China's Supercomputer Regains No. 1 Ranking - ScienceInsider

China's Supercomputer Regains No. 1 Ranking - ScienceInsider

China has regained the top spot on a list of the world's most powerful supercomputers. The latest version of a semiannual ranking posted yesterday shows that Tianhe-2, built by China's National University of Defense Technology, was clocked at 33.86 petaflops (a petaflop is a thousand trillion floating point operations per second). That's nearly twice as powerful as the 17.59 pflops performance of Titan, a supercomputer at Oak Ridge National Laboratory in Tennessee, which led the previous Top 500 list put out by a team of supercomputer researchers in the United States and Germany.


Tianhe-2 marks the second time a Chinese machine has been a world-beater. Tianhe-1 grabbed the top spot in November 2010 before relinquishing it 6 months later to Japan's K computer. China's second ascent demonstrates the country's sustained commitment to funding high performance computing, says Jack Dongarra, a computer scientist at the University of Tennessee, Knoxville, who closely follows international supercomputing trends. "It shows no signs of changing, only increasing," Dongarra says about China's investment in supercomputing.

The United States remains the overall supercomputing leader, with 252 of the top 500 systems. But China is in second place, with 66 machines. Japan, the United Kingdom, France, and Germany fill out the top six, with 30, 29, 23, and 19 systems, respectively.

Source: Science Insider

IT security in 2030 – only humans will be the same

Twenty-three years ago one of the major hacker attacks in the history of the US was widely reported in the media. In this context, Clifford Stoll published his book The Cuckoo’s Egg, which has gone on to become a classic of IT literature. In the same year Tim Berners-Lee invented the World Wide Web, Intel launched its brand new 486 processor with 25 MHz, and the Berlin Wall fell. Back then, though, computing was the preserve of small communities of much-ridiculed geeks, so 1989 remained in the collective memory as the year the Wall came down. Everything else was immediately forgotten.
More than two decades later, computers have not only become socially acceptable but, thanks to Apple, they are even status symbols. These days anyone going to a library for information, transferring money at a bank counter, or exchanging traditional “snail mail” business letters, normally does so as a private individual: in our professional environment it is almost impossible to avoid the use of search engines, online banking and email.
What long-term impact will this development have on our lives? It is clear that any attempt to predict the IT security landscape in 2030 will have to be a forecast of security and society in general. IT is now almost everywhere, and its scope will only increase in the future.

Taking great steps towards the future

Future generations will pinpoint 2012 as the year where the hegemony of the traditional personal computer was ended – ironically by the very company that was once inseparably connected with it – Microsoft. Like Apple and Google, the Windows giant is also now opting for a multiple-device approach: cell phones, tablets and increasingly television sets with a built-in operating system are all steadily challenging the PC’s traditional dominance. Online cloud storage instead of a hard drive in the desktop computer, applications from the App Store instead of downloads from dubious websites – times are changing, just as surely as analogue cameras have been superseded by digital devices. Gradually, more sophisticated camera phones are in turn replacing these. There is no doubt that analogue films, digicams and PCs will still exist in ten years’ time, but their heyday is past. Against this background, it would hardly be surprising if smartphones lost their current cachet as the must-have techie toy within the next five years, because augmented reality glasses are now the up and coming thing.
These are special optical aids – including a built-in camera, display and computer. The special feature of augmented reality is that for the wearer reality and computer-generated images merge together. Thanks to a continuously activated camera and the face recognition function, a poor memory for names won’t be a problem any longer as the name, age and profession of the person we are talking to will be automatically displayed next to his or her face. On holiday, foreign-language menus will simply be replaced by a translated version. And if you get lost, you can use the pedestrian navigation system to virtually project your path onto the pavement in front of you. Additionally, a multimedia diary based on the continuous data flow of the camera, the microphone and GPS will automatically be created. No need to be impatient: in 2013, Google plans to deliver its Google Glasses to developers, and other manufacturers will follow. This fusion of the real and the virtual world will change so many things in the coming years that we simply cannot overestimate the importance of this development.
But when it comes to technology, there is always a dark side: if millions of people walk around with cameras permanently activated, nothing outside their own houses will remain private. Society will monitor itself and it remains to be seen if and how a balance between technology and privacy can be maintained. Automatic deactivation of cameras at particular places is an option for which Apple has already filed a patent.
Another problem: even the sharpest minds can only use the information at their disposal. Seeing is believing, as the saying goes. Just imagine an activated augmented reality feature tricking you into thinking that the restaurant you were going to visit was infested with cockroaches – you’re going to go to the establishment across the street instead, aren’t you? We’ve already seen how these “opinions” can be manipulated by paid “customers” in relation to hotel ratings on the Internet – but we still get tricked. So the advertising industry itself will be particularly interested in “optimizing” our reality to suit its agenda. It really would be dangerous if the system as a whole were hacked without the person concerned realizing that he or she is living in a dream world which has nothing to do with reality.
Of course, the future involves much more than just augmented reality. But even when putting aside fascinating future topics such as nanotechnology, genetic research or food-producing 3D printers, you certainly won’t be bored: the much-heralded Artificial Intelligence is closer than ever to becoming reality. In 1997, IBM’s Deep Blue defeated the Russian Garry Kasparov 3.5-2.5 (the chess world champion had managed to win the previous match played the year before) – but its success was based on enormous processing power rather than true intelligence. Nevertheless, in 2001, IBM launched the amazing Watson computer that managed to trump a 74 times Jeopardy winner in a quiz game. This victory was due to the language processing technology that has been perfected over the years and to algorithms capable of independently gaining new findings on the basis of existing data. In the same year, Apple presented Siri, an imperfect but nonetheless trend-setting digital assistant. As expected, Google has joined the scramble to develop the smartest computer system. In parallel, a number of other projects have been initiated – partly supported by EU funds – whose objective is to emulate a complete human brain in a computer. Whether they are creating digital assistants or artificial brains, researchers have the will and the financial backing to complete this long journey.
Ultimately, we are looking at nothing less than the complete autonomization of our environment: cleaning robots, cars, even houses. We’ve already seen the Google Car obtain a license in the state of Nevada this year, making it the first ever motor vehicle to be recognized as capable of driving itself without human input. There have also been great advances in the field of robotics research: recently, the US agency DARPA demonstrated a robot known as the Cheetah, which runs at 45 km/h, i.e. faster than any human being. When these robots can be animated by genuine artificial intelligence, those visions we’ve seen in sci-fi films could start to become reality. Whether you look forward to all this or it just makes you shudder is up to you!

