AI BriefingIBM Unveils Sub-1nm Chip Technology
Key point
IBM has introduced 0.7nm process technology through a 3D nanostack structure, signaling a breakthrough for AI infrastructure.
Details
IBM has unveiled next-generation semiconductor technology at the 0.7nm (7 angstrom) node to overcome existing physical limitations. This technology is centered on a new 3D transistor architecture called 'nanostack'.
The key features of nanostack technology are as follows.
- 3D vertical stacking structure: Transistors are stacked vertically and arranged crosswise to maximize transistor density relative to chip area.
- Improved performance and efficiency: Compared to the existing 2nm process, performance is expected to improve by up to 50%, and energy efficiency by 70%.
- Optimized for AI workloads: By achieving 40% SRAM scaling, it provides a design optimized for generative AI and cloud infrastructure that require high-bandwidth data.
This technology demonstrates that atomic-scale scaling is possible, and it is expected to serve as a foundation supporting the semiconductor miniaturization roadmap for the next decade and beyond.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
DeepSeek Releases DSec: Elastic Sandbox Infrastructure for Large-Scale Agentic TrainingGoogle Launches First Suncatcher Orbital AI Data Center Test on October 1
KT Cloud Aims to Cut Deployment Failure Root Cause Analysis Time by 90% Using MCP