July 2013
Dinosaur racing at EPCC
Author: Nick BrownPosted: 31 Jul 2013 | 14:49
The Animal Simulation project, run at the University of Manchester, aims to create realistic simulations of animals both present and extinct. By combining the expertise of a number of scientific fields along with high performance computing (HPC), they have created GaitSym, a code capable of realistically simulating movements of animals based on a 3D model of their skeleton and biological data.
DiRAC driving test ready to roll
Author: Mike JacksonPosted: 25 Jul 2013 | 10:44
Since June 2012, The Software Sustainability Institute and Software Carpentry have been working with the DiRAC consortium to develop a "driving test" or basic software skills aptitude test. The test is now ready to be rolled out across DiRAC, the UK's integrated supercomputing facility for theoretical modelling and HPC-based research in particle physics, astronomy and cosmology.
PRACE Summer of HPC Students@EPCC
Author: Irina NazarovaPosted: 22 Jul 2013 | 10:16
The SoHPC programme offers undergraduate and junior postgraduate university students the opportunity to spend two months of the summer at an HPC centre in a PRACE partner country. Students undertake a visualisation project, which is based on the outcomes of PRACE technical work or other work using PRACE resources.
Software Carpentry in Bath
Author: Mike JacksonPosted: 19 Jul 2013 | 07:35
This week I was in Bath to lead a Software Carpentry boot camp organised by Software Sustainability Institute fellow, Alex Chartier. I was joined by Chris Woods from the University of Bristol, who made his instructor debut. The SSI fellow Manchester fellow, Michael Croucher, also came along to help out.
EPCC joins the OpenACC consortium
Author: Adrian JacksonPosted: 18 Jul 2013 | 14:00
EPCC has recently joined the OpenACC consortium. OpenACC, a directives-based parallel programming standard, is designed to simplify the programming and utilisation of heterogenous computer systems, where standard CPUs and accelerators (such as GPUs) are combined. Using OpenACC, developers can specify loops and regions of code in standard C, C++ and Fortran to be offloaded from a CPU to an attached accelerator, and also target parallelism on a range of different CPUs and accelerators without having to modify source code.
