Subscribe to the EPCC news feed
Items of news from other sources where EPCC has featured.
The future of HPC in Europe?
HPCWire highlights a report written by EPCC on Europe’s future HPC development and its economic importance to the region.
The authors echo many of the arguments made by other global organizations—that the key to competitiveness in coming years hinges on HPC and more specifically, on modelling and simulation.
Read more at hpcwire.com
Grid helps breed better horses, fish, chickens… and crocodiles
GridQTL - a new grid-based platform designed at the University of Edinburgh - helps veterinary scientists and farmers to figure out the vast number of genes that can sometimes contribute to just a single, valuable physical trait. It’s already been used to identify previously elusive traits in horses, fish, chickens, and crocodiles…
Read the full story at isgtw.org.
EPCC: past, present and future
The latest issue of the Royal Society of Edinburgh’s Science Scotland newsletter includes 3 features inspired by our recent 20th anniversary celebrations.
PlanetHPC: what’s next for high-performance computing?
What are the challenges and priorities for future European research into high-performance computing (HPC)? EPCC, the supercomputing centre at the UK’s University of Edinburgh, has launched a two-year consultation that aims to answer this question. And with medical physicists prime candidates for exploiting advanced computational resources – the project wants to hear your views.
Read the rest of this article at medicalphysicsweb.
Virtualisation appliances within traditional Grids
Panagiotis Kritikakos of EPCC writes about how virtualisation can enhance a Grid environment.
Virtualisation Appliances within Traditional Grids
The use of multi-core processors opens new horizons in the deployment and the use of computer systems as well as in the design and development of software. Moreover, the modern multi-core processors provide hardware virtualisation support by default. This gives great advantage to virtualisation platforms as virtual machines can gain increased performance and can be deployed in sectors where, traditionally, physical machines were deployed. Virtualisation uptake has been rapid on standard server applications, but has not been yet exploited in Grid and High Performance applications. We identify a number of appliances where virtualisation can be used to enhance a Grid environment, either in academia or industry.
Reliability / Availability / Fault Tolerance
The cost of failure in the Grid and HPC domain applications is significant. Restarting the whole machine is not the most effective way to fix the problem. Virtualisation offers extra reliability as we can divide single systems into multiple ones for different groups of users. Having applications that need low-level access for privileged operations can lead to compromised integrity of the system. Application-induced failure of the operating system will affect only the virtual machine the application is running on. In addition, virtualisation can offer improved performance, as intelligent, pro-active, fault-tolerant solutions enable a virtual machine to migrate automatically from an ‘unhealthy‘ machine to a ‘healthy‘ one. Fault tolerance and live migration increase the probability of completion for applications with long run-times.
Portability
Virtual machines can be set up to test new systems when upgrades are needed. They can be used to exploit new hardware resources by different operating systems and different user groups. A specific virtual machine can easily be ported to another physical host which can even be a desktop or laptop.
Productivity and Development
Virtual machines can be used to set up a lab grid environment for testing purposes. The operating system can be configured in a way to meet the requirements of the specific application. Any tools required can be installed without affecting other applications and users who work on different virtual machines. Geoffroy Vallee terms this “adapting systems to applications and not applications to systems”. For instance, a virtual cluster (i.e. networked virtual machines within a single physical host) could demonstrate the scaling capabilities of Grid applications before being deployed in large scale.
Virtualisation middle-ware supports all major operating systems: Linux, Solaris, BSD variants and Windows. Applications that are developed on one platform do not necessarily need to be ported to another. A virtual machine with the requested operating system can be configured to host the application. On the other hand, multiple virtual machines with different operating systems and different versions of operating systems and system libraries can be made available to developers to experiment, test and debug their code.
Management
Virtual machines and virtual clusters offer ease of management. A virtual machine template can be easily cloned to as many virtual machines as desired. Management tools provide central management of the virtual machines even if they do not run on the same physical host. Monitoring tools of virtual machine inventories help to identify faulty systems and restart or re-configure when and as needed. A crash of the operating system does not need physical presence of the administrator to reboot the machine; it can be done remotely through the management tool.
