Rolls Royce, Johnson Matthey, BAE Systems, EDF, Lang O'Rourke, Airbus, GSK, AstraZeneca Pfizer, Willis Re, AgustaWestland and Boeing. The industry partners will benefit from access to both the large conventional system at Southampton and the GPU-based system at RAL.
- a collaborative approach to industry and academic provision for data intensive research and simulation
- the continuing up-skilling of the workforce
- increased capability of simulation on social, scientific and engineering challenges
- new technology and capability to deal with the tsunami of data that faces researchers, businesses and government alike.
The computational and data demands on academia and industry alike are every increasing however it is often highly impractical and uneconomic for institutions and organisations to build the required e-Infrastructure. The Centre for Innovation will provide that infrastructure, in terms of facilities, software and skills support. It will also provide a template for other UK regional e-infrastructure and will work to increase the UK's international profile. The provision of multiple systems that offer Tier 2 capability within the region will allow new science through existing software, migration of existing software to next generation systems, and development of new many-core algorithms to allow sustainability of codes on future generation systems.
The consortium will initially benefit the following primary sectors: 1) Aerospace, Aviation, Marine and Maritime, 2) Advanced materials, 3) Engineering and 4) Biosciences. These four sectors are best placed to take early advantage of new regional HPC facilities. Candidates for additional sectors include the creative industries and financial services. The e-Infrastructure consortium industrial collaborators include technology companies, IBM, Intel, NVIDIA, Fujitsu, Microsoft, Gnodal and NAG Ltd and industry partners reliant on such research infrastructure such as Rolls Royce, Johnson Matthey, BAE Systems, EDF, Lang O'Rourke, Airbus, GSK, AstraZeneca Pfizer, Willis Re, AgustaWestland and Boeing. The industry partners will benefit from access to both the large conventional system at Southampton and the GPU-based system at RAL.
Organisations
Publications
Adámek K
(2020)
GPU Fast Convolution via the Overlap-and-Save Method in Shared Memory
in ACM Transactions on Architecture and Code Optimization
László E
(2016)
Manycore Algorithms for Batch Scalar and Block Tridiagonal Solvers
in ACM Transactions on Mathematical Software
Scanlon DO
(2015)
Polymorph engineering of CuMO2 (M = Al, Ga, Sc, Y) semiconductors for solar energy applications: from delafossite to wurtzite.
in Acta crystallographica Section B, Structural science, crystal engineering and materials
Kafizas Andreas
(2014)
Combinatorial Atmospheric Pressure Chemical Vapor Deposition of F: TiO 2; the Relationship between Photocatalysis and Transparent Conducting Oxide Properties
in ADVANCED FUNCTIONAL MATERIALS
Rajpalke M
(2013)
Growth and properties of GaSbBi alloys
in Applied Physics Letters
Sallis S
(2013)
La-doped BaSnO3-Degenerate perovskite transparent conducting oxide: Evidence from synchrotron x-ray spectroscopy
in Applied Physics Letters
Regoutz A
(2015)
Electronic and surface properties of Ga-doped In2O3 ceramics
in Applied Surface Science
Mangel M
(2016)
Feedback control in planarian stem cell systems.
in BMC systems biology
Bhachu DS
(2016)
Bismuth oxyhalides: synthesis, structure and photoelectrochemical activity.
