Items tagged with Moore's Law
Moore's Law, as revised in 1975, states the number of transistors in a dense integrated circuit will double around every two years. The observation is named after Gordon Moore, co-founder of Intel and Fairchild Semiconductor, and it's driven processor design for several decades. But what happens when Moore's Law is no longer feasible? Researchers from North Carolina State University believe the solution lies in reconfigurable chaos-based microchips. The smartypants researchers at NC State have gone and developed new, nonlinear, chaos-based integrated circuits that enable computer processors to perform multiple functions while also using fewer transistors. They can be built with off-the-shelf...
Read more...
It's a pretty remarkable thing that, for the most part, Moore's Law has been accurate for over 50 years, helping to set the pace for processor design for several decades. However, Moore's Law is in serious trouble of being broken if, as a group of researchers predict, transistors stop shrinking within the next five years. The Semiconductor Industry Association (SIA) recently put the final touches on its 2015 International Technology Roadmap for Semiconductors (ITRS), a collaborative report that surveys the technological hurdles and opportunities for the semiconductor industry through 2030. In it researchers surmise that companies will no longer find that it makes good fiscal sense to continue...
Read more...
For nearly a decade, Intel has followed a "tick-tock" release strategy for its processors. However, as Intel attempts to transition its manufacturing process from 14 nanometers to 10 nanometers, it's running into challenges that has the Santa Clara chip maker seemingly thinking about abandoning its tick-tock model.Before we go any further, let's talk about the tick-tock model for a moment. Starting in 2007, Intel followed a cadence that consisted of transitioning existing architectures to a new process node (tick) followed by releasing a new architecture on that same node (tock). For example, Broadwell was a tick, as it was a 14nm die shrink of Haswell (22nm), whereas today's Skylake architecture...
Read more...
Three atoms thick. According to a paper published this week in the science journal Nature by a group of researchers from Cornell University, that is the breadth of the transistors that can now be produced using an experimental — and highly conductive — material called transition metal dichalcogenide (also called a TMD). We aren't talking five atoms thick, or even four (because any schmoe with a hobbyist chemistry set can do that), but transistors rendered at a thickness of just three atoms. As it applies to theoretical science and human achievement, the harnessing of TMD for practical use is quite remarkable. It is the prospective leaps that could potentially be made in technological hardware...
Read more...
The transistor is one of the most profound innovations in all of human existence. First discovered in 1947, it has scaled like no advance in human history; we can pack billions of transistors into complicated processors smaller than your thumbnail. After decades of innovation, however, the transistor has faltered. Clock speeds stalled in 2005 and the 20nm process node is set to be more expensive than the 28nm node was for the first time ever. Now, researchers at NASA believe they may have discovered a way to kickstart transistors again -- by using technology from the earliest days of computing: The vacuum tube. No, really. Stop laughing. Once upon a time, vacuum tubes were the fundamental...
Read more...
Intel announced a major technology shift today in a move that fundamentally changes how the company will build transistors in the years to come. Starting with Ivy Bridge, Intel is adopting what it calls Tri-Gate (3D) transistors. Up to this point, Intel has relied on conventional bulk silicon, but its ability to scale this base technology is coming to an end. As processes shrink, it's become increasingly difficult to prevent current leakage. "For years we have seen limits to how small transistors can get," said Gordon E. Moore. "This change in the basic structure is a truly revolutionary approach, and one that should allow Moore's Law, and the historic pace of innovation, to continue."...
Read more...
We don't know what to do with all the multi-core chips we already have, never mind the eight and sixteen core processors looming on the horizon. The software is not keeping pace with the hardware. That realization is dawning over all the big players in computer chip design and tech educators. Think tanks dedicated to parallel computing are being founded and funded at numerous prestigious universities, including Stanford University, with support from all the big chip players, hoping to close the gap between the silicon and the ones and zeros. The Stanford lab, which will cost $6 million over three years, will be led by Kunle Olukotun, a professor of electrical engineering and computer science....
Read more...
IBM has announced a new breakthrough in chip-stacking technology in a manufacturing environment that paves the way for three-dimensional chips... "The IBM breakthrough enables the move from horizontal 2-D chip layouts to 3-D chip stacking, which takes chips and memory devices that traditionally sit side by side on a silicon wafer and stacks them together on top of one another. The result is a compact sandwich of components that dramatically reduces the size of the overall chip package and boosts the speed at which data flows among the functions on the chip."The release states that IBM is already running chips using the new through-silicon via technology in house and that the company will...
Read more...
Hewlett-Packard researchers realized they could pack more transistors on a chip, without shrinking them, simply by moving their connections to a nano-wire grid on top of them and packing more of them in the space they saved. "For a long time, we in the industry have been obsessed with this idea that higher capacity [chips] and lower cost equals smaller transistors, and we've been investing the bulk of our efforts in this area," says Stanley Williams, senior fellow and director of quantum-science research at HP Labs. The new research, Williams says, "is the first proof that it's possible to dramatically improve integrated circuits without shrinking...
Read more...
Multicore chips are a kind of cheating as far as Moore's Law goes. You're bringing a gang to the fight for faster processors. The battle to store the information those chips handle is where a lot of the action is now. Wired took a tour at Seagate's R and D labs, and they're talking about terabits per inch now: Their current solution to this problem is recording data perpendicular to the plane of the media. This technology, however, is expected to peak out at about 1 terabit per square inch. In the next decade, Seagate plans to hit the market with twin technologies that could fly far beyond, ultimately offering as much as 50 terabits per square inch. On a standard 3.5-inch drive,...
Read more...
For all you computer engineers out there, this may come as a shock: Moore's Law is dead according to the man himself. All those years of "the number of transistors on a die will double every 18mo" beaten into your heads is all for naught. Truth be told, the real reason for the death of Moore's Law has to do with the instability introduced in current transistor technology at higher frequencies. To compensate, chips have gone horizontal. Rather than increasing the frequency to produce better performance, manufacturers are increasing the transistor count via the number of cores on a die at a lower frequency. By doubling the number of transistors...
Read more...
Moore's Law, for all of you folks that think overclocking is sleeping late and driving to work faster, is the rule of thumb that computing power will double every eighteen months or so. It's seems to have been stuck a bit lately, and everyone was wondering where the next goose your chip needs -- to show you glistening beads of sweat on cheerleaders in future versions of Madden Football, instead of four pixels per nose--is going to come from. Well, laser beams running around inside your chip might do it: Researchers plan to announce on Monday that they have created a silicon-based chip that can produce laser beams. The advance will make it possible to use laser light rather...
Read more...
