News Posts matching #MIT

Return to Keyword Browsing

Researchers Build a CPU Without Silicon Using Carbon Nanotubes

It is no secret that silicon manufacturing is an expensive and difficult process which requires big investment and a lot of effort to get right. Take Intel's 10 nm for example. It was originally planned to launch in 2015, but because of technical difficulties, it got delayed for 2019. That shows how silicon scaling is getting more difficult than ever, while costs are rising exponentially. Development of newer nodes is expected to cost billions of Dollars more, just for the research alone and that is not even including the costs for the setting up a manufacturing facility. In order to prepare for the moment when the development of ever-decreasing size nodes becomes financially and physically unfeasible, researchers are exploring new technologies that could replace and possibly possess even better electrical properties than silicon. One such material (actually a structure made from it) is Carbon Nanotube or CNT in short.

Researchers from MIT, in collaboration with scientists from Analog Devices, have successfully built a CPU based on RISC-V architecture entirely using CNTs. Called RV16X Nano, this CPU is currently only capable of executing a classic "Hello World" program. CNT is a natural semiconductor, however, when manufactured, it is being made as a metallic nanotube. That is due to the fact that metallic nanotubes are easier to integrate into the manufacturing ecosystem. Its has numerous challenges in production because CNTs tend to position themselves randomly in XYZ axes. Researchers from MIT and Analog Devices solved this problem by making large enough surfaces so that enough random tubes are positioned well.

It Does Matter How You Spin it - Spintronics Could be Answer to Future Semiconductor Technologies

It's only a matter of time before microchip production as we know it disappears entirely, at least for leading-edge tech designs. Either via new materials applied to trusted techniques (such as carbon coating/nanotubes) or entirely new and exotic fabrication technologies, we're rapidly approaching the limits of traditional silicon-based microchips. One solution to the problem, as it stands, might be found in spintronics - an interesting concept which bases processing and data retention not simply on whether current is being applied to a given transistor (as is the case for current silicon chips), but on a property of electrons called spin. Crucially, changing the magnetic orientation of electrons requires but a single charge, instead of a continued supply of power - which allows for much lower power consumption and heat output, two of the encroaching, limiting factors for the usual chips.

MIT Researches Find a New Way to Fix Spectre and Meltdown, Isolation Is Key

The Meltdown and Spectre vulnerabilities have been a real nightmare throughout this year. Those affected were quick (maybe too much) to mitigate the problems with different solutions, but months later even the most recent Intel chips aren't completely safe. Hardware fixes only work for certain Meltdown variants, while the rest are still mitigated with firmware and OS updates that have certain impact on performance.

Intel will have to redesign certain features on their future processors to finally forget Meltdown and Spectre, but meanwhile others have jumped to give some options. MIT researchers have developed a way to partition and isolate memory caches with 'protection domains'. Unlike Intel's Cache Allocation Technology (CAT), MIT's technology, called DAWG (Dynamically Allocated Way Guard) disallows hits across those protection domains. This is important, because attackers targeting this vulnerabilities take advantage of 'cache timing attacks' and can get access to sensible, private data.

MIT, Stanford Partner Towards Making CPU-Memory BUSes Obsolete

Graphene has been hailed for some time now as the next natural successor to silicon, today's most used medium for semiconductor technology. However, even before such more exotic solutions to current semiconductor technology are employed (and we are still way off that future, at least when it comes to mass production), engineers and researchers seem to be increasing their focus in one specific part of computing: internal communication between components.

Typically, communication between a computer's Central Processing Unit (CPU) and a system's memory (usually DRAM) have occurred through a bus, which is essentially a communication highway between data stored in the DRAM, and the data that the CPU needs to process/has just finished processing. The fastest CPU and RAM is still only as fast as the bus, and recent workloads have been increasing the amount of data to be processed (and thus transferred) by orders of magnitude. As such, engineers have been trying to figure out ways of increasing communication speed between the CPU and the memory subsystem, as it is looking increasingly likely that the next bottlenecks in HPC will come not through lack of CPU speed or memory throughput, but from a bottleneck in communication between those two.

Dell Rolls Out the OptiPlex 3020 Desktop

Dell has this week introduced a new OptiPlex business-ready desktop, a model dubbed OptiPlex 3020 that promises to offer 'industry-leading performance and best-in-class security in a budget-friendly package'.

