Intel Shows Off Next-Gen Chips at Fab 42
As we wrote in 2017, Fab 42 was originally designated as the place where Intel’s future chips would be made on a 7nm process. Back then that size of node was very forward-looking as Intel was still struggling with its 10nm development, which it recently resolved with the launch of Alder Lake. Now Fab 42 is humming right along on the company’s next-gen products, and just as we predicted four years ago it’s using Extreme Ultraviolet Lithography, or EUV. This 7nm process is also known as Intel 4, with the 4 representing 4 angstroms, which is the unit of measurement below nanometer. One angstrom = 100 picometers, while one nanometer = 1000 picometers. Alder Lake was made on an Intel 10nm process, which is called Intel 7.
Highlights of Shankland’s trip include a look at the company’s 2023 chips, which are dubbed Meteor Lake. These 14th generation chips are significant because they are the first client-oriented CPUs to utilize an all-new chipset design, as opposed to the monolithic design it’s used in previous chips. This represents a stark departure for Intel, but as nodes get smaller and smaller both AMD and now Intel have turned their attention to chiplets and packaging as the key to improving performance in their next-gen offerings. Intel’s future Meteor Lake will use Foveros technology to stack chiplets vertically, as opposed to side-by-side. The chips shown to Cnet lacked functioning processing circuitry, and were apparently just being used to test the fab’s packaging functionality.
Other notable appearances include Intel’s absolutely massive Ponte Vecchio chip, which was designed to power the Department of Energy’s Aurora supercomputer. The chip combines every next-gen technology Intel is currently pursuing, with 47 separate chiplets connected laterally with Embedded Multi-Die Interconnect Bridges (EMIB), and vertically with Foveros stacking.
Intel giving reporters a look inside its facilities seems like part of its multi-year plan to once again become known as an engineering powerhouse; a mantle it has seemingly lost to rival TSMC in the recent past. Part of this strategy includes Intel offering its silicon fabrication services to other companies, which is it now doing under the moniker Intel Foundry Service, and has even gone so far as to say it hopes to win back Apple’s business, as the iPhone maker famously jettisoned Chipzilla’s CPUs in favor of TSMC. That goes the same for AMD, which also switched to TSMC for its latest chips. As proof of Intel’s commitment to regaining the mantle of engineering supremacy, Cnet notes Intel is currently ramping up two more fabs in Arizona — Fab 52 and 62 — at the cost of $20 billion, with plans for third fab that will cost a whopping $100 billion, location unannounced thus far.
Overall, Shankland’s article provides a fascinating look inside Intel’s operations, and the photo gallery that accompanies it is not to be missed.
Continue reading
In Massive Shift, Apple Announces New Macs With ARM-Based M1 Chip
Apple saw huge success the last time it switched architectures to Intel, but this time? The jury's still out, but one thing is certain: Apple is about to make a lot more money.
Microsoft: Pluton Chip Will Bring Xbox-Like Security to Windows PCs
Intel, AMD, and Qualcomm are working to make Pluton part of their upcoming designs, which should make PCs more difficult to hack, but it also bakes Microsoft technology into your hardware.
Why Apple’s M1 Chip Threatens Intel and AMD
Intel's own history suggests it and AMD should take Apple's new M1 SoC very seriously.
How L1 and L2 CPU Caches Work, and Why They’re an Essential Part of Modern Chips
Ever been curious how L1 and L2 cache work? We're glad you asked. Here, we deep dive into the structure and nature of one of computing's most fundamental designs and innovations.