Does a node name like 5nm describe a real physical dimension?

No, not since roughly the 22nm era. Modern node names such as 5nm or 3nm are marketing labels for a process generation, not the gate length or any single measured feature. Actual transistor dimensions are larger than the name implies, and the figure mainly signals density and performance improvements over the previous node.

What is the difference between FinFET and gate-all-around?

FinFET transistors use a vertical fin of silicon with the gate wrapping three sides, introduced around 22nm. Gate-all-around (GAA, also called nanosheet) wraps the gate around all four sides of stacked channels, giving better control of leakage. The industry began moving to GAA at the 3nm/2nm generations.

Why do Intel's node names differ from TSMC's?

Historically Intel's nodes were denser than the same-named foundry node, so its '10nm' was comparable to TSMC's '7nm'. To align with the market, Intel renamed its roadmap in 2021 — Intel 7, Intel 4, Intel 3, Intel 20A and Intel 18A — where 'A' denotes ångströms (18A is roughly 1.8nm-class).

Which company leads at the leading edge?

Through the 7nm to 3nm generations TSMC has generally led in high-volume leading-edge production, with Samsung close behind and Intel regaining ground via its Intel 4/3 and 18A nodes. Leadership shifts each generation, so the timeline here reflects approximate volume-production years rather than a fixed ranking.

Does this reference store my searches?

No. The timeline and filter run entirely in your browser. Nothing you type is uploaded, logged or stored.

Semiconductor Process Node Reference

Email me this result

Get this tool's output sent to your inbox, plus one useful tool a week. No spam, unsubscribe any time.

A timeline of semiconductor process nodes

A process node names a generation of chip manufacturing technology. Smaller node numbers historically meant smaller transistors, but since around 22nm the names are marketing labels for a process generation rather than a measured dimension. This reference lays out the path from 90nm down to 2nm, with the approximate year each entered volume production, the dominant makers, and the transistor structure that defined it.

How it works

Each new node packs more transistors into the same area and usually improves speed and power. The big structural shifts matter more than the numbers: planar transistors gave way to FinFET around 22nm/16nm, and gate-all-around (GAA) nanosheet transistors arrived at the 3nm/2nm generations. Because foundries label generations differently, the same-named node from two makers is not identical — Intel’s renamed roadmap (Intel 7, 4, 3, 20A, 18A) realigns its names with TSMC and Samsung. Years shown are approximate first volume-production dates, which can differ from first-announcement or first-tape-out dates.

Tips and notes

Node names below ~22nm are marketing generations, not physical gate lengths.
The planar → FinFET → GAA progression is the real engineering story.
Intel 18A’s “A” means ångström — roughly a 1.8nm-class node.
Treat the years as volume-production estimates; sources vary by a year.