Huawei Unveils Tau Scaling Law for Next-Gen Chip Evolution

2026-05-26 · Source: AI Magazine · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation, Cloud Computing & IT Infrastructure · Depth: Advanced, short

Summary

Huawei has unveiled the Tau Scaling Law, a new principle for chip design, at the 2026 IEEE International Symposium on Circuits and Systems (ISCAS) in Shanghai. This law, also known as Her's Law, shifts focus from transistor shrinking to reducing signal transmission times within chips and computing systems, addressing the limitations of Moore's Law. Central to this is LogicFolding, a 3D architecture methodology that layers multiple 2D planar circuits vertically, creating room for more transistors and shortening data travel distances. This multi-level co-optimization mechanism, spanning devices, circuits, chips, and systems, aims to boost speed and energy efficiency by systematically shortening the time constant τ. Huawei has already designed and mass-produced 381 chips based on this law, with Kirin chips adopting LogicFolding set to launch in autumn 2026. By 2031, high-end chips are projected to achieve a transistor density equivalent to 14 Å processes (1.4 nm scale), impacting next-gen smartphones and AI computing infrastructure.

Key takeaway

For AI Hardware Engineers and AI Architects designing next-generation computing platforms, Huawei's Tau Scaling Law and LogicFolding technology signal a critical shift towards 3D chip architectures. You should evaluate the implications of vertical stacking and time constant compression for your future designs, particularly for high-performance AI accelerators and mobile devices. Consider exploring multi-level co-optimization strategies to enhance system-level parallelism and reduce communication latency in your projects.

Key insights

Huawei's Tau Scaling Law and LogicFolding enable 3D chip architectures to reduce signal transmission times, overcoming Moore's Law limits.

Principles

• Shift from transistor size to signal transmission time.
• 3D chip architecture enhances density and reduces latency.
• Multi-level co-optimization improves system performance.

Method

LogicFolding transitions chip architecture from 2D grids to 3D vertical stacking, layering circuits to shorten data travel and reduce resistive/capacitive load, optimizing time constant τ across device to system levels.

In practice

• Implement 3D LogicFolding for increased transistor density.
• Optimize resistance and parasitic capacitance at device level.
• Redefine interconnect protocols with UnifiedBus for systems.

Topics

• Tau Scaling Law
• LogicFolding
• 3D Chip Architecture
• Semiconductor Industry
• AI Computing Infrastructure
• Kirin Chips

Best for: AI Hardware Engineer, AI Architect, Director of AI/ML

Related on AIssential

• Huawei unveils plan for 1.4nm chip density as US sanctions persist — Tau (τ) Scaling Law shifts chip design focus from geometric shrinking to reducing data propagation time.
• From Shrinking Transistors to Compressing Time: Deciphering Huawei’s τ Law — Huawei's τ Law shifts semiconductor evolution from geometric scaling to temporal scaling, compressing system time via structural optimization.
• 🗞️ China’s Huawei reveals a new chip design breakthrough which can close its gap with TSMC and Intel — Chip progress can shift from transistor shrinkage to optimizing signal delay (τ) across the entire system stack.
• Necessity is the Mother of Invention: Huawei Replaces Moore’s Law With Her’s Law — Sanctions drive innovation, compelling Huawei to accelerate 3D stacking for performance gains beyond traditional geometric scaling.
• What They Just Built Is Unreal — Imec drives future computing by inventing post-Moore's Law chip architectures and materials, enabling continued technological advancement.
• Huawei Ascend Production Ramp: Die Banks, TSMC Continued Production, HBM is The Bottleneck — China's drive for AI compute self-sufficiency is bottlenecked by HBM supply, despite significant domestic chip production efforts.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI Magazine.