Manufacturing Bits: March 29


Brain-inspired computing Lawrence Livermore National Laboratory (LLNL) has purchased a brain-inspired supercomputing platform for deep learning developed by IBM Research. Based on a neurosynaptic computer chip called IBM TrueNorth, the scalable platform will process the equivalent of 16 million neurons and 4 billion synapses. It will consume the energy equivalent of a tablet computer. ... » read more

Power/Performance Bits: March 29


Photonic-phononic circuit Researchers at the National Institute of Standards and Technology (NIST) developed a piezo-optomechanical circuit that converts signals among optical, acoustic and radio waves. At the heart of the piezoelectric optomechanical circuit is an optomechanical cavity, which consists of a suspended nanoscale beam. Within the beam are a series of holes that act like a ha... » read more

System Bits: March 22


How nanocrystal structures self assemble Researchers at MIT and the Cornell High Energy Synchrotron Source (CHESS) have discovered some of the secrets to a long-hidden magic trick behind the self-assembly of nanocrystal structures, the understanding of which could be used to create more vivid display screens and optical sensory devices. The transformation of simple colloidal particles — b... » read more

Manufacturing Bits: March 22


Tunable windows Harvard University has put a new twist on tunable windows. Researchers have devised a new manufacturing technique that can change the opacity of a window. With the flip of a switch, the window can become cloudy, clear or somewhere in the middle. Tunable windows, which aren’t new, rely on electrochemical reactions. Typically, the glass is coated with materials using vacuum... » read more

Power/Performance Bits: March 22


Superconducting memory A group of scientists from the Moscow Institute of Physics and Technology and the Moscow State University developed a fundamentally new type of memory cell based on superconductors, which they believe will be able to work hundreds of times faster than memory devices commonly used today. The basic memory cells are based on quantum effects in "sandwiches" of supercond... » read more

System Bits: March 15


Drilling into metabolic details with big data In a development that may help researchers find new therapeutic targets for cancer and other diseases, Rice University researchers have created a fast computational method to model tissue-specific metabolic pathways. The team explained that metabolic pathways are immense networks of biochemical reactions that keep organisms functioning and are a... » read more

Manufacturing Bits: March 15


More multi-beam The multi-beam e-beam market is a hot topic. For example, Intel is quietly in the process of acquiring IMS Nanofabrication, a developer of multi-beam e-beam tools for mask writing applications. Meanwhile, at the recent SPIE Advanced Lithography conference, Mapper Lithography disclosed new upgrades for its multi-beam e-beam tool for use in direct-write lithography application... » read more

Power/Performance Bits: March 15


Magnetic computing Engineers at the University of California, Berkeley, demonstrated that magnetic chips can operate with the lowest fundamental level of energy dissipation possible under the laws of thermodynamics. "We wanted to know how small we could shrink the amount of energy needed for computing," said Jeffrey Bokor, a UC Berkeley professor of electrical engineering and computer sci... » read more

System Bits: March 8


Living, breathing supercomputers Adenosine triphosphate (ATP), the substance that provides energy to all the cells in the human body, may also be able to power the next generation of supercomputers, according to McGill University researchers. The team has described a model of a biological computer that they have created that is able to process information very quickly and accurately using p... » read more

Power/Performance Bits: March 8


Configurable analog chip Researchers at Georgia Tech built a new configurable computing device, the Field-Programmable Analog Array (FPAA) SoC, that uses analog technology supported by digital components and can be built up to a hundred times smaller while using a thousand times less electrical power than comparable digital floating-gate configurable devices. Professionals familiar with F... » read more

← Older posts Newer posts →