Driving UK HPC enabled science and innovation through US collaborations 2014

Lead Research Organisation: Imperial College London
Department Name: Earth Science and Engineering

Abstract

We propose a continuation of the EPSRC UK-USA High Performance Computing Network to underpin pump priming of UK-USA collaborations in high performance computing (HPC) related areas, with a special emphasis on developing the careers of young researchers in the field. The network aims to increase the competitiveness of UK HPC enabled science and innovation by improve the UK's community's engagement with USA's HPC community. A two pronged strategy focuses on supporting individual collaborations at the grass roots level through travel grants, as well as developing and maintaining links with USA university supercomputing centres, national laboratories and key organizations such as XSEDE (Extreme Science and Engineering Discovery Environment); INCITE (Innovative and Novel Computational Impact on Theory and Experiment); and CASC (Coalition for Academic Scientific Computation).

In the previous year the EPSRC UK-USA HPC network funded 10, primarily early career, researchers to attend Supercomputing Conference (SC13) in Denver Colorado. This proven to be a popular initiative - we received 21 applications although the funding call was only advertised for two weeks. As detailed in our post-SC13 report this was found to be highly successful in creating new collaborations and professional relationships between the UK and USA. The network also catalyzed cooperation between CASC and the UK HPC-SIG. This has the potential to a unified network of across supercomputing centers at universities across the UK and USA.

Planned Impact

The central theme of this network proposal is generating scientific and economic impact from UK HPC enabled science and innovation through US collaborations. This is articulated both in the network's objectives and the proposed actions.

Metrics by which the success of this network can be quantified include:
1) Diversity and degree of industrial engagement with the network.
2) Number of new academic (including national laboratory) collaborations.
3) Number of new industrial sponsorship's, collaborations or partnerships.
4) Increase in UK applications to US XSEDE/INCITE programs.
5) Increase in UK research proposals with US partners or vise versa.

Publications

10 25 50
publication icon
Beskos A (2017) Geometric MCMC for infinite-dimensional inverse problems in Journal of Computational Physics

publication icon
Chapman S (2017) Analysis of Carrier's Problem in SIAM Journal on Applied Mathematics

publication icon
Charalampidis E (2018) Computing stationary solutions of the two-dimensional Gross-Pitaevskii equation with deflated continuation in Communications in Nonlinear Science and Numerical Simulation

publication icon
Farrell P (2016) The Number of Distinct Eigenvalues of a Matrix After Perturbation in SIAM Journal on Matrix Analysis and Applications

publication icon
Lange M (2016) Efficient Mesh Management in Firedrake Using PETSc DMPlex in SIAM Journal on Scientific Computing

 
Description Because much of computational science is based on open source software it is clear that this is a relatively straightforward area for transatlantic collaboration. While the UK and the US might work on open source together for the benefit of academic science and engineering it is also apparent that commercial products can also be built upon this open technology.
Exploitation Route Mobility for researchers is key in this area. On key projects we found it was straightforward for 2 way exchange of researchers and the IP situation was trivial once a sensible open source licence covered the technology in question. It is clear that this approach enables the UK the leverage massive investment into software in the US while still been viewed as important partners because of the technical expertise that the UK community brings.
Sectors Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Energy,Environment,Manufacturing, including Industrial Biotechology

 
Description The funding has been used to promote engagement of UK early career researchers with HPC and computational science activities in the UK. This was done through a combination of: funding early career researchers to attend Supercomputing'14 (by far the largest conference in this field); travel grants for early career researchers to have extended collaboration visits with US research groups; invite leading US researchers to the UK to give talks and participate in workshops.
First Year Of Impact 2014
Sector Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Energy,Environment,Manufacturing, including Industrial Biotechology
Impact Types Economic

 
Description CASC 
Organisation Coalition for Academic Scientific Computation
Country United States 
Sector Charity/Non Profit 
PI Contribution We facilitated the networking between the UK HPC-SIG and the corresponding organization in the USA - CASC (http://casc.org/)
Collaborator Contribution Funded travel for networking. Met with leaders from both organizations to foster a relationship with continues to today.
Impact Knowledge exchange relating to e-infrastructure and HPC.
Start Year 2014