In summary, virtualisation offers significant user and provider benefits. The combination of wide virtualisation support in modern commodity hardware (Intel VT and AMD-V) shows great promise for virtualisation to become one of the default ICT infrastructure technologies of the future.
This article first appeared on the IT-TUDE blog:
http://www.it-tude.com/grid_voices/2010/04/virtualisation-appliances-within-traditional-grids/
FT: Supercomputers: Speed within reach
EPCC’s Mark Parsons appears in the Financial Times, talking about providing supercomputing facilities for business. Read more:
FT.com: Supercomputers: Speed within reach at affordable prices
Guardian: LEaD Project
EPCC’s Judy Hardy talks to The Guardian about the LEaD project, which is investigating student experiences of learning technology…
Scientific Computing World: UK supercomputer rises to scientific challenges
Scientific Computing World features an article about HECToR’s impact on the world of scientific computing.
HPCwire: DEISA2 Aims for Integrated European HPC Ecosystem
HPCwire features a DEISA press-release, DEISA2 Aims for Integrated European HPC Ecosystem.
British Council: Supercomputer Power
As part of its Cubed webzine, the British Council has an article on the power and application of supercomputers entitled ‘Supercomputer Power‘.
iSGTW: A Data Grid For Cell Biology
As cell biology moves from labs to computer desktops, researchers must deal with increasingly vast volumes of data. Traditional ways of sharing this data—such as physically shipping hard drives—just cannot keep up.
iSGTW feature: A Data Grid For Cell Biology
Public Service Review: A super computer
Public Service Review: European Union Issue 15: Jane Nicholson, of the EPSRC, gives an overview of HECToR – a modern day hero for science.
BBC: How HECToR supports scientific research
BBC Radio 4’s Material World talks to Prof. Arthur Trew and Prof. Richard Kenway about HECToR.
INWA: intercontinental grid links EPCC to Beijing and Western Australia
GRIDtoday has an article about how an intercontinental grid links EPCC to Beijing and Western Australia: Intercontinental Grid Reduces Latency via TEIN2.
Scientific Computing World: UK national supercomputer unveiled
Scientific Computing World has an article about HECToR: UK national supercomputer unveiled
Nature: Britain upgrades its number cruncher
Nature has an article about HECToR: Britain upgrades its number cruncher
The Herald: The new brain of Britain
The Herald has an article about HECToR: The new brain of Britain
The Scotsman: Inside the life-saving £60m supercomputer
The Scotsman has an article about HECToR: Inside the life-saving £60m supercomputer
Scientific Computing: UK supercomputer to weather climate change
Scientific Computing World has an article about HECToR: UK supercomputer to weather climate change
UK’s best supercomputer set to launch in Lothian
Edinburgh’s Evening News has an article about HECToR’s impending launch.
HECToR in The Guardian
James Randerson, The Guardian’s science correspondent, takes a look at HECToR and discovers how it will will help British researchers simulate everything from climate change to financial markets.
Scottish Technology News: FHPCA Maxwell
The FPGA High Performance Computing Alliance (FHPCA) is continuing to promote Scotland as a hub of Field Programmable Gate Array (FPGA) technology. The Alliance, run from the University of Edinburgh by the EPCC, draws on the expertise and vision of both Scottish and international companies and the support of Scottish Enterprise. Hardware and software developed by the Alliance were used to build the Maxwell supercomputer, launched earlier this year. This computer is not only substantially quicker than standard PCs but is far more energy efficient, meaning its environmental impact is also minimised.
The FHPCA has recently held a number of seminars to demonstrate the capabilities of the Maxwell supercomputer. Taking part in a Birds-of-a-Feather session at the International Supercomputing Conference (ISC’07) in Dresden provided an opportunity to discuss and demonstrate the programmability of FPGAs for Application Developers.
The potential for utilising the technology within the oil and gas sector was highlighted at an Aberdeen event which featured a case study from OHM Surveys Ltd. The oil services company was one of the first firms to use Maxwell. Using one of the company’s codes for reservoir exploration proved a great success, significantly speeding up the process of data processing and the firm continues to work with Alliance partners.
Medical imaging technology also benefits greatly. Producing 3D images of a person’s face, used in surgery planning, traditionally took several minutes. By using Maxwell the process has been reduced to a few seconds.
