The latest TOP500 list, which twice yearly publishes a list of 500 supercomputers, said that China tripled the number of supercomputers or high performance systems.
Meanwhile, the authors of the report said that the USA has fallen to its lowest point since the list was first compiled in 1993.
The report notes that China is also fast becoming a serious manufacture of high performance computers (HPCs) with “multiple” vendors become more active.
Top of the lsit is China’s Tianhe-2, which has kept its position as the world’s most powerful supercomputer. Tianhe-2 was developed by the Chinese National University of Defence Technology.
Tienhe-2 has a performance of 33.86 petaflop/s using the Linkpack benchmark. Second on the list is a Cray XK7 system called Titan, deployed at the US Department of Energy’s Oak Ridge National Laboratory.
Nvidia and IBM have teamed up to create two supercomputer centres – one based at the Lawrence Livermore labs and the other at the Oak Ridge National Laboratory.
It’s part of IBM’s supercomputing contract with the US Department of Energy (DoE) and will help to create scientific and engineering applications for DoE initiatives and for two supercomputers called Summit and Sierra.
Summit and Sierra will be delivered to both Oak Ridge and Lawrence Livermore in 2017 and will swing into operation in 2018.
Applications will be created for energy, climate research, cosmogology, biophysics and health. But there will also be applications related to US national security.
Summit and Sierra will be built using IBM Power CPUsand with Tesla GPU accelerators, using Nvidia’s NVLink, which is a high speed processor bus.
Engineering scientists from IBM and Nvidia will work together with scientis at both labs to optimise code and speed up performance.
IBM said it’s more than just delivering hardware systems and they believe that the work the four teams will do will create new ways of thinking about applications and software.
A partly Dell-powered supercomputer, Stampede, is being lauded tomorrow at its home in Texas Advanced Computing Center (TACC) at Austin’s University of Texas.
Stampede has Dell’s PowerEdge servers under the bonnet and is the largest of the company’s public production cluster deployments so far. The supercomputer is supported by the National Science Foundation and has a 2.2 petaflop base cluster.
TACC also has what is currently the largest configuration of IntelXeon Phi parallel coprocessors, managing just over seven petaflops of performance. All in, the integrated system has almost 10 petaflops, which Dell points out means the supercomputer can run nearly 10 quadrillion math operations a second.
Research is already being carried out on Stampede to predict the frequency of earthquakes in California, as well as to identify and image brain tumours, mixing MRI scan data with other biophysical models to chart tumour growth. The research is also focusing on designing nanocatalysts to capture CO2 from exhaust, to be converted into valuable substances used for industrial applications, Dell said.
While Stampede is not gunning for the top spot on the international supercomputing arms race, it’s clear the system has interesting applications. Supercomputers are increasingly being used to tackle tough questions and make complex calculations, quickly, where traditional methods could take weeks for similar results – for instance, in DNA mapping.
Last year, our favourite supercomputer story was about a system running calculations to see if the entire universe is, in fact, a simulation created by supercomputers in the distant future.
The dedication event for Stampede will be tomorrow at the J J Pickle Research Campus, Austin. Former stakeholders will be speaking at the event, including Michael Dell, Intel’s Diane Bryant, Congressman Lamar Smith and the University of Texas at Austin president William Powers.
Two of the UK’s most powerful supercomputers will whirr into action tomorrow, giving businesses and academics access to the cutting edge processing power.
One is an HP machine with Nvidia‘s Tesla accelerated GPU on board, named Emerald, which will come online along the Iridis 3, and will be used for a variety of number-crunching applications.
These will include healthcare studies into Tamiflu and swine flu, as well helping deploy the world’s most powerful telescope, simulating 4G communications networks, and more.
They will also be used for business applications, giving SMEs a leg up to use the power of High Performance Computing, and can be used for testing new products.
The supercomputers were funded by a £3.7 million grant from the Engineering and Physical Sciences Research Council – part of a £145 million government investment in e-infrastructure. Both the supercomputers will be unveiled at the Science and Technology Facilities Council’s Rutherford Appleton Laboratory (RAL).
This is where Emerald will be housed, while the Iridis 3 is being hosted by the University of Southampton.
Dr Lesley Thompson, Director of EPSRC’s Research Base said that the new supercomputers are crucial to “maintaining the UK’s leading science base and underpinning our national competitiveness and economic recovery”.
Universities secretary David Willets heralded the suptercomputers as keeping the UK at the cutting edge of science.
The Top 500 supercomputer list gave ample opportunity for bitter rivals Intel and AMD to talk up all the good they’re doing in that sector.
AMD issued a statement headlined: “AMD supercomputing leadership continues with broader developer ecosystem and latest top 500”. It keenly pointed out that 24 of the top 100 are powered by AMD, though Intel was pleased to announce its architecture powered 74 percent of all systems, and 77 percent of all new entries.
Intel talked up the fact that Europe’s fastest supercomputer – SuperMUC in Germany – makes use of the Intel Xeon E5 family. The system delivers 2.9 petaflops, which is a fair amount of flops. Meanwhile, the company has decided on the brand for its Many Integrated Core architecture products. They will be out by the end of 2012. Chipzilla has abandoned Knight’s Corner to go with ‘Xeon Phi’. Xeon Phi will be available in the PCIe form factor, holding over 50 cores and a minimum of 8GB GDDR5 memory, plus 512b wide SIMD support.
