DiRAC-2: Recurrent Costs for Complexity@DiRAC Cluster at University of Leicester

Lead Research Organisation: University of Leicester
Department Name: Physics and Astronomy

Abstract

This award is for the recurrent costs of Complexity@DiRAC cluster at the the University of Leicester. It will cover electricity costs, support staff costs of the cluster which is part of the DiRAC-2 national facility.

Planned Impact

The pathways to impact for the project are as agreed at the DiRAC PMB meeting on 21 November 2011 and subsequently reported on in the annual reports of the facility.

The high-performance computing applications supported by DiRAC typically involve new algorithms and implementations optimised for high energy efficiency which impose demands on computer architectures that the computing industry has found useful for hardware and system software design and testing.

DiRAC researchers have on-going collaborations with computing companies that maintain this strong connection between the scientific goals of the DiRAC Consortium and the development of new computing technologies that drive the commercial high-performance computing market, with economic benefits to the companies involved and more powerful computing capabilities available to other application areas including many that address socio-economic challenges.

Boyle (University of Edinburgh) co-designed the Blue-Gene/Q compute chip with IBM. This is now deployed in 1.3 Pflop/s systems at Edinburgh and Daresbury and 15 other sites in the world, including the world's largest system at Lawrence Livermore Labs. This is the greenest HPC architecture in the world and offers a route to cheap affordable petascale and exascale computing that will have profound effects on Energy, Health, Environment and Security sectors.

Boyle and IBM have 4 US patents pending resulting from the Blue Gene/Q chip set design project with IBM. Boyle was a co-author of IBM's Gauss Award winning paper at the International Supercomputing conference and has co-authored IEEE and IBM Journal papers on the Blue Gene/Q architecture with IBM.

Falle (Leeds University) partially developed the MG code on DiRAC. This has been used in the National Grid COOLTRANS project to model dispersion of CO2 from high pressure pipelines carrying CO2 for carbon sequestration.

At UCL, a virtual quantum laboratory suite has been created by the UCL spinout firm, QUANTEMOL. It has application in industry, energy, health and environmental monitoring.

Calleja (Cambridge University) is using DiRAC to work with Xyratex, the UK's leading disk manufacturer, to develop the fastest storage arrays in the world.

The COSMOS consortium (Shellard) has had a long-standing collaboration with SGI (since 1997) and with Intel (since 2003) which has allowed access to leading-edge shared-memory technologies, inlcuding the world's first UV2000 in 2012, which was also the first SMP system enabled with Intel Phi (KnightsCorner) processors. Adaptive Computing are using the COSMOS@DiRAC platform to develop a single-image version of their MOAB HPC Suite.

Publications

10 25 50
publication icon
Aviles A (2020) Marked correlation functions in perturbation theory in Journal of Cosmology and Astroparticle Physics

publication icon
Bahé Y (2021) Strongly lensed cluster substructures are not in tension with ?CDM in Monthly Notices of the Royal Astronomical Society

publication icon
Bahé Y (2022) The importance of black hole repositioning for galaxy formation simulations in Monthly Notices of the Royal Astronomical Society

publication icon
Ballabio G (2018) Enforcing dust mass conservation in 3D simulations of tightly coupled grains with the Phantom SPH code in Monthly Notices of the Royal Astronomical Society

publication icon
Ballabio G (2021) HD 143006: circumbinary planet or misaligned disc? in Monthly Notices of the Royal Astronomical Society

publication icon
Bamber J (2021) Quasinormal modes of growing dirty black holes in Physical Review D

 
Description Many new discoveries about the formation and evolution of galaxies, star formation, planet formation have been made possible by the award.
Exploitation Route Many international collaborative projects are supported by the HPC resources provided by DiRAC.
Sectors Aerospace, Defence and Marine,Creative Economy,Digital/Communication/Information Technologies (including Software),Education,Manufacturing, including Industrial Biotechology,Retail,Other

URL http://www.dirac.ac.uk
 
Description Significant co-design project with Hewlett-Packard Enterprise, including partnership in the HPE/Arm/Suse Catalyst UK programme.
First Year Of Impact 2017
Sector Digital/Communication/Information Technologies (including Software)
Impact Types Societal

 
Description DiRAC 2.5x Project Office 2017-2020
Amount £300,000 (GBP)
Organisation Science and Technologies Facilities Council (STFC) 
Sector Public
Country United Kingdom
Start 02/2018 
End 03/2020
 
Title Citation analysys and Impact 
Description Use of IT to determineacademic impact of eInfrastructure 
Type Of Material Improvements to research infrastructure 
Year Produced 2017 
Provided To Others? Yes  
Impact Understood emerging trends in DiRAC Science and helped decide the scale and type of IT investments and direct us to develop new technologies 
URL http://www.dirac.ac.uk
 
Description Co-design project with Hewlett Packard Enterprise 
Organisation Hewlett Packard Enterprise (HPE)
Country United Kingdom 
Sector Private 
PI Contribution Technical support and operations costs for running the hardware. Research workflows to test the system performance, and investment of academic time and software engineering time to optimise code for new hardware. Project will explore suitability of hardware for DiRAC workflows and provide feedback to HPE.
Collaborator Contribution In-kind provision of research computing hardware. Value is commercially confidential.
Impact As this collaboration is about to commence, there are no outcomes to report at this point.
Start Year 2018
 
Description Nuclei from Lattice QCD 
Organisation RIKEN
Department RIKEN-Nishina Center for Accelerator-Based Science
Country Japan 
Sector Public 
PI Contribution Surrey performed ab initio studies of LQCD-derived nuclear forces
Collaborator Contribution Work by Prof. Hatsuda and collaborators at the iTHEMS and Quantum Hadron Physics Laboratory to provide nuclear forces derived from LQCD
Impact Phys. Rev. C 97, 021303(R)
Start Year 2015
 
Description STFC Centres for Doctoral Training in Data Intensive Science 
Organisation University of Leicester
Department STFC DiRAC Complexity Cluster (HPC Facility Leicester)
Country United Kingdom 
Sector Academic/University 
PI Contribution Support for STFC Centres for Doctoral Training (CDT) in Data Intensive Science - DiRAC is a partner in five of the eight of the newly established STFC CDTs, and is actively engaged with them in developing industrial partnerships. DiRAC is also offering placements to CDT students interested in Research Software Engineering roles.
Collaborator Contribution Students to work on interesting technical problems for DiRAC
Impact This is the first year
Start Year 2017