in Chemical science
Bhachu D
(2015)
Origin of High Mobility in Molybdenum-Doped Indium Oxide
in Chemistry of Materials
Buckeridge J
(2015)
Polymorph Engineering of TiO 2 : Demonstrating How Absolute Reference Potentials Are Determined by Local Coordination
in Chemistry of Materials
Buckeridge J
(2014)
Automated procedure to determine the thermodynamic stability of a material and the range of chemical potentials necessary for its formation relative to competing phases and compounds
in Computer Physics Communications
Witherden F
(2014)
PyFR: An open source framework for solving advection-diffusion type problems on streaming architectures using the flux reconstruction approach
in Computer Physics Communications
Reguly I
(2015)
Vectorizing unstructured mesh computations for many-core architectures
in Concurrency and Computation: Practice and Experience
Reguly I
(2018)
Loop Tiling in Large-Scale Stencil Codes at Run-Time with OPS
in IEEE Transactions on Parallel and Distributed Systems
Klingbeil G
(2012)
Fat versus Thin Threading Approach on GPUs: Application to Stochastic Simulation of Chemical Reactions
in IEEE Transactions on Parallel and Distributed Systems
Reguly I
(2016)
Acceleration of a Full-Scale Industrial CFD Application with OP2
in IEEE Transactions on Parallel and Distributed Systems
Dunning P
(2016)
Level-set topology optimization with many linear buckling constraints using an efficient and robust eigensolver
in International Journal for Numerical Methods in Engineering
Jammy S
(2016)
Block-structured compressible Navier-Stokes solution using the OPS high-level abstraction
in International Journal of Computational Fluid Dynamics
Reguly I
(2013)
Finite Element Algorithms and Data Structures on Graphical Processing Units
in International Journal of Parallel Programming
Bayliss R
(2014)
Understanding the defect chemistry of alkali metal strontium silicate solid solutions: insights from experiment and theory
in J. Mater. Chem. A
Scanlon D
(2014)
Understanding doping anomalies in degenerate p-type semiconductor LaCuOSe
in J. Mater. Chem. C
Sadiq SK
(2015)
Computing the role of near attack conformations in an enzyme-catalyzed nucleophilic bimolecular reaction.
in Journal of chemical theory and computation
Wright DW
(2014)
Computing Clinically Relevant Binding Free Energies of HIV-1 Protease Inhibitors.
in Journal of chemical theory and computation
Berardo E
(2014)
Modeling Excited States in TiO2 Nanoparticles: On the Accuracy of a TD-DFT Based Description.
in Journal of chemical theory and computation
Berardo E
(2014)
Describing Excited State Relaxation and Localization in TiO2 Nanoparticles Using TD-DFT.
in Journal of chemical theory and computation
Wilkinson K
(2013)
Porting ONETEP to graphical processing unit-based coprocessors. 1. FFT box operations.
in Journal of computational chemistry
Huang Y
(2014)
Understanding the stability of MnPO 4
in Journal of Materials Chemistry A
Jurcic M
(2015)
The vapour phase detection of explosive markers and derivatives using two fluorescent metal-organic frameworks
in Journal of Materials Chemistry A
Bhachu D
(2015)
Scalable route to CH 3 NH 3 PbI 3 perovskite thin films by aerosol assisted chemical vapour deposition
in Journal of Materials Chemistry A
Ganose A
(2016)
Band gap and work function tailoring of SnO 2 for improved transparent conducting ability in photovoltaics
in Journal of Materials Chemistry C
Savory CN
(2016)
An assessment of silver copper sulfides for photovoltaic applications: theoretical and experimental insights.
in Journal of materials chemistry. A
Marchand P
(2016)
A single-source precursor approach to solution processed indium arsenide thin films.
in Journal of materials chemistry. C
Giles M
(2013)
Designing OP2 for GPU architectures
in Journal of Parallel and Distributed Computing
Zhou S
(2014)
Low Temperature Preparation and Electrochemical Properties of LiFeSi 2 O 6
in Journal of The Electrochemical Society
Underwood TS
(2013)
Detector density and small field dosimetry: integral versus point dose measurement schemes.
in Medical physics
Kawata D
(2014)
Gas and stellar motions and observational signatures of corotating spiral arms
in Monthly Notices of the Royal Astronomical Society
Hunt J
(2014)
M2M modelling of the Galactic disc via primal: fitting to Gaia error added data
in Monthly Notices of the Royal Astronomical Society
Trypogeorgos D
(2013)
Precise shaping of laser light by an acousto-optic deflector.
in Optics express
Mudalige G
(2013)
Design and initial performance of a high-level unstructured mesh framework on heterogeneous parallel systems
in Parallel Computing
Giles MB
(2014)
Trends in high-performance computing for engineering calculations.
in Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
Coveney PV
(2016)
On the calculation of equilibrium thermodynamic properties from molecular dynamics.
in Physical chemistry chemical physics : PCCP
Guiglion P
(2015)
Contrasting the optical properties of the different isomers of oligophenylene.
in Physical chemistry chemical physics : PCCP
Zwijnenburg MA
(2013)
Excited state localisation cascades in inorganic semiconductor nanoparticles.
