STFC and Maxeler Technologies to develop energy efficient HPC system
The Science and Technology Facilities Council (STFC) and London-based Maxeler Technologies are collaborating in a project funded by the UK Department of Business Innovation and Skills to install the next generation of supercomputing technology in a new facility at the Daresbury Laboratory focusing on energy efficient supercomputing to enable UK industry to have the edge in using a technology designed for the move towards Exascale computing.
It is claimed that the dataflow supercomputer will feature Maxeler developed MPC-X nodes capable of an equivalent 8.52TFLOPs per 1U and 8.97 GFLOPs per watt, a figure that would top the Green500 if the system was available today. MPC-X nodes build on the previous generation technology from Maxeler deployed at JP Morgan where real-time risk computation equivalent to 12000 x86 cores was achieved in 40U of dataflow engines.
STFC Technology Division head, Dr Peter Oliver said: ‘The use of MPC-X technology builds on the expertise of STFC’s Scientific Computing Department and allows us to develop energy efficient High Performance Computing applications meeting the needs of our academic and industrial collaborators.’
The new MPC-X supercomputer will be available in Summer 2014 and will allow UK industry and academia to develop products and services based on MPC data analytics engines for applications domains such as; medical imaging and healthcare data analytics, manufacturing, industrial microscopy, large scale simulations, security, real-time operations risk, and media/entertainment.
Prof Michael J Flynn, chairman of Maxeler Technologies and Professor of Electrical Engineering at Stanford University said: ‘Multiscale Dataflow Computing came out of early research funded by the US government and it is exciting to see a first deployment in a national laboratory in the UK. Combined with our collective efforts as part of the OpenSPL consortium, we at Maxeler are excited to see spatial computing at the forefront of next generation computing technology.’