AMD pointed out that, working closely with its partners in HPC, there have been several new developments in LS-DYNA simulation software for LSTC’s AMD Opteron 6200 series, as well as programming options for AMD GPUs from CAPS, and Mellanox’s Connect-IB announcement that promises to bring FDR 56Gb/s InfiiBand to AMD portfolios.
LS-DYNA is an element program that simulates complex problems and is used by the auto, aerospace, construction, military, manufacturing, and biongineering industries. The beta version is available while general availability should come in the third quarter 2012.
Intel claims that, with its technology, the HPC industry will be tackling challenges like mapping the full human genome in 12 hours at under $1,000, compared to the two weeks at $60,000 that is necessary now. The company promises to deliver exascale performance by 2018.
IBM has won a contract to install a $3.3 million supercomputer at a new technology centre in New Jersey, due to open today, in partnership with Rutgers University.
IBM’s machine, called Blue Gene/P, reports the Wall Street Journal, will be among the most powerful computer systems in the north east of the USA. It has been compared to the gameshow-addicted Watson, which made a splash when it put contestants to shame on TV’s Jeopardy.
It will be different to other installations as Rutgers university said private companies will be allowed to use the system, including Xerox, Siemens Ag, Johnson & Johnson, JP Morgan Chase, and Bristol-Myers Squibb. Rutgers is hoping that having the system on-site will open the doors to more investment from the National Science Foundation and National Institutes of Health.
The university is yet to decide how much private companies will have to pay for access.
Blue/Gene P is likely to be used mostly to sort through big data for analysis. Through simulations, supercomputers are able to calculate and answer complex questions far quicker than traditional research methods.
A Palo Alto venture capitalist told the Wall Street Journal that research institutions are going to have to learn to adapt to commercial models. “Universities must start to develop these broad partnerships with industry,” he said.
An IBM spokesperson gave us a few more details on the machine. The two Blue Gene/ P racks at Rutgers will be “far more powerful than any computer at the university today.” Rutgers has decided to call the machine Excalibur, and as future funding is made available, the university plans to add the latest-generation Blue Gene/Q system by the end of the year.
Blue Gene /P has 1024 quad core processors per rack (4096 cores/rack) and runs at 13.9 TFlop/s rack and consumes approximately 27 KWatts/ rack. Rutgers have bought 2 racks, so it runs at around 27 Tflop/s.
The University of Edinburgh said the next stage of supercomputers for UK scientists and researchers is ready to roll and rock.
The computers, dubbed Hector and Bluegene Q, are based at Edinburgh Uni’s advanced computing facility and David “Two Brain” Willetts announced the move this afternoon. He is called “Two Brain Willetts” because he is so brainy, but the supercomputers at Edinburgh can transact 250,000 calculations a second, something which is possibly beyond his abilities.
The computers are funded by four research councils in the fields of engineering and physical sciences, science and technology, environment, and biological sciences.
Hector and Bluegene can each manage 800 Teraflops. Hector has a 90 Terabyte memory and a Petabyte of disk space.
Bluegene, an IBM box, is the most energy efficient supercomputer ever, it’s claimed. Hector is a Cray system.
Supercomputer peddlerCray has won a huge contract with the University of Illinois’ National Center [sic] for Supercomputing Applications. It’ll be providing the beast of a machine for the National Science Foundation’s Blue Waters project.
The NSF’s Blue Waters project has been on the cards for some time. Initially, IBM was set to build the machine but it pulled out at the last minute. So Cray got the contract.
Cray says the computer will be a Cray XE6 system twinned with an upgraded XK6 with GPU capability. Both will be bunged into the same machine to achieve a sustained performance of over a petaflop for more demanding scientific simulations.
Together, the integrated machne will sport 16-core AMDOpteron 6200 processors, AKA Interlagos, along with Nvidia’s Kepler GPU. Cray will provide its own storage.
The Cray contract runs at $188 million. It will take most of 2012 to get the system up and running but it should be all systems go in the fourth quarter, where it will be hosted at the University of Illinois’ National Petascale Computing Facility.
The contract win means Cray has tinkered with its financial outlook. Its 2011 projections are the same, but for 2012 Cray expects revenues to sit somewhere between $340 – $360 million. The Blue Waters system is penned in to cover around 40 percent of that.
With the help of a fair few Nvidia Tesla GPUs, a team of Chinese researchers has managed to construct a simulation of the H1N1 influenza virus – down to the atomic level.
A team at the catchy-named Institute of Process Engineering of Chinese Academy of Sciences is taking advantage of molecular dynamic simulations to use as a kind of microscope, letting them look into the atomic structure of H1N1. Over 2,200 Tesla GPUs power the Mole-8.5 supercomputer.
Without the supercomputer they’d be in for a tough job. The problem with studying bacteria and viruses in the lab is that specific reactions happen very quickly, and the detail is so minute they’re often lost forever. Using an accurate simulation means the team can stop-and-start whever they need to.
Even simulating viruses has been difficult in the past, according to Nvidia, because of the complexity of running billions of particles in exactly the right environment.
To get around that, the researchers created a molecular dynamics simulation which uses GPU acceleration, running on 288 server nodes.
Using the Mole-8.5 supercomputer, they managed to simulate 770 picoseconds perday, with, says the team, an integration time step of one femtosecond for 300 million atoms. A femtosecond is not long at all.
Eventually, the team believes its research could lead to important breakthroughs in anti-viral drugs to control H1N1, and provide the researchers with an insight into controlling epidemics.