Posted: 19 Jun 2013 | 07:31
Posted: 17 Jun 2013 | 09:18
Three members of EPCC staff (Terry, myself and Alistair) went back to school on 7th June when Musselburgh Grammar near Edinburgh held a science fair for its 200 First Year students (12-13 year olds).
Our remit was to introduce these young folks to supercomputers, in particular HECToR, the UK national supercomputing service hosted here in Edinburgh, and to give them an idea of how these types of system work and the sort of research that is undertaken using them.
Posted: 14 Jun 2013 | 16:02
EPCC's seminar series, which is usually open to all and given by EPCC staff, that covers a wide variety of topics, from those closely related to HPC to others which are much more general. An example of the latter is a talk I recently gave on cyber security. With an estimated ten million cyber-attacks worldwide per day, from individuals to small and large-scale organisations, this is something that we should all be aware of.
Posted: 12 Jun 2013 | 13:20
Following on from my recent post on Xeon Phi, thanks to the hard work of our Systems Development Team we now have a fully configured server sporting the two Intel 5110P Many Integrated Core (MIC) co-processor cards installed and ready to go. The imaginately named 'phi' machine is connected to our internal Hydra cluster and is available for staff, students and visitors to port and test their applications.
Posted: 12 Jun 2013 | 10:13
Posted: 10 Jun 2013 | 12:26
TPLS (Two-Phase Level Set) is a Computational Fluid Dynamics code developed by Dr Prash Valluri of the University of Edinburgh's School of Engineering and Dr Lennon Ó Náraigh of University College Dublin. It simulates the interface between two fluid phases, a phenomenon with a number of industrial applications including oil and gas hydrate transport, cleaning processes, distillation/absorption, and evaporative cooling of microelectronics.
Posted: 6 Jun 2013 | 10:20
In my Software Sustainability Institute role here at EPCC, together with Neil Chue Hong and Arno Proeme, I have been working on a Jisc-funded project that is attempting to create a Software Hub for Jisc.
What is the Jisc Software Hub? Well, it serves two purposes: it attempts to catalogue all the existing software that Jisc has funded over the last decade or so and it will also try to promote some of this software to encourage uptake within the UK academic community and further afield. This is a Jis-funded pilot project to establish the feasibility/cost/value of such work and based on that a decision will be made on how to progress this and whether other organisations may join in this effort. Jisc is keen for other funding councils to join in this undertaking, instead of building their own Software Hub.
Posted: 3 Jun 2013 | 09:42
A joint effort between MathWorks and EPCC has successfully demonstrated cloud-like access to MathWork’s modelling suite on INDY, EPCC's HPC cluster targeted at industrial users. Users can now readily scale-up their computationally intensive MATLAB® programs and Simulink® models. The complete MathWork’s software suite, including MATLAB®, Parallel Computing Toolbox™(MPCT) and Distributed Compute Server™(MDCS) has been installed.
Posted: 31 May 2013 | 09:08
Austria Center, Vienna (© IAKW-AG / Marius Höfinger)
This year’s European Geophysical Union General Assembly (EGU2013) was held last month at the Austria Center in Vienna. About 11,000 participants come together from all fields in Earth science: seismology, oceanography, geology, meteorology, planetology… you name it, it’s there. So, lots of parallel sessions. I gave a presentation on iCORDI and the RDA at two sessions: ‘ICT-based hydrometeorology science and natural disaster societal impact assessment’ and ‘Marine Data Management’.
Posted: 28 May 2013 | 14:32
While a surprisingly high proportion of HPC users are happy to keep their data on a single HPC service, or at most to move it within the hosting institution, sometimes is becomes necessary to move large volumes of data between different sites and institutions. As anyone who has ever tried to support users in this endeavour knows, it can be much harder to get good performance than it should be. This post is an attempt to document the available tools and technologies as well as common problems and bottlenecks.