The post Quantum Computer Simulation: New World Record on JUGENE appeared first on HPCwire.

]]>The civil engineer Konrad Zuse was born in Berlin exactly 100 years ago. In 1941, he built the world’s first computer. And thanks to his pioneering work, the scientists at the Jülich Supercomputing Center have now succeeded in setting a world record by simulating the largest quantum computer system with 42 qubits. As yet, only small prototypes of quantum computers exist in laboratories, with a capacity of a few bits. This is now going to change.

Compared to the so-called quantum computers, today’s supercomputers would simply look old. A new project is aiming to catapult these impressive machines out of the realm of the hypothetical and into reality, or at least to raise the hope that such computers will not just be sketches on paper.

**Low value, large effect**

** **To understand the extent of the accomplishment, you have to grasp the underlying principle of a quantum system. “The computing power of a quantum computer grows exponentially with its size,” says Prof. Dr. Kristel Michielsen from the Jülich Supercomputing Center, and who heads the Institute for Advanced Simulation. “If a quantum computer is expanded by just one single computer bit, its computing power is immediately doubled due to the laws of quantum mechanics on which it is based.”

By contrast, the computing power of a classical computer only grows linearly with its components. Ten percent more transistors only means ten percent more performance, at best.

The qubit is still the smallest unit for quantum computers; however, they offer quite different possibilities. While the traditional 8-bit byte can represent 256 different values, quantum bytes have over 65,535 independent states. For computational operations, quantum computers use atoms and subatomic particles as transmission units. They are both the memory and the executing computational unit. This property would allow such a computer to perform computational operations simultaneously, to take on highly scientific tasks, and to control the cand decryption of data streams.

This last function is already no longer a secret in the world of cryptography. Since Phil Zimmermann placed his PGP encryption on the Internet with free access for everyone in 1991, anyone can easily encrypt their data stream. This cryptographic undertaking is naturally a thorn in the side of intelligence agencies because terrorists are also able to use it.

**JUGENE: Europe’s fastest supercomputer **

Of course, if you want to simulate a quantum computer using a traditional computer, you soon run up against limitations. For a 42-qubit simulation, you need machines like the Jülich supercomputer. JUGENE is the fastest computer in Europe with almost 300,000 processors and a computing power of one quadrillion floating point operations per second. One billion people would each have to perform one million calculations per second on a calculator to get anywhere near as fast as that. On this machine, scientists succeeded in running Shor’s algorithm, one of the most common test applications for quantum computers, with 42 computer bits factorizing 15,707 into 113×139. “The simulation can now factorize numbers that are about a thousand times larger than those previously possible with experimental quantum computers,” says Michielsen proudly.

The simulation was built by enhancing existing software. When so many processors work together, it may easily be the case that threads are waiting for each other, leading to performance loss. The Jülich software is optimized to allow thousands of processors to work together seamlessly. Codes like this are able to scale almost perfectly. Scaling is the term computer scientists use to describe the property of software such that it is able to convert processors into computational performance in a linear manner.

Jülich is also at the heart of the QPACE project (QCD Parallel Computing on the Cell). In the future, the supercomputer center will come into even “greater consideration” for larger projects involving several research institutes. An international consortium consisting of six German and Italian universities and research centers plans to calculate simulations in quantum chromodynamics (QCD), a field of elementary physics. QCD describes how protons are built up of quarks and gluons. The work in this field can also help increase the understanding of the the fundamental forces of the universe. Here too, IBM, or more precisely IBM’s research and development center in Böblingen, Germany, is also supporting the prototype of a research computer that can handle such simulations.

**Jülich’s red carpet **

The QPACE concept consists of a network of programmable components, the so-called “field programmable gate arrays” (FPGAs) that connect processors to a powerful, scalable research computer. The prototype is intended to reach a maximum performance of up to 200 teraflops. Due to the scalability of the network employed, it is theoretically possible to increase the performance up into the petaflop range.

But quantum physics is not only an issue at Jülich. Quantum research has long since been an international business. It was the Danes who, as it were, rolled out Jülich’s red carpet in 2008. Dr. Henrik Ingerslev Jørgensen from the Niels Bohr Institute in Copenhagen succeeded in getting qubits to interact with each other. His results gave the first glimpse into understanding the interaction of two electrons lying next to each other in carbon nanotubes, which are tiny tubes made up of graphite layers.

**A glance into the future **

“Quantum computers are still a fascinating vision – nothing more,” says Michael Malms, head of High Performance Computing at the German IBM research and development center in Böblingen. “But if we look at the technical evolution that has been successful in a relatively short time in the area of high performance computing and project that into the future, then we cannot exclude the possibility that quantum computers too will one day become a reality.”

No doubt Konrad Zuse would be amazed if he were able to look at the cutting edge of computing research today. And it’s not just quantum computing. Scientists at the Weizmann Institute of Science in Rehovot in Israel are conducting research into the possibility of using synthetic genetic “snippets” as software. Enzymes that read, split and join DNA form the hardware. Then based on the aggregate number of such “computers,” they are able to parallelize computations. About three trillion such molecular computers are packed into a drop of water, and since they work simultaneously, they can theoretically perform 66 billion operations per drop. Zuse would have loved to hear this “pitter-pattering” of computing.

