Semidynamics Unveils 3nm AI Inference Silicon and Full-Stack Systems

Feb 8, 2026
Semidynamics has introduced its 3nm AI inference silicon and a vertically integrated stack covering chips, boards, and rack-scale systems for next-generation data centers.

Semidynamics has unveiled its 3nm AI inference silicon and full-stack infrastructure, marking its expansion into vertically integrated AI systems announced in a press release. The company’s roadmap includes chips, boards, and rack-level systems designed to support large-scale AI inference workloads in advanced data centers.

The new architecture introduces a memory subsystem aimed at reducing bandwidth bottlenecks and improving efficiency for high-concurrency AI applications. Semidynamics achieved silicon readiness at the 3nm node with TSMC in December 2025, confirming its transition toward production-grade silicon.

The company’s vertically integrated offering includes the 3nm AI inference silicon, boards, and racks for multi-accelerator AI platforms. Partnerships supporting the initiative include EuroHPC Joint Undertaking, HPE, Bull (Atos Group), Telefónica, Multiverse Computing, E4 Computer Engineering, and Megware, each contributing to system design, deployment, and optimization.

Founded in 2016 and headquartered in Barcelona, Semidynamics focuses on developing high-performance silicon and infrastructure solutions for AI and HPC workloads.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.