UK’s Emerald Supercomptuer Enters Service
|Emerald GPU cluster|
Using the newly-available technology, researchers will tackle areas ranging from healthcare (Tamiflu and swine flu); astrophysics (real-time pulsar detection application for the forthcoming Square Kilometre Array Project to deploy the world's most powerful radio telescope), bioinformatics (analysis and statistical modelling of whole-genome sequencing data); climate change modelling; complex engineering systems; simulating 3G and 4G communications networks and developing new tools for processing and managing medical images.
Both supercomputers will be unveiled tomorrow at the Science and Technology Facilities Council's Rutherford Appleton Laboratory (RAL), which will host and operate Emerald, a GPGPU system utilizing NVIDIA's Tesla accelerator technology. Iridis 3 is being hosted by the University of Southampton.
The occasion also marks the official launch of the e-Infrastructure South Consortium, which comprises four of the UK's leading universities — Bristol, Oxford, University College London and Southampton. The Consortium has collaborated with the Department of Scientific Computing at RAL to form the e-infrastructure South Centre for Innovation which will own and operate both supercomputers. The Consortium also will share access between the partners, providing an infrastructure for the development of data-driven applications, simulation and software, as well as training to create the next generation of scientists and engineers.
Both supercomputers have been funded by a £3.7 million grant from the Engineering and Physical Sciences Research Council (EPSRC), part of a £145 million Government investment in e-infrastructure.
Minister for Universities and Science David Willetts MP said: "These two new supercomputers form part of the Government's £145 million investment in e-infrastructure and will be invaluable assets to business and universities. They will drive growth and innovation, encourage inward investment in the UK and keep us at the very leading edge of science."
Dr Lesley Thompson, Director of EPSRC's Research Base said: "High performance computers based within the Consortium's research-intensive universities will enable better training and recruitment of world-class research talent, help develop new research ideas, and speed up the rate at which complex data can be processed. These new supercomputers are crucial to maintaining the UK's leading science base and underpinning our national competitiveness and economic recovery."
Professor Anne Trefethen, Professor of Scientific Computing, University of Oxford said: "The high set-up costs both in terms of equipment and expertise can be a major barrier to SMEs expanding into newer or bigger markets. This new center will make it easier for them to step up into the next league. In turn, the supercomputers will help university-led researchers work with industrial partners to develop and test innovative new products and technologies.
Local businesses that will benefit from use of the supercomputers include Numerical Algorithms Group, Schlumberger Abingdon and InhibOx.
SupercomputersEmerald is a Hewlett Packard-based system with 372 NVIDIA Tesla GPUs. It is the UK's largest and most powerful GPU-based supercomputer. NVIDIA awakened the world to computer graphics when it invented the GPU in 1999. From its roots in visual computing, the company expanded into parallel computing and mobile computing. Today, its processors power a broad range of products, from smart phones to supercomputers. NVIDIA's mobile processors are used in phones, tablets and auto infotainment systems. PC gamers rely on GPUs to enjoy spectacularly immersive worlds. Professionals use them to create visual effects in movies and design everything from golf clubs to jumbo jets. And researchers utilize GPUs to advance the frontiers of science with high-performance computers. The company holds more than 2,300 patents worldwide, including ones covering ideas essential to modern computing.
Emerald is the UK's largest and most powerful GPU-based supercomputer, ranked #159 on the June 2012 Top 500 list, with a score of 114.4 Tflops. Emerald has 372 NVIDIA Tesla M2090 processors installed by HP with high speed Panasas storage and Gnodal low latency 10 gigabit Ethernet.
GPU computers use a CPU and GPU together in a heterogeneous co-processing computing model. The sequential part of the application runs on the CPU and the computationally-intensive part is accelerated by the high floating point performance of the GPU's 100s of processor cores that operate together to crunch through the data in the application.
The Tesla 20-series GPU is based on the latest CUDA architecture which is optimized for scientific applications at 1/10th the cost and 1/20th the power of traditional CPU-only servers. Mapping a function to the GPU involves rewriting the function to expose its parallelism and to manage the movement of data to and from the GPU so the function can be calculated by 1000s of threads simultaneously.
GPU computing helps researchers address scientific problems, such as modelling the formation of planets, stars and galaxies, and provides the parallelization for their codes to take advantage of the capability offered by the massively parallel GPU architecture.
Iridis is the supercomputer of the University of Southampton. The latest generation is called Iridis 3 and was launched in 2010 when it was ranked position #74 in the Top 500 worldwide. Iridis 3's 8,000 processors are capable of performing 72 trillion calculations per second.