Lifeboat Foundation

Eurolab HPC tries to assess the future disruptive technology for high performance computing beyond Exascale computers.

They survey the currents state of research and development and its potential for the future of the following hardware technologies:

CMOS scaling
Die stacking and 3D chip technologies
Non-volatile Memory (NVM) technologies
Photonics
Resistive Computing
Neuromorphic Computing
Quantum Computing
Nanotubes
Graphene and
Diamond Transistors

Continue reading “Beyond Exaflop supercomputers will require new materials, new architectures, new memory and quantum computers” »

Machines enrich and enhance our lives, whether it’s the smartphones that allow us to stay connected or the supercomputers that solve our toughest computational problems. Imagine how much more productive and innovative our world will be when computers become infinitely more powerful. Indeed, the growing field of quantum computing may make our current technological capacities look feeble and primitive in comparison. It could even transform the workings of the human brain and revolutionize how we think in ways we can’t begin to imagine.

Today, computers operate at the most basic level by manipulating two states: a zero or a one. In contrast, quantum computers are not limited to two states, but can encode information in multiple states that exist in superposition, also known as quantum bits or qubits.

Continue reading “This Is Your Brain on Quantum Computers” »

Scientists all around the world are working towards making the quantum computing a reality for past few years as it will bring another revolution in the world of technology. Quantam computers are thousands of times faster and way smaller than the conventional computing devices as they use photons to do computing and are also compatible with fibre optics.

A team of researchers from the University of Innsbruck in Austria claims that they have invented world’s first scalable quantum computer. Although the device is still several years behind coming to reality but still scientists consider it as a giant leap towards bringing quantum computers into people’s hands.

From hypothetical models in last decade to practical models now is promising. Former Microsoft CEO Bill Gates believes that we will make quantum computers by next decade. This promising, complex technology may soon amplify the capabilities of today’s computers, which will greatly benefit science and business organizations by helping them work faster and more efficiently. Quantum computers are next step of computers and they can solve problems with ease which are nearly impossible for computers and supercomputers of current generation.

Continue reading “First ever scalable quantum computer developed by scientists” »

IBM delivered on the DARPA SyNAPSE project with a one million neuron brain-inspired processor. The chip consumes merely 70 milliwatts, and is capable of 46 billion synaptic operations per second, per watt–literally a synaptic supercomputer in your palm.

Along the way—progressing through Phase 0, Phase 1, Phase 2, and Phase 3—we have journeyed from neuroscience to supercomputing, to a new computer architecture, to a new programming language, to algorithms, applications, and now to a new chip—TrueNorth.

Fabricated in Samsung’s 28nm process, with 5.4 billion transistors, TrueNorth is IBM’s largest chip to date in transistor count. While simulating complex recurrent neural networks, TrueNorth consumes less than 100mW of power and has a power density of 20mW / cm².

Continue reading “IBM Neuromorphic chip hits DARPA milestone and has been used to implement deep learning” »

If all goes according to the plan, tech giant Google might be able to present the world with a phenomenally powerful quantum computer by the end of 2017.

Googler John Martinis and his team of researchers have been working on how quantum computers could be worked out for a long duration of 30 years. And now, it seems, they’re finally on the verge of making the wonder computer a reality. Since the computer would harness the unusual properties of quantum physics that take birth in extreme circumstances like those on the ultra-cold chip, the wonder computer would allow a Google coder to run the calculations he/she requires in a short interval of time like in the duration of a tea/coffee break. This would be quite impressive as the supercomputers of today would take millions of years to run the same calculations. This means, the quantum computer would be able to outperform conventional computers—a concept known as quantum supremacy. But, the Google software, which has been developed on ordinary computers to answer questions or drive cars, is still capable of becoming more intelligent.

http://www.unz.com/akarlin/sinotriumph/

Nothing illustrates China’s meteoric rise as some well chosen numbers.

By the end of the 1990s, China had come to dominate the mainstays of geopolitical power in the 20th century – coal and steel production. As a consequence, it leapt to the top of the Compositive Index of National Capability, which uses military expenditure, military personnel, energy consumption, iron and steel production, urban population, and total population as a proxy of national power. Still, one could legitimately argue that all of these factors are hardly relevant today. While Germany’s fourfold preponderance in steel production over Russia may have been a critical number in 1914, China’s eightfold advantage in steel production over the US by 2014 is all but meaningless in any relevant comparison of national power. The world has moved on.

Continue reading “China Overtakes US in Scientific Articles, Robots, Supercomputers” »

Brain is the most complex biological computing system and performs almost every activity with jet speed and precision. Despite the numerous advancements in the interaction of technology and science, there is no machine that functions as swift as a brain. Nevertheless, the recent experiment by the researchers of Okinawa Institute of Science and Technology Graduate University in Japan and Forschungszentrum Jülich in Germany is a milestone in the history of producing human brain simulations by a computer.

The team of researchers from Japan and Germany have managed to produce the most accurate simulation of a human brain in Japan’s computer. The single second worth of activity in the human brain from just one percent of the complex organ was able to be produced in 40 minutes by the world’s fourth largest computer.

The computer used is the K computer in Japan to simulate human brain activity. The computer has 705,024 processor cores and 1.4 million GB of RAM, but still took 40 minutes to crunch the data for just one second of brain activity. The open-source Neural Simulation Technology (NEST) tool is used to replicate a network consisting of 1.73 billion nerve cells connected by 10.4 trillion synapses.

Continue reading “Supercomputer Simulates One Second of Human Brain” »

This new computer system is 100 billion times more energy efficient than the most energy efficient conventional green supercomputer. Using only links and rotary joints, this “molecular mechanical computer” removes the need for parts that create friction and generate heat.

The trend for computing, and for technology in general, really consists of just one word: Smaller. Previously, technology that could fit on your desk was the rage. Then it became tech that fit in your bag. Then the palm of your hand. Now, scientists are playing with even smaller technology, down to the molecular size.

Scientists have developed a computer system that can, theoretically, be 100 billion times more energy efficient than the most energy efficient conventional green supercomputer. Using only links and rotary joints, this “molecular mechanical computer” removes the need for gears, clutches, switches, springs, and other parts that create friction and generate heat.

Continue reading “New Molecular Mechanical Computer Design is 100 Billion Times More Energy Efficient” »

The Elon Musk-backed OpenAI project became Nvidia’s first ever customer to buy a DGX-1 “AI supercomputer in a box.” The system can deliver up to 170 teraflops of performance, which should enable the OpenAI team to significantly improve their AI research.