• Skip to main content
  • Skip to search
  • Skip to footer
Cadence Home
  • This search text may be transcribed, used, stored, or accessed by our third-party service providers per our Cookie Policy and Privacy Policy.

  1. Blogs
  2. Corporate News
  3. Cadence Tapes Out UCIe IP Solution at 64G Speeds on TSMC…
Corporate
Corporate

Community Member

Blog Activity
Options
  • Subscribe by email
  • More
  • Cancel
CDNS - RequestDemo

Discover what makes Cadence a Great Place to Work

Learn About
news story
ucie
featured
chiplets
TSMC N3P
64G
chiplet connectivity

Cadence Tapes Out UCIe IP Solution at 64G Speeds on TSMC N3P Technology

17 Dec 2025 • 2 minute read

Delivering the next wave of chiplet innovation, Cadence has successfully taped out its third-generation Universal Chiplet Interconnect Express (UCIe) IP solution, achieving industry-leading 64Gbps per-lane speeds on the advanced TSMC N3P process. As the industry moves toward increasingly complex AI, high-performance computing (HPC), and data center architectures, the need for robust, high-bandwidth chiplet connectivity has never been greater. This milestone positions Cadence at the forefront of enabling scalable, energy-efficient multi-die systems for the most demanding applications.

Eye diagrams for sampler data input and sampler clock output

As process nodes advance to 3nm and below, SoC designers face the challenge of balancing optimal power, performance, and area (PPA) with the requirements of high-speed, reliable die-to-die communication. The Cadence UCIe IP solution, fully compliant with the UCIe specification, is engineered to address these challenges directly. Leveraging TSMC's innovative N3P technology, the solution delivers excellent power efficiency, allowing customers to meet aggressive energy budgets without sacrificing performance.

Tapeout of 64Gbps UCIe IP Subsystem with TSMC N3P

The tapeout of Cadence's UCIe IP at 64G speeds marks a significant leap in chiplet interconnect technology. With support for up to 64Gbps per lane, designers can achieve ultra-high bandwidth density, unlocking new possibilities for scalable chiplet architectures. The solution's flexible and seamless incorporation of the diverse interface protocols available, such as AXI, CXS.B, CHI-C2C, PCIe, and CXL, enables rapid integration into a diverse range of platforms, from AI accelerators and networking appliances to advanced data center systems.

Reliability and integration flexibility are at the core of Cadence's UCIe IP. Advanced error correction, lane margining, and diagnostic capabilities ensure robust operation across heterogeneous multi-die environments. The architecture is designed to simplify system integration, supporting seamless interoperability across multi-vendor chiplet ecosystems.

"Cadence has been at the forefront of die-to-die interface solutions since our first tapeout in 2018. Pivoting to UCIe in 2022, we have extensively demonstrated silicon proofs of our Gen 1 and Gen 2 UCIe solutions over the past two years," said Arif Khan, vice president of marketing in the Silicon Solutions Group at Cadence. "Given the insatiable demand for throughput and efficiency driven by AI and HPC applications, we are proud to make our third-generation UCIe IP—achieving speeds of 64G—available. By collaborating with our trusted partner, TSMC, we are bringing a high-quality and efficient solution to our mutual customers."

Industry-Leading Features for AI/HPC Applications

Delivering 64Gbps performance, this solution achieves an impressive bandwidth density of 3.6Tbps/mm in the Standard Package and 21.08Tbps/mm in the Advanced Package. Featuring best-in-class PPA metrics, the architecture is optimized for HPC and AI applications. As with all Cadence UCIe generations, it supports a broad range of protocols—including AXI, CXS, CHI-C2C, PCIe, and CXL.io—seamlessly integrated with the high-speed PHY to provide a complete IP subsystem that accelerates design deployment. Self-calibrating capabilities and hardware-based bring-up eliminate the need for firmware intervention, enabling rapid system initialization and simplifying setup. A streamlined clocking scheme with an integrated phase-locked loop (PLL), combined with robust performance across voltage and temperature variations, ensures reliability and efficiency—allowing designers to focus on what matters most: their core logic.

With this achievement, Cadence expands its comprehensive IP portfolio, providing customers and partners with the tools needed to overcome the challenges of modern computing. By combining higher data rates, expansive and complete customer solutions, and robust standards compliance, Cadence is enabling the next generation of scalable, high-performance systems.

Learn more about Cadence's UCIe IP solution and how it can accelerate your next design at www.cadence.com/designip.


CDNS - RequestDemo

Have a question? Need more information?

Contact Us

© 2025 Cadence Design Systems, Inc. All Rights Reserved.

  • Terms of Use
  • Privacy
  • Cookie Policy
  • US Trademarks
  • Do Not Sell or Share My Personal Information