HomeElectronics NewsSmart Connectivity for AI Infrastructure

Smart Connectivity for AI Infrastructure

A new approach to AI connectivity could let system designers change their hardware choices without redesigning the board.

Astera Labs Expands Taurus Family with Industry’s First OCP-Standard Footprint Compatible 3.2T Smart Retimers and Smart Redrivers
Astera Labs Expands Taurus Family with Industry’s First OCP-Standard Footprint Compatible 3.2T Smart Retimers and Smart Redrivers

Astera Labs has expanded its Taurus family of smart signal conditioners with new 16-lane retimers and redrivers for 200G-per-lane Ethernet, UALink, and ESUN connections in AI infrastructure.

- Advertisement -

The new devices are designed for hyperscalers, neoclouds, AI system providers, and networking companies building larger AI clusters. They aim to help these systems handle higher bandwidth while managing power use, signal quality, and accelerator utilisation.

As AI models become larger and more distributed, more accelerators need to communicate with each other. This is increasing the need for 200G-per-lane connections, which provide more bandwidth without increasing the number of lanes, connectors, or board space.

However, moving to higher-speed links also makes signal integrity, reach, power, heat, and system validation more difficult. Designers may also have to decide early whether a system needs a redriver for lower power or a retimer for longer reach. Changing that choice later can require a board redesign and additional validation work.

- Advertisement -

The expanded Taurus family addresses this through a Smart Swap feature. It allows customers to switch between footprint-compatible Smart Retimers and Smart Redrivers based on system requirements. Both devices use the OCP Signal Conditioner Standard Footprint, allowing customers to make the choice later in the design process.

Customers can configure, monitor, and deploy the devices through Astera Labs’ COSMOS software platform using a common workflow. The Smart Redrivers also provide telemetry and link management features, including temperature-compensating equalisation, channel estimation, and eye monitoring.

These functions can help system designers monitor link conditions, find signal problems earlier, and adjust high-speed connections as temperature and channel conditions change.

“AI infrastructure is entering a phase where flexibility becomes a competitive advantage,” said Adit Narasimha, senior vice president & general manager of Signal Connectivity Group at Astera Labs. “As 200G-per-lane signal conditioners become critical for on-board connectivity, customers need the freedom to optimise reach, power, and cost later in the design cycle. By expanding the Taurus family with footprint-compatible x16 Smart Retimers and Smart Redrivers, we are giving customers a more flexible path to scaling denser AI infrastructure with stronger economics.”

Click here for the original announcement.

Loading form…
Nidhi Agarwal
Nidhi Agarwal
Nidhi Agarwal is a Senior Technology Journalist at Electronics For You, specialising in embedded systems, development boards, and IoT cloud solutions. With a Master’s degree in Signal Processing, she combines strong technical knowledge with hands-on industry experience to deliver clear, insightful, and application-focused content. Nidhi began her career in engineering roles, working as a Product Engineer at Makerdemy, where she gained practical exposure to IoT systems, development platforms, and real-world implementation challenges. She has also worked as an IoT intern and robotics developer, building a solid foundation in hardware-software integration and emerging technologies. Before transitioning fully into technology journalism, she spent several years in academia as an Assistant Professor and Lecturer, teaching electronics and related subjects. This background reflects in her writing, which is structured, easy to understand, and highly educational for both students and professionals. At Electronics For You, Nidhi covers a wide range of topics including embedded development, cloud-connected devices, and next-generation electronics platforms. Her work focuses on simplifying complex technologies while maintaining technical accuracy, helping engineers, developers, and learners stay updated in a rapidly evolving ecosystem.

SHARE YOUR THOUGHTS & COMMENTS

EFY Prime

Unique DIY Projects

Electronics News

Truly Innovative Electronics

Latest DIY Videos

Electronics Components

Electronics Jobs

Calculators For Electronics