March 23, 2011
HPC Wales has selected Fujitsu to deliver a 190-teraflop high performance computing grid that will be deployed at a number of sites across the Welsh countryside. Fujitsu will be paid £15m ($24 million) over the next four years to set up and maintain the computing infrastructure for the project, as well as provide application and computing expertise.
Announced in July 2010, HPC Wales is an ambititous five-year project intended to kickstart the use of high performance computing across academia and industry in Wales -- and potentially further afield. The idea is to construct a supercomputing grid for supporting university R&D to be used as a springboard for commercial HPC adoption. Major targeted applications include digital entertainment, environment and energy, life sciences, advanced materials, and manufacturing.
HPC Wales hopes to be able to sell supercomputing time to regional businesses to help support and grow the effort, but most of the impetus behind the effort is being driven by the academic research community. More than 100 HPC-ready projects encompassing 540 researchers have already been identified. Of these, 80 percent had either current business partners or potential commercial applications.
The project is being funded to the tune of £40m: £19m from the European Regional Development Fund (ERDF) and European Social Fund (ESF), and £10m from the UK Department for Business, Innovation and Skills (BIS). The remainder will come locally from collaborating academic institutions, the Welsh Assembly Government, and the private sector. About £4 million of this is coming from Fujitsu, itself, who is investing in the project as a partner. HPC Wales will be managed by a non-profit alliance set up by the St David's Day Group of Universities and the University of Wales.
The deal will mark the return of Fujitsu-bred HPC to the United Kingdom after a 10-year hiatus. It will also represent the company's largest HPC deployment in Europe to date. Although the Japan-based firm is multinational in scope, in the HPC arena Fujitsu has tended to stick close to home, collecting government-backed HPC deals at a fairly regular clip.
Thanks to the project, 450 Fujitsu employees will be now be working at offices in Swansea and Cardiff, a sizable contingent given the relatively modest size of the contract. To put that in perspective, Cray would have had to send more than half its workforce to Wales to equal this effort.
No information was forthcoming about other vendors bidding on the contract, but one can speculate that Tier 1's with a strong European presence (such as IBM, HP, and Bull) were also in the running. The fact that Fujitsu was awarded the deal is something of a coup, and suggests the Japanese computer maker was serious about its intentions to become an HPC technology exporter.
Not that the company lacks the HPC cred to close a big deal. Fujitsu is the primary contractor for Japan's Next Generation Supercomputing Project. The company became the lone system vendor when NEC and Hitachi backed out of the project in in 2009. That work will culminate in the 2012 deployment of a 10-petaflop SPARC 64 VIIIfx-based "K system" supercomputer for the government-backed RIKEN research institute.
Nothing quite so exotic for the Welsh, however. The HPC Wales computing grid will be made up of 1,400 Fujitsu Primergy servers, using Intel Xeon processors and InfinBand interconnects. The individual clusters, which will be installed at 12 different sites, will run either Linux or Windows. Those individual systems will use similar technology to Fujitsu's Primergy BX900 machine at the Japan Atomic Energy Agency. That system alone tops 190 teraflops -- larger than the entire HPC Wales setup.
Other vendors that will be supplying equipment or software for the project include Intel, Platform Computing, Microsoft, Mellanox, DataDirect Networks, Cisco and Symantec.
The major hubs for HPC Wales will be at Swansea University/Pembrokeshire Science and Technology Park and Cardiff University, with links to smaller systems at Swansea, Aberystwyth, Bangor and the University of Glamorgan. Additional links will be made to the University of Wales Alliance Universities and participating businesses.
The server clusters at the individual sites will be hooked up via a high bandwidth network (the details of which were not immediately available) so as to make the computing resources available as a grid. Fujitsu's secret sauce is their SynfiniWay middleware technology, which will provide a service-oriented framework for the grid in the style of a private cloud. Basically SynfiniWay manages workflows through the grid/cloud by way of its meta-scheduler, while providing a high-level interface to the end user that hides most of the messy details of the hardware infrastructure.
The overarching goal of the project is to stimulate the Welsh economy and make the area a regional base for high performance computing. The effort is projected to bring in an additional £22.8m of economic output over the next 10 years, while creating over 400 high-end jobs and at least 10 new businesses. That seems fairly modest in scope, especially considering the £40m input for the project.
Although the project is only funded for five years, all the stakeholders hope and expect the work will be extended well beyond 2015. To make that possible the project will have to attract enough commercial partners to become self-sustaining such that it can cover operational and equipment costs going forward. If successful, it could become a model for other efforts to mainstream HPC for commercial users.
Jun 18, 2013 |
The world's largest supercomputers, like Tianhe-2, are great at traditional, compute-intensive HPC workloads, such as simulating atomic decay or modeling tornados. But data-intensive applications--such as mining big data sets for connections--is a different sort of workload, and runs best on a different sort of computer.
Read more...
Jun 18, 2013 |
Researchers are finding innovative uses for Gordon, the 285 teraflop supercomputer housed at the San Diego Supercomputer Center (SDSC) that has a unique Flash-based storage system. Since going online, researchers have put the incredibly fast I/O to use on a wide variety of workloads, ranging from chemistry to political science.
Read more...
Jun 17, 2013 |
The advent of low-power mobile processors and cloud delivery models is changing the economics of computing. But just as an economy car is good at different things than a full size truck, an HPC workload still has certain computing demands that neither the fastest smartphone nor the most elastic cloud cluster can fulfill.
Read more...
Jun 14, 2013 |
For all the progress we've made in IT over the last 50 years, there's one area of life that has steadfastly eluded the grasp of computers: understanding human language. Now, researchers at the Texas Advanced Computing Center (TACC) are utilizing a Hadoop cluster on its Longhorn supercomputer to move the state of the art of language processing a little bit further.
Read more...
Jun 13, 2013 |
Titan, the Cray XK7 at the Oak Ridge National Lab that debuted last fall as the fastest supercomputer in the world with 17.59 petaflops of sustained computing power, will rely on its previous LINPACK test for the upcoming edition of the Top 500 list.
Read more...
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?
Join our webinar to learn how IT managers can migrate to a more resilient, flexible and scalable solution that grows with the data center. Mellanox VMS is future-proof, efficient and brings significant CAPEX and OPEX savings. The VMS is available today.