However, the most spectacular results occurred when Maxwell turned its hand to running risk modelling codes used in the financial services industry. Mark Parsons, Commercial Director of EPCC explains: “We programmed up our own version of a code used to do risk calculations, and we had a very interesting experience. The other two codes sped up between 5 and 10 times when run on an FPGA. With this one we saw speed improvements of over 300 times.”
The Alliance is now speaking to a number of leading investment banks, some of whom have been conducting their own experiments with FPGAs.
It is not just these three sectors which would benefit from this Scottish innovation. Drug design, seismology and mobile telecoms are just some of the other areas which could see huge performance enhancements. A number of further seminars and forums are planned to maximise business opportunities.
Maxwell, currently in the running for the BCS IT Industry Awards 2007 for Best Use of Green Technology Project Award and the BT Flagship Award for Innovation, was designed and built by two Scottish firms, Nallatech and Alpha Data, and EPCC, the supercomputing centre at The University of Edinburgh. Although the team behind Maxwell want to see people buying the technology from the two SMEs, Mark added that Maxwell also exists “to allow companies to come and use it with their codes and understand whether it is going to be useful technology for them.”
For further information on the FHPCA events and activities, visit www.fhpca.org
iSGTW: BEinGRID launches next two million Euro call
BEinGRID—Business Experiments in GRID—today launched their next competitive two million Euro call for additional Business Experiments proposals targeting industry and research organizations to provide, use and validate grid technologies to meet business challenges.
The BEinGRID project has been conducting real-world experiments with grid technologies for more than a year and are promoting their first project results and innovative grid solutions at the European Services, Software and Grid Technology Days event today, organized by the European Commission with the support of BEinGRID.
Read the full iSGTW article.
iSGTW: Disaster management: in safe hands with FireGrid
Fire breaks out.
Your fire fighters arrive outside the burning building. It is buried in smoke; flames flick behind the haze. Should you enter? Or evacuate? Is the fire waning? How will it progress?
Countless fires have come under this same spotlight, including the World Trade Center collapse in 2001; the Mont Blanc tunnel fire in 1999; the Piper Alpha Explosion in the North Sea in 1988; and the Kings Cross subway station fire in London in 1987.
“These were all major disasters,” says Dave Berry, research manager of the National e-Science Centre in Edinburgh, UK. “People ask why they happened; in each case, if we’d had more information, the fires could’ve been dealt with more effectively.”
Berry is working on FireGrid, an R&D initiative with the long-term vision of running real-time fire simulations that include data available from multiple sources—models of fire and human behavior simulations; sensors like smoke detectors, motion detectors, temperature sensors; information from building management systems; and data from scenarios predicted by emergency service experts—and then incorporating these simulations into active fire response systems.
In this way, FireGrid aims to provide firefighters with the best available information, right when and where they need it.
BBC: A new kind of fire fighting
By Professor Jose Torero
The collapse of the Twin Towers of the World Trade Center (WTC) on 11 September 2001 was not directly caused by the impact of the two hijacked airliners but by the fires that followed.
New advances in the smart design and monitoring of buildings could mitigate future disasters and save many lives.
Today, with the improved knowledge and modern fire safety engineering at our disposal, we think we can now change some of these catastrophic outcomes.
For past 10 years, I and colleagues at the University of Edinburgh have been developing a new high-computing system called FireGrid.
It proposes a new paradigm for emergency response, the acquisition and digestion of large quantities of data by means of remote computer resources that can be accessed via the Grid.
Sensors within the buildings will provide a window to the inside of the fire while sophisticated computer models will use this information to forecast the progression of an event.
BBC: UK supercomputer sets faster pace
The UK’s fastest-proven supercomputer used by the academic community has doubled in size and performance.
The HPCx machine, based in Warrington, is now capable of operating at speeds up to 15.4 teraflops, or 15.4 trillion calculations every second.
DEISA: TeraGrid, DEISA Linked Via Wide-Area Global File System
TeraGrid and DEISA, the European supercomputing Grid infrastructure, have been linked, for the purposes of a technology demonstration, by a common, scalable, wide-area global file system spanning two continents.
