What They Just Built Is Unreal

2025-11-19 · Source: Anastasi In Tech · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation, Cloud Computing & IT Infrastructure · Depth: Intermediate, extended

Summary

Imec, a research hub in Leuven, Belgium, is at the forefront of semiconductor innovation, developing technologies that major chipmakers like Apple, Google, NVIDIA, AMD, TSMC, Samsung, and Intel will use in 10 to 20 years. The industry is facing the physical limits of Moore's Law, with FinFET transistors reaching mechanical instability at 6 nm wide and 60 nm tall. Imec pioneered the Gate-All-Around (GAA) transistor, which stacks thin sheets horizontally, solving FinFET's mechanical issues and extending chip scaling for three more generations. Currently, Imec is developing 3D transistors, specifically CFETs, which stack devices vertically to double transistor density. This involves extensive simulation, material science, and the co-development of advanced tools like High NA EUV lithography machines with partners such as ASML. Beyond CFET, Imec is exploring system-level innovations like chiplets, silicon photonics for inter-chip communication, 3D computing cubes, and entirely new physics-based devices using materials like germanium, graphene, and 2D crystals, aiming to overcome the fundamental limitations of silicon.

Key takeaway

For AI Architects and Research Scientists evaluating future hardware roadmaps, understand that traditional transistor scaling is ending. Your long-term strategies must account for the shift towards 3D architectures like CFETs, system-level innovations such as chiplets and silicon photonics, and potentially entirely new physics-based computing paradigms being developed at research hubs like Imec. Prepare to integrate these complex, vertically integrated solutions as they become commercially viable over the next decade.

Key insights

Imec drives future computing by inventing post-Moore's Law chip architectures and materials, enabling continued technological advancement.

Principles

• Innovation requires deep collaboration.
• Vertical scaling extends transistor density.
• System-level improvements redefine Moore's Law.

Method

Imec's innovation cycle involves years of simulation, prototyping in a dedicated research fab, co-developing advanced manufacturing tools with partners, and perfecting new device recipes before industry adoption.

In practice

• Explore 3D stacking for density gains.
• Invest in silicon photonics for inter-chip communication.
• Research novel materials beyond silicon.

Topics

• Moore's Law Limits
• Advanced Transistor Technology
• 3D Chip Integration
• Semiconductor Manufacturing
• Post-Silicon Computing

Best for: AI Engineer, Research Scientist, AI Architect

Related on AIssential

• Beyond Chiplets, CMOS 2.0 Moves Scaling into the Circuit — CMOS 2.0 disaggregates circuits at the lowest level for ultra-dense 3D integration, driven by AI's data movement demands.
• IBM has unveiled chip technology that could help extend Moore’s Law another decade — IBM's nanostack architecture vertically stacks transistors, extending Moore's Law by enabling higher density and efficiency.
• Huawei Unveils Tau Scaling Law for Next-Gen Chip Evolution — Huawei's Tau Scaling Law and LogicFolding enable 3D chip architectures to reduce signal transmission times, overcoming Moore's Law limits.
• Accelerating Chipmaking Innovation for the Energy-Efficient AI Era — The AI era demands a coupled, accelerated co-innovation model for energy-efficient semiconductor design, replacing slow, siloed R&D.
• How Silicon Chips Are Made (Explained in 7 Mins) — Silicon's unique semiconductivity and oxide formation enable the complex, multi-stage fabrication of advanced microchips.
• Coherent Breaks Ground on Expanded Texas Facility, Scaling AI’s Optical Backbone — Optical interconnects, leveraging 6-inch indium phosphide wafers, are fundamental for scaling high-performance AI infrastructure efficiently.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Anastasi In Tech.