Coming in two versions - Minitower (MIT) and Small Form Factor (SFF), this compact PC features a tool-free design and packs a 4th gen Intel Core processor, up to 16 GB of RAM, Intel HD 4600 graphics, either a hard drive or a solid-state hybrid drive (for up to 2 TB of storage on the minitower SKU), one PCIe x16 slot for graphics expansion, two USB 3.0 ports, and VGA and DisplayPort 1.2 outputs. The OptiPlex 3020 starts at $499.

AMD Appoints Ahmed Yahia Al Idrissi to Board of Directors

AMD (NYSE: AMD) announced today that Ahmed Yahia Al Idrissi has been appointed to the company's board of directors as a second representative of Mubadala Development Company. Yahia currently serves as executive director of Mubadala Industry, where he is responsible for Mubadala's growing industrial portfolio, including metals, mining, utilities, and advanced materials and products. Prior to joining Mubadala, Yahia was a partner at McKinsey & Company where he co-led the firm's Principal Investor practice. He was also the managing partner of McKinsey's Abu Dhabi practice.

"Ahmed's years of success at McKinsey, his responsibilities as part of the senior executive management team at Mubadala and his extensive experience with a number of different boards make him an excellent addition to AMD's board of directors," said Bruce Claflin, AMD's chairman of the board.

Re-engineered Battery Material Could Lead to Rapid Recharging of Many Devices

MIT engineers have created a kind of beltway that allows for the rapid transit of electrical energy through a well-known battery material, an advance that could usher in smaller, lighter batteries -- for cell phones and other devices -- that could recharge in seconds rather than hours. The work could also allow for the quick recharging of batteries in electric cars, although that particular application would be limited by the amount of power available to a homeowner through the electric grid.
The work, led by Gerbrand Ceder, the Richard P. Simmons Professor of Materials Science and Engineering, is reported in the March 12 issue of Nature. Because the material involved is not new -- the researchers have simply changed the way they make it -- Ceder believes the work could make it into the marketplace within two to three years.

NVIDIA Names Stanford's Bill Dally Chief Scientist, VP of Research

NVIDIA Corporation today announced that Bill Dally, the chairman of Stanford University's computer science department, will join the company as Chief Scientist and Vice President of NVIDIA Research. The company also announced that longtime Chief Scientist David Kirk has been appointed "NVIDIA Fellow."

"I am thrilled to welcome Bill to NVIDIA at such a pivotal time for our company," said Jen-Hsun Huang, president and CEO, NVIDIA. "His pioneering work in stream processors at Stanford greatly influenced the work we are doing at NVIDIA today. As one of the world's founding visionaries in parallel computing, he shares our passion for the GPU's evolution into a general purpose parallel processor and how it is increasingly becoming the soul of the new PC. His reputation as an innovator in our industry is unrivaled. It is truly an honor to have a legend like Bill in our company."

Buy a Laptop for a Child, Get Another Laptop Free

One Laptop Per Child, an ambitious project to bring computing to the developing world's children, has considerable momentum. The early reviews have been glowing, and mass production is set to start next month.

Orders, however, are slow. "I have to some degree underestimated the difference between shaking the hand of a head of state and having a check written," said Nicholas Negroponte, chairman of the nonprofit project. "And yes, it has been a disappointment."

But Mr. Negroponte, the founding director of the M.I.T. Media Laboratory, views the problem as a temporary one in the long-term pursuit of using technology as a new channel of learning and self-expression for children worldwide. He is reaching out to the public to try to give the laptop campaign a boost. The marketing program, to be announced today, is called "Give 1 Get 1," in which Americans and Canadians can buy two laptops for $399. One of the machines will be given to a child in a developing nation, and the other one will be shipped to the purchaser by Christmas. The donated computer is a tax-deductible charitable contribution. The program will run for two weeks, with orders accepted from Nov. 12 to Nov. 26.

MIT Team Simplifies Programming

The group of people who were previously responsible for creating the popular LEGO Mindstorms series of programmable capable robotics kits are responsible for creating Scratch a program which makes it easier for young kids above eight years old to learn programming. Scratch is available as a free 35 MB download, and so far runs on both Windows and Mac OS X. Programming commands are very simple and are separated into categories such as Motion and Sensing and the commands can be dragged and dropped into the scripts panel.
Return to Keyword Browsing