Engineers built a supercomputer from 64 Raspberry Pi computers and Lego

ScienceDaily (Sep. 11, 2012) — Computational Engineers at the University of Southampton have built a supercomputer from 64 Raspberry Pi computers and Lego.

The team, led by Professor Simon Cox, consisted of Richard Boardman, Andy Everett, Steven Johnston, Gereon Kaiping, Neil O'Brien, Mark Scott and Oz Parchment, along with Professor Cox's son James Cox (aged 6) who provided specialist support on Lego and system testing.

Professor Cox comments: "As soon as we were able to source sufficient Raspberry Pi computers we wanted to see if it was possible to link them together into a supercomputer. We installed and built all of the necessary software on the Pi starting from a standard Debian Wheezy system image and we have published a guide so you can build your own supercomputer."

The racking was built using Lego with a design developed by Simon and James, who has also been testing the Raspberry Pi by programming it using free computer programming software Python and Scratch over the summer. The machine, named "Iridis-Pi" after the University's Iridis supercomputer, runs off a single 13 Amp mains socket and uses MPI (Message Passing Interface) to communicate between nodes using Ethernet. The whole system cost under £2,500 (excluding switches) and has a total of 64 processors and 1Tb of memory (16Gb SD cards for each Raspberry Pi). Professor Cox uses the free plug-in 'Python Tools for Visual Studio' to develop code for the Raspberry Pi.

Professor Cox adds: "The first test we ran -- well obviously we calculated Pi on the Raspberry Pi using MPI, which is a well-known first test for any new supercomputer."

"The team wants to see this low-cost system as a starting point to inspire and enable students to apply high-performance computing and data handling to tackle complex engineering and scientific challenges as part of our on-going outreach activities."

James Cox (aged 6) says: "The Raspberry Pi is great fun and it is amazing that I can hold it in my hand and write computer programs or play games on it."

If you want to build a Raspberry Pi Supercomputer yourself see: http://www.soton.ac.uk/~sjc/raspberrypi

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by University of Southampton, via AlphaGalileo.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Note: If no author is given, the source is cited instead.

Disclaimer: Views expressed in this article do not necessarily reflect those of ScienceDaily or its staff.

View the original article here

Android-based network built to study cyber disruptions and help secure hand-held devices

ScienceDaily (Oct. 2, 2012) — As part of ongoing research to help prevent and mitigate disruptions to computer networks on the Internet, researchers at Sandia National Laboratories in California have turned their attention to smartphones and other hand-held computing devices.

Sandia cyber researchers linked together 300,000 virtual hand-held computing devices running the Android operating system so they can study large networks of smartphones and find ways to make them more reliable and secure. Android dominates the smartphone industry and runs on a range of computing gadgets.

The work is expected to result in a software tool that will allow others in the cyber research community to model similar environments and study the behaviors of smartphone networks. Ultimately, the tool will enable the computing industry to better protect hand-held devices from malicious intent.

The project builds on the success of earlier work in which Sandia focused on virtual Linux and Windows desktop systems.

"Smartphones are now ubiquitous and used as general-purpose computing devices as much as desktop or laptop computers," said Sandia's David Fritz. "But even though they are easy targets, no one appears to be studying them at the scale we're attempting."

The Android project, dubbed MegaDroid, is expected to help researchers at Sandia and elsewhere who struggle to understand large scale networks. Soon, Sandia expects to complete a sophisticated demonstration of the MegaDroid project that could be presented to potential industry or government collaborators.

The virtual Android network at Sandia, said computer scientist John Floren, is carefully insulated from other networks at the Labs and the outside world, but can be built up into a realistic computing environment. That environment might include a full domain name service (DNS), an Internet relay chat (IRC) server, a web server and multiple subnets.

A key element of the Android project, Floren said, is a "spoof" Global Positioning System (GPS). He and his colleagues created simulated GPS data of a smartphone user in an urban environment, an important experiment since smartphones and such key features as Bluetooth and Wi-Fi capabilities are highly location-dependent and thus could easily be controlled and manipulated by rogue actors.

The researchers then fed that data into the GPS input of an Android virtual machine. Software on the virtual machine treats the location data as indistinguishable from real GPS data, which offers researchers a much richer and more accurate emulation environment from which to analyze and study what hackers can do to smartphone networks, Floren said.

This latest development by Sandia cyber researchers represents a significant steppingstone for those hoping to understand and limit the damage from network disruptions due to glitches in software or protocols, natural disasters, acts of terrorism, or other causes. These disruptions can cause significant economic and other losses for individual consumers, companies and governments.

"You can't defend against something you don't understand," Floren said. The larger the scale the better, he said, since more computer nodes offer more data for researchers to observe and study.

The research builds upon the Megatux project that started in 2009, in which Sandia scientists ran a million virtual Linux machines, and on a later project that focused on the Windows operating system, called MegaWin. Sandia researchers created those virtual networks at large scale using real Linux and Windows instances in virtual machines.

The main challenge in studying Android-based machines, the researchers say, is the sheer complexity of the software. Google, which developed the Android operating system, wrote some 14 million lines of code into the software, and the system runs on top of a Linux kernel, which more than doubles the amount of code.

