Even that impressive feat is just business as usual. After all, Moore’s Law has been in effect for decades. The bigger news would be if Moore’s Law no longer applied to Intel chips.
So what’s the big deal with Intel’s 3D transistors? The answer lies in more than just smartphones, tablets, and set-top boxes. This fundamental new way of making the circuits of microchips could have a dramatic impact on everything from the smallest handheld devices to the biggest datacenters.
The Future of Computing
There’s no denying that the future of computing lies in small, low-power solutions coupled with big-iron cloud services. Smartphones are becoming personal computers, powerful enough to run simple desktop computing environments. Tablets are cannibalizing laptops. Entire home entertainment experiences are being jammed into tiny set-top boxes and embedded into televisions. Even Microsoft’s next version of Windows will run on low-power ARM-based chips.
Intel hasn’t excelled in all of these areas. It has a presence in televisions, thanks to Google TV and the Boxee Box, but so far the company hasn’t gained much traction in smartphones and tablets. Intel’s Moorestown chips are largely ignored. Its Medfield chips aren’t due to appear in any products until later this year, and they still may not fare well against the more-established ARM processors.
With 3D transistors, Intel may finally have the ammunition it needs to do battle in the smartphone and tablet markets. Intel claims its new transistors can switch 37 percent faster than those made with its existing 32-nm process in chips that operate at low voltage, or 18% faster in chips that operate at high voltage. Transistors switching at the same speed as those in the company’s 32nm chips can operate at significantly lower voltage, cutting power consumption in half. This change in how chips are produced is expected to raise production costs by a modest 2 or 3%, which is well worth the dramatic improvement in performance.
The first products to hit the market using this new manufacturing technique will be Intel’s “Ivy Bridge” line, the successor line to the current “Sandy Bridge” line. This means the new technology will first appear in laptops, desktops, and servers that use Intel’s chips. The faster switching speeds, lower voltage operation, and lower leakage should make Ivy Bridge processors considerably more energy-efficient than the Sandy Bridge CPUs in systems today. These products are expected to hit the market in early 2012.
It will take more time for the 22nm process, and its associated 3D transistor technology, to show up in Intel’s low-power Atom CPU lineup and system-on-chips designed for smartphones and tablets. In April, Intel said it would release its first true ARM competitor in 2013. This manufacturing technology is what will make that product possible.
Intel will use this 3D transistor structure on all chips produced on its 22nm manufacturing process, regardless of the type of chip or to which market it is targeted. The upsides should be considerable and the downsides minimal. Other chip fabrication companies have been working on 3D gate structures, but aren’t expected to bring them to market for some time. Most of Intel’s competitors aren’t expected to ship 22nm high-performance products until at least late 2012, and won’t use a 3D gate structure similar to Intel’s until the next major manufacturing process step, a couple of years later.
Follow Jared on Facebook and Twitter for even more tech news and commentary.