Everything changes

Discontinued model	Solution for the future
Television, PCs, laptops, tablets and smartphones	Augmented reality glasses and displays available everywhere – from watches to monitor walls
Software, movies, music bought ‘in a box’	Cloud-based content, charge according to frequency of use
Video game consoles	Virtual play worlds which can be entered from any computer system
Manually controlled cars	Fully automated transport systems
Cash	Digital payment systems
School	Individualized teaching by intelligent systems, perfectly tailored to students’ individual skills
Workers	Robots

The world in 2030

So, what will life in the future look like? Augmented reality devices will mostly replace today’s ultra-popular smartphones. Overwhelming progress in directly connecting computer chips and optical nerves will enable blind people to access augmented reality. And the most popular videos in the YouTube of the future will be self-made 3D movies – including unlimited viewing angles and freely focusable depth range. Traditional game consoles will disappear. Instead, virtual universes will be computed by huge computer systems distributed across numerous cities – partly located down in the basements of big apartment buildings to keep transmissions paths as short as possible. It’s a great opportunity, if you can create play worlds which are interesting enough to persuade other players to join up and pay a subscription or joining fee.
Extremely powerful computers are required for all this. The rule of thumb is: the smaller the transistors in a processor the better the speed. With every further step towards miniaturization, Intel and co. are approaching the limits of what is physically feasible. In the past, though, processor developers have repeatedly demonstrated their creativity, and a massive increase of the core number on every chip could also be an option. At present, the processing performance of computers is expected to double every 18 months, while the price remains the same. This would mean that in 18 years’ time, computers would be four thousand times faster than those of the machines available today. In theory, home computers could be more powerful than that IBM Watson supercomputer (for the techies: 2880 Power7-cores featuring 3.55 GHz each), at a cost comparable to an ordinary laptop today. It would be possible to create the first Toy Story film on a home desktop, in real time and at cinema resolution, and the first-ever complete computer simulation of the simplest known genome Mycoplasma Genitalium, celebrated just a few months ago as a scientific milestone, would be a standard experiment conducted in school classrooms.
The quantum computer technology we hear so much about is also expected to have matured by 2030. Considering the present state of knowledge, it won’t be possible to solve every typical computer problem using a handful of quantum bits, but the cracking of strong RSA encryption (applied for instance to provide security for emails and online-banking transactions) could have become reality twenty years from now.
It seems certain, however, that rootkits, Trojans and phishing attacks will continue to be serious problems over the coming years, with attackers concentrating more on servers than on devices. This is because more vulnerabilities appear in complex environments and it is reasonable to assume that the operating systems of tablets and smartphones will be “purged” within the next few years and that the bulk of the coding will be shifted into the cloud – and thus onto the server side.
It is, of course, not just the financial implications of the computer viruses of the future that are serious. The detection of the sabotage worm known as Stuxnet in 2010 confirmed suspicions that malware could also have a political context. The continuous militarization of cyberspace will produce legions of professional malware authors as the creation of Trojans and the carrying out of web attacks is legitimized and even supported by some states.