**About the Author**

*Markus Henkel is a geodesist, science writer and lives in Hamburg, Germany. He writes about supercomputing, environmental protection and clinical medicine. For more information, email him at **info@laengsynt.de** or visit the Web site: **http://laengsynt.de**.*

The post Quantum Computer Simulation: New World Record on JUGENE appeared first on HPCwire.

]]>The post IBM Invents Short-Cut to Assessing Data Quality appeared first on HPCwire.

]]>In what IBM is characterizing as a “breakthrough,” researchers have developed an algorithm that cuts the computational costs of assessing data quality by two orders of magnitude. The idea is to bring uncertainty quantification within reach of present-day supercomputers and even much more computationally-modest machines. The new algorithm has potentially far-reaching applicability, extending to nearly all types of analytics applications as well as scientific modeling and simulation.

The development of the algorithm was performed at IBM Research – Zurich and was presented on Thursday at the Society for Industrial and Applied Mathematics conference in Seattle. The Zurich team has been working on the software for the last year-and-a-half and they were able to patent it at the end of 2009, prior to publishing the results. The announcement this week followed a demonstration on JuGene, the Blue Gene/P system at the Jülich Supercomputing Center in Germany.

In that experiment, 72 Blue Gene racks were used to validate nine terabytes of data in less than 20 minutes. According to IBM researchers, using conventional techniques, that analysis would have consumed more than a day, and in the process, used 100 times as much energy. A sustained performance of 730 teraflops, representing 73 percent of theoretical peak, was demonstrated on the Blue Gene/P machine, and similar or even better efficiencies would be expected on smaller clusters and workstations.

The impetus behind this work is the flood of data that is fed to computers to solve real-world problems — everything from stock portfolio management to computational fluid dynamics. The data can be generated from physical sources, like financial market feeds, weather sensors, electrical grid measurement devices, and Internet streams, as well as from synthetic sources like computer models. “Essentially we live in an ocean of bits and bytes,” says Costas Bekas of IBM Research – Zurich.

The idea, of course, is to employ computers to transform all this raw data into valuable knowledge. But before that, you have to figure out how good the data is, so that the results are trustworthy. And since the collection and generation of all this information is never error-free, one must find a way to quantify all the noise and anomalies in the data.

Statistical techniques to characterize data quality have been around for a while and come under the general term *uncertainty quantification*, or UQ, for short. There are a number of methods employed for UQ analysis, including the well-known Monte Carlo technique. But one of the most powerful ones uses something called inverse covariance matrix analysis. The problem with this method is that as data sizes grow, the computational cost becomes impractical, even for the most powerful systems. For example, Bekas says a sample of one million data samples would require an exaflop of compute power. That’s roughly 1,000 times the performance of the top petaflop supercomputing systems that exist today. To compensate, people have been manually “remodeling” the data and reducing the size of the problem, but this introduces the element of human bias into the analysis.

The overarching goal of the research was to make UQ practical, not just for elite scientists on supercomputers, but for average users on computing clusters and even personal computers. And because they wanted to cover the whole range of hardware platforms, they needed to design the algorithm so that it would be highly scalable as well as fault tolerant.

The solution the IBM’ers came up with was to replace the inverse covariance matrix method with one using stochastic estimation and iterative refinement. This enabled the researchers to cast the problem as a linear system. “The key is that the number of linear systems that we solve is small,” explains Bekas. “So if you have, say, one million data samples, then you only have to solve 100 linear systems.”

According to Bekas, this model not only enabled them to parallelize the technique, but to reduce the computational cost by a factor of 100. In addition, the algorithm employs a mixed precision scheme such that the main computation can take place in single precision (or even lower), but generate results in double precision (or even higher). While most modern CPUs can’t take advantage of this particular trick, computational accelerators, like Cell processors, GPUs, and presumably even FPGAs, can use this feature to optimal effect.

Fault tolerance is a by-product of the stochastic estimation model. “If for example something goes wrong in your machine while it is solving one of the linear systems, you can safely ignore it and you can go on to the next one,” says Bekas. “On the other hand, if you were to do full matrix inversion [and] something went wrong at the end of a very large matrix calculation, then your data is destroyed.” The technique maintains accuracies of three, four, or even five digits, which according to him, far exceeds what is required for applications.

Now that IBM’s intellectual property related to the algorithm has been patented and the technology is out of the experimental stage, the next step is to begin commercialization. There is no dearth of potential applications: weather forecasting, supply chain management, nuclear weapons simulation, astrophysics, magnetic resonance imaging, and all kinds of business intelligence — essentially any analytics or modeling application where data quality is a driving issue. Perhaps the lowest-hanging fruit is financial portfolio analysis, where exposure to risk is at the very heart of the application. IBM has a Business Analytics and Optimization group within their consulting organization ready to start client engagements.

“You’d be surprised to see how many different disciplines rely on the same basic mathematical problems,” says Bekas. “And this uncertainty quantification is one of them.”

The post IBM Invents Short-Cut to Assessing Data Quality appeared first on HPCwire.

]]>