DigestAI news desk

Cut through the AI noise.

Hardware & Computeupdated 2 min read

ASML Adapts High-NA EUV Lithography for Next-Gen Nvidia AI Chips

Dutch lithography giant ASML is collaborating with major chipmakers to adapt its next-generation High-NA EUV tools for the massive data-center processors designed by Nvidia and other tech firms. The initiative addresses a key limitation of ASML's TWINSCAN EXE:5000 systems, which feature an exposure field half the size of conventional EUV machines. This smaller field poses manufacturing…

6 sources

Key points

  • ASML is adapting High-NA EUV tools to overcome a half-size exposure field limitation for large AI processors.
  • Nvidia's upcoming 2027 Rubin Ultra system is projected to require 10 wafers, up from 2.5 for Blackwell.
  • Intel has initiated high-volume manufacturing for selected Intel 18A layers using ASML's High-NA EUV systems.

The urgency of this adaptation is highlighted by the soaring silicon demands of modern AI architectures. According to ASML, Nvidia's 2024 Blackwell system requires 2.5 wafers, whereas the projected 2027 Rubin Ultra system will demand 10 wafers—a fourfold increase in system-level silicon. While Intel has already begun using High-NA EUV for selected layers of its Intel 18A process, ASML expects broader customer insertion of the technology between 2027 and 2028.

Full story from cryptodaily.co.uk · by Andrei Popescu · via Search: ASMLOpen source ↗

ASML Plans Larger High-NA EUV Chips for Nvidia-Scale AI Processors

cryptodaily.co.uk · 9 September 2026

Loading the full article…

This text was published by cryptodaily.co.uk and written by Andrei Popescu. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

6sources
Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Hardware & Compute

All →

Related stories