Singularity

As suddenly as this trend has emerged, its end may not be far off – humans working to create new security threats could be superseded by machines fighting against machines. This is where the progress of artificial intelligence could be crucial. The magic word is “singularity”, used in future studies to describe the point in time when computers will be sufficiently intelligent to develop independently without human support. It sounds incredible and there is still huge controversy among scientists about when – or indeed if – we will reach this point. I don’t want to bore you and duck the question: my guess is that it will arrive in 10-15 years.
Even today it is difficult for us to keep pace with the breathtaking speed of new developments. But when singularity is achieved, the pace will accelerate significantly yet again: it’s as if prehistoric man had discovered fire at breakfast, had been catapulted into the Middle Ages by lunch time, witnessed the industrial revolution in the afternoon and then arrived in the computer age by the evening!
Our minds, as well as our senses, developed over millions of years by the gentle hand of evolution, will be suddenly exposed in one blink of history’s eye to technologies that are generations ahead of our biological development.
Now, there’s nothing bad about technical aids, though our ancestors certainly took advantage of the illiterate once written language had been invented. In recent years, search engines and services like Wikipedia have pushed information processing forward. But one thing still applies: it is man who holds the ropes, while the computer lends its technical horsepower to the task at hand. If, though, we allow our lives to be entirely optimized through digital assistance systems, that balance of power will be reversed. Every attempt to return control to the human mind will inevitably cause efficiency losses.
After a certain point, intelligent systems could become so superior to us that we would no longer be able to grasp the mechanisms and reasons underlying the advice they gave us. We would resemble infants who trust their mothers blindly because they have no other option. The difference, though, is that a child grows and will, as an adult, finally be able to stand on his or her own feet. Humanity could be dependent on the assistance of computers for the rest of our lives.
Even if the next few years are relatively calm, we need to start thinking now about how to deal with these developments. How should researchers react to a breakthrough in artificial intelligence? When all is said and done, a highly intelligent system could be abused as a weapon. Developing nuclear devices is forbidden to the average citizen by international treaties – but building an all-powerful intelligence at home will present the creators with no legal problems at all and regulating them will probably be impossible. Let’s just hope that the lucky creator of the first genuine artificial intelligence will not immediately decide to go for world supremacy!
Another challenge is how to deal with the truth: we expect computers to be absolutely objective. If a head of state was just told that he is wrong in front of his people and asked if he would kindly resign – would he accept? Or will we force computers to adopt our “truths” against “their” better judgment? In such a world, we would not need antivirus software but psychologists as the compulsory processing of contradictory information can only lead to digital psychosis – remember the film 2001: A Space Odyssey?

Common sense

The future holds exciting opportunities, but there are also lots of risks and our own weaknesses, in particular, will play a major role. In the 1950s, scientists Peter Milner and James Olds experimented on rats with electrodes implanted in their brains’ “pleasure centers” – if these animals were offered the chance to stimulate themselves at the push of a button they continued doing that until they died of complete exhaustion. On a computer-controlled planet, neither clocking in nor job centers would exist. Everybody would be free to realize his or her own dreams and talents. Depending on our self-discipline, a world full of artists, athletes and writers might emerge – or, on the contrary, a sad little heap of lethargic couch potatoes!
When I am asked in interviews how people can best protect themselves against Internet threats, I always emphasize – apart from technical solutions – the importance of common sense. And if common sense ever fails, we can only hope at least that the computers will keep cool heads!

