
A new chip architecture from IBM can integrate nearly 100 billion transistors on a chip the size of a human fingernail—nearly twice the transistor density of the company’s previous generation of chip technology. The resulting improvement in chip compute performance and energy efficiency comes from what IBM describes as the “world’s first sub-1 nanometer chip technology” for AI data centers. “It's not just an incremental step, it's a meaningful leap forward,” said Jay Gambetta, director of IBM Re
IBM announced a new chip architecture called "nanostack" that can fit nearly 100 billion transistors on a fingernail-sized chip, roughly doubling the transistor density of its previous generation. The technology is described as "sub-1 nanometer" because it delivers computing performance improvements expected from theoretically smaller transistors, though actual physical features cannot be built smaller than 1 nanometer due to physical limitations. The nanostack architecture vertically stacks transistors in a staggered layout and could provide up to 50 percent higher computing performance or 70 percent greater energy efficiency compared to previous chips, along with 40 percent improvement in memory scaling for AI applications. Commercial chips using this technology are expected to begin production within five to ten years and could eventually replace the current mainstream nanosheet architecture used by leading semiconductor manufacturers.

US electricity demand could rise 39% by 2035, but a new ICF report suggests the bigger challenge may be delivering power to fast-growing load centers.

The future of AI infrastructure is taking shape in Texas, where policy reform, power-first strategies, and transmission constraints are determining which gigawatt-scale campuses move from announcement to actual operation.

Corning’s AI deals with Meta, Amazon, and Nvidia show how optical infrastructure has become a strategic capacity as hyperscalers race to build AI clusters.
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven