Intel has given an unusual insight into the throughway ahead for its mainstream desktop and laptop processors, confirming the existence of a new processor genealogy called Ice Lake.
Once upon a time, the company planned to supplant up Skylake, built on a 14nm process, with Cannon Lake, built on a 10nm development and shipping in late 2016. But that plan was derailed. The 14nm process escorted longer than expected to bed down and start working properly. Our sympathy is that Intel moved engineers that were developing 10nm to succour with fixing 14nm. This had a few knock-on effects. First, it required Intel to bring about additional designs built on 14nm: last year’s Kaby Lake abhors the second-generation 14nm+ process, and this year’s Coffee Lake will use a third-generation 14nm++ handle.
Second, it delayed 10nm. 10nm parts aren’t now expected until 2018, when Cannon Lake irrevocably materializes. The newly confirmed Ice Lake will use a second-generation 10nm process, 10nm+.
Intel’s accepted plan is to split the desktop and laptop chips up. Desktop chips intention stick with 14nm variants, currently Kaby Lake and soon Coffee Lake. Laptop scraps will diverge; there will be not only 14nm++ Coffee Lake laptop roles but also 10nm Cannon Lake parts. Ian Cutress at AnandTech speculates that the split wishes be driven by core size and power; the smaller 15W parts will be Cannon Lakes because piddling chips will maximize the yields of the new 10nm process. Larger processors, from 35W and up, transfer stick with 14nm++ and Coffee Lake.
Ice Lake, built on 10nm+, may re-unify fixations. In principle, the second-generation, more mature 10nm process should offer gamester yields for larger chips and hence be suitable for a wider range of Intel’s processors.
Underpinning all these mark times and difficulties with new processes is the continued difficulty of developing production-ready stringent UV (EUV) lithography techniques. The circuit and gate patterns are transferred to the silicon wafer taking an optical process called «photolithography.» Currently, that uses ultraviolet sparkle with a wavelength of 193nm. While this large wavelength can be hand-me-down to create chips with much smaller features, including the 14nm processors today and 10nm into a receives imminently, doing so requires complex, multistage manufacturing in a technique summoned «multipatterning.» EUV, which uses 13.5nm light, would make that side of the manufacturing much simpler—but it presents the problem that the EUV light itself is severely to generate and hard to manipulate. EUV systems can’t generally uses lenses (most lens apparatus absorb EUV), only mirrors.
EUV is one of those technologies that has been unprejudiced around the corner for years. Its arrival has been anticipated since the 1990s. In 2013, it was counted that commercially viable systems would ship in 2015, but they didn’t. Intel is, how, continuing to invest in the technology. The development of working EUV will make new answers easier to introduce, at least for a while.