The biggest opportunities and dangers of our digital future

Technology	Utopia	Dystopia
Singularity	Living in paradise – everybody does what he likes – machines handle the rest.	The last world war could have been won by a laptop that only “acted under orders” – or which classified humanity as a whole as a risk to security.
Intelligent infrastructures	Traffic flows, logistics – everything is perfectly coordinated, thus preserving resources and also the environment.	In case of a malicious attack, cities could be cut off from food supplies, citizens held hostage in their houses, and the doors of prisons opened.
Digital life coaches	Personal all-around advice: never again forgetting appointments or wasting time with paperwork.	Complete technology dependence and thus the associated risk of leading heteronomous lives because of manipulated data.
Medical robots	Cheaper operations, reduced risks of medical malpractice and wrong diagnosis, no waiting times at the doctor’s surgery.	Loss of expert knowledge as medical education will be financially less attractive. Cases of death resulting from hacked systems.
Military robots	The advantages are obvious – for those who have the more powerful robots.	If, in the event of war, you have no fear of human losses on your own side, then the threshold for starting an aggressive war will be lower.
Augmented Reality	We extend our perceptive abilities and gain new insights into ourselves by continuous life logging.	Total loss of privacy and dependence on computerized prostheses in the long run.
Cashless payment solutions	Shopping becomes more convenient. Tax fraud becomes impossible so the tax burden is distributed fairly and equitably.	Abandoning cash entirely means, in the event of a computer breakdown, no standardized medium of exchange would be available.
Quantum computers	The opening of amazing perspectives, especially in the field of science, e.g. in the simulation of chemical elements.	Quantum computing could pose a serious threat to some encryption technologies such as RSA.

The German version of this article was originally published on the 10th of December 2012 in the book “Vision 2030” (GABAL publishing house)

Source: Securelist

Sequoia Supercomputer

Lawrence Livermore’s Sequoia Supercomputer Towers above the Rest in Latest TOP500 List

Thu, 2012-06-14 13:28

MANNHEIM, Germany; BERKELEY, Calif.; and KNOXVILLE, Tenn.—For the first time since November 2009, a United States supercomputer sits atop the TOP500 list of the world’s top supercomputers. Named Sequoia, the IBM BlueGene/Q system installed at the Department of Energy’s Lawrence Livermore National Laboratory achieved an impressive 16.32 petaflop/s on the Linpack benchmark using 1,572,864 cores.

Sequoia is also one of the most energy efficient systems on the list, which will be released Monday, June 18, at the 2012 International Supercomputing Conference in Hamburg, Germany. This will mark the 39th edition of the list, which is compiled twice each year.

Complete information on the trends indicated by the latest list, as well as the complete list, can be found on the TOP500 website.

On the latest list, Fujitsu’s “K Computer” installed at the RIKEN Advanced Institute for Computational Science (AICS) in Kobe, Japan, is now the No. 2 system with 10.51 Pflop/s on the Linpack benchmark using 705,024 SPARC64 processing cores. The K Computer held the No. 1 spot on the previous two lists.

The new Mira supercomputer, an IBM BlueGene/Q system at Argonne National Laboratory in Illinois, debuted at No. 3, with 8.15 petaflop/s on the Linpack benchmark using 786,432 cores. The other U.S. system in the Top 10 is the upgraded Jaguar at Oak Ridge National Laboratory in Tennessee, which was the top U.S. system on the previous list and now clocks in at No. 6.

The newest list also marks a return of European systems in force. The most powerful system in Europe and No.4 on the List is SuperMUC, an IBM iDataplex system installed at Leibniz Rechenzentrum in Germany. Another German machine, the JuQUEEN BlueGene/Q at Forschungszentrum Juelich, is No. 8.

Italy makes its debut in the Top 10 with an IBM BlueGene/Q system installed at CINECA. The system is at No. 7 on the list with 1.72 Pflop/s performance. In all, four of the top 10 supercomputers are IBM BlueGene/Q systems. France occupies the No. 9 spot with a homegrown Bull supercomputer.

China, which briefly took the No. 1 and No.3 spots in November 2010, has two systems in the Top 10, with Tianhe-1Aat the National Supercomputing Center in Tianjin in No. 5 and Nebulae at the National Supercomputing Centre in Shenzhen No. 10.

Total performance of all the systems on the list has increased considerably since November 2011, reaching 123.4 Pflop/s. The combined performance of the last list was 74.2 Pflop/s. In all, 20 of the supercomputers on the newest list reached performance levels of 1 Pflop/s or more. The No. 500 machine on the list notched a performance level of 60.8 teraflop/s, which was enough to reach No. 332 just seven months ago.

A look at processors

A total of 372 systems (74.4 percent) are now using Intel processors, down from 384 systems (76.8 percent) on the last list. Intel is now followed by the AMD Opteron family with 63 systems (12.6 percent), same as in the in the previous list. The share of IBM Power processors has increased from 49 to 58 systems (11.6 percent).

58 systems use accelerators or co-processors (up from 39 six months ago), 53 of these use NVIDIA chips, two use Cell processors, two use ATI Radeon and there is one new system with Intel MIC technology.