"It's possible for something to go wrong on the scale of a big wireless network because of a coding mistake in an operating system or an application, and it's very hard to diagnose and fix," said Fritz. "You can't possibly read through 15 million lines of code and understand every possible interaction between all these devices and the network."

Much of Sandia's work on virtual computing environments will soon be available for other cyber researchers via open source. Floren and Fritz believe Sandia should continue to work on tools that industry leaders and developers can use to better diagnose and fix problems in computer networks.

"Tools are only useful if they're used," said Fritz.

MegaDroid primarily will be useful as a tool to ferret out problems that would manifest themselves when large numbers of smartphones interact, said Keith Vanderveen, manager of Sandia's Scalable and Secure Systems Research department.

"You could also extend the technology to other platforms besides Android," said Vanderveen. "Apple's iOS, for instance, could take advantage of our body of knowledge and the toolkit we're developing." He said Sandia also plans to use MegaDroid to explore issues of data protection and data leakage, which he said concern government agencies such as the departments of Defense and Homeland Security.

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by Sandia National Laboratories.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Note: If no author is given, the source is cited instead.

Disclaimer: Views expressed in this article do not necessarily reflect those of ScienceDaily or its staff.

View the original article here

Quantum computer built inside a diamond

ScienceDaily (Apr. 4, 2012) — Diamonds are forever -- or, at least, the effects of this diamond on quantum computing may be. A team that includes scientists from USC has built a quantum computer in a diamond, the first of its kind to include protection against "decoherence" -- noise that prevents the computer from functioning properly.

The demonstration shows the viability of solid-state quantum computers, which -- unlike earlier gas- and liquid-state systems -- may represent the future of quantum computing because they can be easily scaled up in size. Current quantum computers are typically very small and -- though impressive -- cannot yet compete with the speed of larger, traditional computers.

The multinational team included USC Professor Daniel Lidar and USC postdoctoral researcher Zhihui Wang, as well as researchers from the Delft University of Technology in the Netherlands, Iowa State University and the University of California, Santa Barbara. Their findings will be published on April 5 in Nature.

The team's diamond quantum computer system featured two quantum bits (called "qubits"), made of subatomic particles.

As opposed to traditional computer bits, which can encode distinctly either a one or a zero, qubits can encode a one and a zero at the same time. This property, called superposition, along with the ability of quantum states to "tunnel" through energy barriers, will some day allow quantum computers to perform optimization calculations much faster than traditional computers.

Like all diamonds, the diamond used by the researchers has impurities -- things other than carbon. The more impurities in a diamond, the less attractive it is as a piece of jewelry, because it makes the crystal appear cloudy.

The team, however, utilized the impurities themselves.

A rogue nitrogen nucleus became the first qubit. In a second flaw sat an electron, which became the second qubit. (Though put more accurately, the "spin" of each of these subatomic particles was used as the qubit.)

Electrons are smaller than nuclei and perform computations much more quickly, but also fall victim more quickly to "decoherence." A qubit based on a nucleus, which is large, is much more stable but slower.

"A nucleus has a long decoherence time -- in the milliseconds. You can think of it as very sluggish," said Lidar, who holds a joint appointment with the USC Viterbi School of Engineering and the USC Dornsife College of Letters, Arts and Sciences.

Though solid-state computing systems have existed before, this was the first to incorporate decoherence protection -- using microwave pulses to continually switch the direction of the electron spin rotation.

"It's a little like time travel," Lidar said, because switching the direction of rotation time-reverses the inconsistencies in motion as the qubits move back to their original position.

The team was able to demonstrate that their diamond-encased system does indeed operate in a quantum fashion by seeing how closely it matched "Grover's algorithm."

The algorithm is not new -- Lov Grover of Bell Labs invented it in 1996 -- but it shows the promise of quantum computing.

The test is a search of an unsorted database, akin to being told to search for a name in a phone book when you've only been given the phone number.

Sometimes you'd miraculously find it on the first try, other times you might have to search through the entire book to find it. If you did the search countless times, on average, you'd find the name you were looking for after searching through half of the phone book.

Mathematically, this can be expressed by saying you'd find the correct choice in X/2 tries -- if X is the number of total choices you have to search through. So, with four choices total, you'll find the correct one after two tries on average.

A quantum computer, using the properties of superposition, can find the correct choice much more quickly. The mathematics behind it are complicated, but in practical terms, a quantum computer searching through an unsorted list of four choices will find the correct choice on the first try, every time.

Though not perfect, the new computer picked the correct choice on the first try about 95 percent of the time -- enough to demonstrate that it operates in a quantum fashion.

Share this story on Facebook, Twitter, and Google:

Other social bookmarking and sharing tools:

Story Source:

The above story is reprinted from materials provided by University of Southern California, via EurekAlert!, a service of AAAS.

Note: Materials may be edited for content and length. For further information, please contact the source cited above.

Journal Reference:

T. van der Sar, Z. H. Wang, M. S. Blok, H. Bernien, T. H. Taminiau, D. M. Toyli, D. A. Lidar, D. D. Awschalom, R. Hanson, V. V. Dobrovitski. Decoherence-protected quantum gates for a hybrid solid-state spin register. Nature, 2012; 484 (7392): 82 DOI: 10.1038/nature10900

Note: If no author is given, the source is cited instead.

Disclaimer: Views expressed in this article do not necessarily reflect those of ScienceDaily or its staff.

View the original article here