Intel's Roadmap Includes 4nm Fab in 2022 259
Precision submits "Intel Corp., the largest maker of chips in the world, has outlined plans to make chips using 4nm process technology in about thirteen years. According to Intel, integration capacity of chips will increase much higher compared to fabrication process."
My business plan includes world domination (Score:5, Insightful)
The people that created this must not be engineers (Score:3, Insightful)
12 years seems ambitious (Score:3, Insightful)
Re:Oh Intel. Such optimists... (Score:1, Insightful)
Dnap crozak mucky mucky hoodwiggle. Aptach TRS-80 4,whacka-mole wuppa puppa. Bezdig 6502 Assembler!
Re:My Roadmap (Score:5, Insightful)
Who can predict that far out? (Score:4, Insightful)
I would suspect that unforeseen developments, such as big advances in 3d circuit design, would alter this schedule a lot. This is simply daydreaming.
Re:Who can predict that far out? (Score:5, Insightful)
Re:Oh Intel. Such optimists... (Score:3, Insightful)
Re:The people that created this must not be engine (Score:5, Insightful)
"After all there's a reason you're not actually working in enginerring, when you're such a great engineer..."
Yeah - the pay is better.
Re:Oh Intel. Such optimists... (Score:3, Insightful)
What's to stop you from carving them out of the bone of those rat-men? Are they boneless? ;)
Or are they actually your children by then?
Re:It's not the radius that matters!!! (Score:3, Insightful)
Um, for those building supercomputers?
Today, supercomputers are not solely the purvue of RISC chips (which could also use this technology with proper patent-licensing fees paid), but also often made of commodity hardware, such as that coming from Intel. See: Google. With the sheer volume of data to mine that we have today, and the accelerated growth of data warehouses and other VLDBs (not just multi-TB, but multi-PB), faster everything is important in order to turn that data into value (sorry - that's already too buzzwordy). Yes, network speeds and hard disk speeds are important here. But not only does Intel not do that (well, they do some network, but that's not the biggest bottleneck anyway in this environment), but you can always fake disk speed by spreading your data over more disks until SSD or other technology displaces hard disks in server environments.
It's not like Intel backing off on this will entice software companies to produce quality software. That suggestion is moot. The server market is huge. Intel wants to make more money by helping its customers do what they need to do with their data faster. I see nothing to complain about here.
Besides, when we get chipsize down, we also get more powerful (and usually more energy-efficient) mobile devices in smaller footprints. A remote control for your home theatre system that can display a second channel on a minidisplay so you know what you're going to before you get there. A phone that you can capture video with and edit it right there before uploading to YouTube('s replacement) ... before the cops get there to confiscate it ;-) These don't just drive value/revenue for big corps in their backrooms, these come out and hit us as consumers. Interestingly, the big corps who fund this type of thing through purchase of ever-faster top-end equipment end up making it profitable enough to enter the consumer landscape, meaning they are in effect subsidising the rest of us. That video-editing phone probably wouldn't be profitable enough on its own to drive this development pace, but once the development is paid for by big corps, it's available to the rest of us some time later.
Re:How about 1994, 1997 and 2000/2001? (Score:4, Insightful)
Re:It's not the radius that matters!!! (Score:3, Insightful)
No need to use hydrogen, which, BTW, doesn't really exist as a solid, at reasonable temperatures.
Yeah, I was kidding with that. My point is, it seems like we're not talking about anything that's orders of magnitude better than Silicon. Before too long, if they keep shrinking things at this rate, they're going to hit a brick wall, right? They can only go so small with Silicon, and then if they switch to Graphene, they can get features a little smaller, but then they'll run up against the limits there, and won't have anywhere to turn and will have to do something completely different, like 3D chips or something.
Re:My business plan includes world domination (Score:3, Insightful)