process node
In plain wordsThe label for a generation of chip-making technology, like '3 nanometer'. Smaller numbers mean newer, denser chips, but the number no longer measures any actual part of the chip.
A generation of semiconductor manufacturing technology, with its own design rules, transistor structure and performance, named by a nominal feature size such as 7 nm, 3 nm or 2 nm. The number once tracked transistor gate length or half-pitch, but it gradually became a marketing label: a '2 nm' process has no 2 nm feature, and different foundries' equally named nodes differ in density. Each new node typically offers 10–30% better performance or power and higher density than its predecessor, at sharply rising design and wafer costs. Transistor structures have moved from planar devices to FinFETs (2011–2012) and to gate-all-around nanosheets (Samsung's 3 nm in 2022; TSMC's N2 and Intel's 18A in volume from late 2025). Leading AI accelerators of 2024–2026 are built mostly on TSMC 4 nm- and 3 nm-class nodes, and access to such nodes is restricted by export controls on AI chipsexport controls on AI chips, n.: Government rules that limit which countries and companies may buy the most advanced AI chips and the machines used to make them. The United States uses them mainly to slow China's progress in AI..
Origin
Node names followed the generations of the semiconductor industry's roadmaps, codified in the International Technology Roadmap for Semiconductors (1998–2016). The link between name and physical dimension weakened from the 1990s and was purely nominal by about 2009; Intel adopted 'angstrom' names (20A, 18A) in 2021.
Usage note
Compare manufacturers by measured density (transistors per mm²) or performance, not by node names. Intel renamed its nodes in 2021 (e.g., 10 nm Enhanced SuperFin became 'Intel 7') partly to align with competitors' naming.
Related
- Moore's lawMoore's law, n.: Gordon Moore's prediction that chipmakers could pack twice as many transistors onto a chip roughly every two years — a pace that for decades made computers steadily faster and cheaper, and has slowed but not stopped.
- semiconductor foundrysemiconductor foundry, n.: A factory company that manufactures chips designed by other companies. Taiwan's TSMC, the largest, makes nearly all of the world's most advanced AI chips.
- extreme ultraviolet lithographyextreme ultraviolet lithography, n.: The chip-printing technique used for the most advanced chips, which draws circuit patterns with ultra-short-wavelength light. A single Dutch company, ASML, makes all the machines, each costing well over $100 million.
- chipletchiplet, n.: One of several smaller chips that are made separately and then joined inside a single package to work as one processor, which is cheaper than making one giant chip and lets makers reuse parts.
- Dennard scalingDennard scaling, n.: The rule that as transistors shrank they also used proportionally less power, so chips got faster without getting hotter. It stopped working in the mid-2000s, ending the era of ever-faster single processors.
- export controls on AI chipsexport controls on AI chips, n.: Government rules that limit which countries and companies may buy the most advanced AI chips and the machines used to make them. The United States uses them mainly to slow China's progress in AI.
Mentioned in
Moore's lawMoore's law, n.: Gordon Moore's prediction that chipmakers could pack twice as many transistors onto a chip roughly every two years — a pace that for decades made computers steadily faster and cheaper, and has slowed but not stopped., ASICASIC, abbr.: A chip whose circuits are laid out to do one kind of work extremely well instead of running any program. AI companies design their own to run their models more cheaply than with off-the-shelf chips., ASMLASML, prop. n.: A Dutch maker of the giant machines that print circuit patterns onto chips. It alone can build the extreme-ultraviolet models on which today's most advanced chips, including AI chips, depend., H100H100, prop. n.: Nvidia's flagship AI chip of 2022–2024, so scarce and sought-after during the generative-AI boom that it became a unit of measure for AI computing power., interconnectinterconnect, n.: The wiring and networking that connect chips to each other — inside a server, across a data center, or within a single chip — so they can share data and work as one., semiconductor foundrysemiconductor foundry, n.: A factory company that manufactures chips designed by other companies. Taiwan's TSMC, the largest, makes nearly all of the world's most advanced AI chips., TSMCTSMC, prop. n.: The Taiwanese company that manufactures most of the world's advanced computer chips, including nearly all of the specialized chips used to train and run AI., chipletchiplet, n.: One of several smaller chips that are made separately and then joined inside a single package to work as one processor, which is cheaper than making one giant chip and lets makers reuse parts., Dennard scalingDennard scaling, n.: The rule that as transistors shrank they also used proportionally less power, so chips got faster without getting hotter. It stopped working in the mid-2000s, ending the era of ever-faster single processors., extreme ultraviolet lithographyextreme ultraviolet lithography, n.: The chip-printing technique used for the most advanced chips, which draws circuit patterns with ultra-short-wavelength light. A single Dutch company, ASML, makes all the machines, each costing well over $100 million., SRAMSRAM, abbr.: The fastest kind of computer memory, built directly into processor chips. It is quick but takes up a lot of space, so chips hold only a little of it.