in Physical chemistry chemical physics : PCCP
Wobbe MC
(2015)
Chemical trends in the optical properties of rocksalt nanoparticles.
in Physical chemistry chemical physics : PCCP
Wobbe MC
(2014)
Optical excitation of MgO nanoparticles; a computational perspective.
in Physical chemistry chemical physics : PCCP
Buckeridge J
(2014)
N incorporation and associated localized vibrational modes in GaSb
in Physical Review B
Vasheghani Farahani S
(2014)
Valence-band density of states and surface electron accumulation in epitaxial SnO 2 films
in Physical Review B
Buckeridge J
(2016)
Efficient and accurate approach to modeling the microstructure and defect properties of LaCoO 3
in Physical Review B
| Description | The Centre for Innovation, e-Infrastructure south, was a collaboration between a number of Universities in the south of England, Oxford, UCL, Southampton, and Bristol together with STFC Rutherford labs. The consortium invested £3.7M to provide two distinctive HPC resources, focussed around traditional HPC cluster computing (IRIDIS) and around the novel architectures of GPU based computing (Emerald). The focus of the collaboration was to provide a shared infrastructure for the development of data driven applications, simulation and software; science and enterprise drivers for the continuing development of that infrastructure and software; a training centre to create the next generation scientists, engineers, social scientists and other research computing practitioners and to maintain a skilled workforce. It will offer both traditional large-scale high-performance computing capacity and leading-edge GPU-based facilities. As can be seen from the list of publications the consortium enabled a broad range of science research. Over 250 users from within the consortia, working on a diverse range of applications ranging from modelling of tsunami at UCL, simulating their impact on coastlines (informing emergency service response plans as well as insurance pricing) to gaining insight into swine flu's resistance to currently available antivirals such as Relenza and Tamiflu (Bristol). Since start-up we have also attracted two SMEs in the region who are directly engaged in using the Emerald system (Xenotech and Cresset), a resource which would otherwise not be available to them. The investments made in the 'Centre also underpin long term industrial-academic collaborations within the consortium as well as new. An example of which is the use of IRIDIS in computational fluid dynamics activity at Southampton's Wolfson Unit. The Unit ran aerodynamic CFD simulations of the wing sail for Luna Rossa Challenge (Italy), in the America's Cup, optimising performance and efficiency, and collaborating with Emirates Team New Zealand on validation, with all simulations being run on the Iridis3 cluster at the University of Southampton. This high performance computational (HPC) facility has allowed the designers to run thousands of simulations, giving quick and accurate results for a complete performance model. The access to HPC facilities allowed the researchers to combine world class experimental and computational resources to produce complete simulations of complex, dynamic environments. This world leading status was recognised in the Queens Anniversary Prize 2011. The consortium developed to become Science and Engineering South (SES) and a full set of case studies of the broad set of applications that include the e-Infrastructure activities can be found at http://www.ses.ac.uk/case-studies/ . In addition to providing raw compute power, the centre has also brought together world class best with best expertise to drive forward research capability. Early fruit of this has been the re-write of the VOLNA tsunami modelling code to take full advantage of EMERALD by Prof Mike Giles and his team (Oxford) to provide a step change in the productivity for researchers using this code and access to a new architecture previously beyond reach." Professor Giles also led the development and delivery of GPU training that was provided to consortium members and beyond. Through focussed workshops the Centre provided a mechanism for sharing best practice, introducing industry and academics, and providing a platform for dissemination of research. The workshops included topics such as "Accelerating Research for industry", " Data sharing and curation", and working with the SSI on software engineering. The Emerald system became a crucial part of the regional e-Infrastructure particularly for innovative computing. Following on from this members of the Centre for Innovation took forward the Tier 2 system Jade, to provide a national Tier 2 GPU system that now underpins AI and machine learning algorithm development. |
| First Year Of Impact | 2011 |
| Sector | Aerospace, Defence and Marine,Chemicals,Creative Economy,Education,Energy,Environment,Financial Services, and Management Consultancy,Healthcare,Manufacturing, including Industrial Biotechology,Pharmaceuticals and Medical Biotechnology,Transport |
| Impact Types | Societal |
| Description | JADE: Joint Academic Data science Endeavour |
| Amount | £3,000,000 (GBP) |
| Funding ID | EP/P020275/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 10/2016 |
| End | 03/2020 |