EPCC@15: This year marks the 15th birthday of EPCC
This is, for us a significant milestone and I want to take this opportunity to review the past decade and a half, not only in terms of the changes we have seen as an organization, but also to reflect on the revolution that has taken place in the HPC arena more generally.
DEISA: The benefits of a virtual European supercomputer
The DEISA Consortium… a major step towards an integrated European HPC infrastructure.
OGSA-DAI: OGSA-DAI project receives additional $3.2 million
A research team that created software used by scientists worldwide has received follow-on funding of $3.2million (1.86 million pounds)…
QCDOC and Blue Gene: QCDOC and Blue Gene event in Edinburgh
The University of Edinburgh’s Parallel Computing Centre (EPCC) is holding an international event investigating the potential of two groundbreaking computing architectures: QCDOC and IBM’s Blue Gene.
The University of Edinburgh is the only centre in the world to host both systems…
INWA World’s longest grid computing link unlocks data
The three-continent grid links computers at the Edinburgh Parallel Computing Centre (EPCC) in the United Kingdom, Curtin University of Technology in Western Australia and the Chinese Academy of Sciences in Beijing…
FPGAs: Self-wiring supercomputer is cool and compact
An experimental supercomputer made from hardware that can reconfigure itself to tackle different software problems is being built by researchers in Scotland.
Opening of Advanced Computing Facility: Centre Advances Edinburgh’s High Powered Reputation
HRH Prince Philip did the honours Friday at Edinburgh University’s Advanced Computing Facility, which will help scientists to tackle complex scientific puzzles. The opening of Europe’s premier supercomputing facility will help researchers make key scientific breakthroughs in a way that would have been unimaginable only a generation ago.
QCDOC: Supercomputers target 12,000 nodes
A five-year project to develop three 10Tflops supercomputers to tackle a particularly complex problem of physics has concluded with the opening last week of one of the machines at Brookhaven National Laboratory in the US.
However, the Scottish member of the trio of 12,000-node computers sited at the Edinburgh Parallel Computer Centre (EPCC) has been operational since November, and is on the way to working at full specification …
FHPCA: Scottish Alliance to develop supercomputer unveiled
A Scottish industry alliance to build a supercomputer 200 times faster than a normal PC has been unveiled in Edinburgh …
DEISA: Europe looks to continental supercomputer
Several leading European HPC centers have devised an innovative strategy to build a terascale supercomputing facility with continental scope, called Distributed European Infrastructure for Supercomputing Applications (DEISA).
IBM BlueGene: University of Edinburgh orders Blue Gene supercomputer
One of the first commercial installations of IBM’s prototype system. The University of Edinburgh has confirmed that it has ordered a version of IBM’s prototype Blue Gene/L supercomputer, which was yesterday confirmed as the fastest computer in the world.
The Times: Britain falling behind in battle for biggest byte
IT has the power to unlock some of the world’s greatest mysteries, solve seemingly unanswerable questions and enable nations to steal a march on their competitors.
Little wonder then that the world’s major economies have been engaged in a fierce battle for decades to develop the world’s fastest supercomputer, and even less of a wonder that America has revelled this week in having wrestled ownership of the world’s fastest computer from Japan.
The $200 million IBM BlueGene/L computer, unveiled by beaming officials on Wednesday, can number-crunch faster than any other existing computer, managing 36.01 trillion calculations per second.
Grid computing - Harness the power
A recent demonstration of the world’s largest grid computer gives hope for those seeking to deliver intensive commercial applications.
NextGrid: EU grants 52m Euros to boost use of Grid
A 52-million-euro package of 12 European Union-funded research projects, that together aim to bring “Grid” networked computing out of research labs and into industry, has just been launched by the European Commission.
GRIDSTART: Surgeons turn to grid applications
A grid-enabled software application co-developed by UK researchers is helping surgeons performing facial reconstructions by simulating possible results prior to an operation.
EPCC Financial seminar: JP Morgan and EPCC in financial services tech drive
An Edinburgh University technology company, EPCC, and JP Morgan Chase, one of the world’s largest banking groups, have teamed up to spearhead the introduction of new financial services technology, which they claim is vital to the future of the industry in Scotland.