The top vendors

IBM kept its lead in systems and has now 213 systems (42.6 percent) compared to HP with 138 systems (27.6 percent). HP is slightly down from 141 systems (28.2 percent) seven months ago, compared to IBM with 223 systems (44.6 percent). In the system category, Cray, Appro, SGI and Bull follow with 5.4 percent, 3.6 percent, 3.2 percent, and 3.2 percent respectively.

IBM remains the clear leader in the TOP500 list in performance and considerably increased its share with 47.5 percent of installed total performance (up from 27.3 percent). HP is second with 10.2 percent down from 13.1 percent. Due to the impressive performance of the No. 1 K Computer, Fujitsu follows closely in the third spot with 9.9 percent, down from 14.7 percent. Cray follows in fourth place in this category with 8.9 percent, down from 14.3 percent.

Where are they now?

The U.S. is clearly the leading consumer of HPC systems with 253 of the 500 systems (down from 263). The European share (107 systems – up from 103) is still lower than the Asian share (121 systems – up from 118). Dominant countries in Asia are China with 68 systems (down from 74), Japan with 34 systems (up from 30). In Europe, UK, France, and Germany, are almost equal with 25, 22, and 20 respectively.

About the TOP500 List

The TOP500 list is compiled by Hans Meuer of the University of Mannheim, Germany; Erich Strohmaier and Horst Simon of Lawrence Berkeley National Laboratory; and Jack Dongarra of the University of Tennessee, Knoxville.

Source: Top 500 Supercomputer Sites

World's Fastest Computer Gets an Upgrade, Breaks Its Own Record

By James Mulroy, PCWorld    Nov 7, 2011 11:05 PM

The world's fastest computer, the "K" supercomputer by Fujitsu and RIKEN, will keep its title as by breaking its own speed record. How much number-crunching power are we talking about? It completely smashes the processing power of the world's second- through eight-fastest supercomputers combined, coming in at an astounding 10.51 petaflops. That thoroughly crushes the old record of 8.162 petaflops.

Fujitsu--an information technology company--and RIKEN--a large research institute in Japan--upgraded their K supercomputer with an additional 19,584 CPUs, allowing it to break its own world speed record in the number of calculations the computer can perform per second. The new record is an astounding 10.51 quadrillion calculations per second.

According to Fujitsu the letter "K," the name of the computer, "comes from the Japanese Kanji letter 'Kei' which means ten peta or 10 to the 16th power", or quadrillions of calculations per second. A "FLOP" is the number of floating-point operations per second; in layman's terms, it's the number of instructions the computer can process in a single second. Now that K reached10 petaflops, it holds true to its name.

The supercomputer became the world's fastest back in June 2011, replacing the Tianhe-1A at theNational Supercomputing Center in Tianjin which comes in at a mere 2.51 petaflops. The K supercomputer uses 88,128 SPARC64 VIIIfx CPUs across 864 computing racks. In June, it only (relatviely speaking) had 68,544 CPUs across 672 computing racks.

Source: GeekTech - PC World US

New Ways of Thinking - IBM SyNAPSE

Beyond machines
For more than half a century, computers have been little better than calculators with storage structures and programmable memory, a model that scientists have continually aimed to improve.
Comparatively, the human brain—the world's most sophisticated computer—can perform complex tasks rapidly and accurately using the same amount of energy as a 20 watt light bulb in a space equivalent to a 2 liter soda bottle.


Cognitive computing: thought for the future
Making sense of real-time input flowing in at a dizzying rate is a Herculean task for today's computers, but would be natural for a brain-inspired system. Using advanced algorithms and silicon circuitry, cognitive computers learn through experiences, find correlations, create hypotheses, and remember—and learn from—the outcomes.
For example, a cognitive computing system monitoring the world's water supply could contain a network of sensors and actuators that constantly record and report metrics such as temperature, pressure, wave height, acoustics and ocean tide, and issue tsunami warnings based on its decision making.


Meeting of the minds
Researchers at IBM have been working on a cognitive computing project called Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE). By reproducing the structure and architecture of the brain—the way its elements receive sensory input, connect to each other, adapt these connections, and transmit motor output—the SyNAPSE project models computing systems that emulate the brain's computing efficiency, size and power usage without being programmed.
IBM is combining principles from nanoscience, neuroscience and supercomputing as part of a multi-year cognitive computing initiative. The Defense Advanced Research Projects Agency (DARPA) has awarded approximately US$21 million in new funding from for phase 2 of the SyNAPSE project. For this project, a world-class, multi-dimensional team has been assembled, consisting of IBM researchers and collaborators from Columbia University; Cornell University; University of California, Merced; and University of Wisconsin-Madison.