Beyond Chiplets, CMOS 2.0 Moves Scaling into the Circuit
The next phase of 3D integration could depend on repartitioning circuits themselves, not just stacking finished dies or packaging larger functional blocks.
By Pat Brans, EE Times | June 17, 2026

As transistor scaling becomes harder, the semiconductor industry has been moving outward toward chiplets, advanced packaging, high-bandwidth memory, and heterogeneous integration.
CMOS 2.0, imec’s term for a new scaling paradigm, takes that movement in the opposite direction. Rather than treating advanced packaging as the endpoint of disaggregation, it pushes the idea deeper into the chip itself. The goal is to create new ways to connect logic, memory, I/O, and power delivery inside a 3D architecture.
“When we are doing CMOS 2.0, it’s of course about disaggregating the system,” Zsolt Tokei, imec fellow and program director for 3D system integration, told EE Times. “But not necessarily in the traditional way.”
To read the full article, click here
Related Chiplet
- Integrated voltage regulator (IVR) chiplet
- High-performance connectivity chiplets
- eFPGA Chiplet
- DPIQ Tx PICs
- IMDD Tx PICs
Related News
- Why Chiplets Need a “Beyond IP” Management Approach
- Why tiny chiplets matter in the AI compute frenzy
- The Role of Chiplets in Redefining Semiconductor Design
- Lightmatter Joins UALink™ Consortium to Propel AI Interconnect into the Photonic Era
Latest News
- Point2 Completes $136M Series B Funding with Arm, LB Investment, and Maverick Silicon
- Multibeam Appoints Interim CFO Following $200M Funding Milestone
- Multibeam Signs $140 Million Letter of Intent with the U.S. Department of Commerce
- Credo to Contribute OmniConnect Scale-In Interconnect Solution to the Open Compute Project to Address AI Inference Memory Wall
- Silicon Box Ships 500M Units at High Yield, Expands Production Capacity for Panel-Level Packaging