Marvell Acquires Polariton Technologies to Expand Optical Connectivity Portfolio

Apr 27, 2026
Marvell Technology has acquired Swiss silicon photonics startup Polariton Technologies to strengthen its optical interconnect capabilities and advance performance scaling to 3.2T and beyond. Financial details of the transaction were not disclosed.

Marvell Technology, Inc. has acquired Swiss silicon photonics company Polariton Technologies, announced in a press release. The acquisition adds plasmonics based modulation technology and engineering expertise to Marvell's optical portfolio. Financial terms of the deal were not disclosed.

Polariton develops high speed, low power photonic devices that use plasmonics to enable dense optical links with very low energy per bit. The technology supports scaling of optical interconnects for coherent and data center applications, including ZR and ZR+ modules. By integrating Polariton's plasmonics with its existing silicon photonics and digital signal processing capabilities, Marvell aims to deliver more compact and efficient optical solutions.

The acquisition enhances Marvell's connectivity offerings across photonics, electro optics, switching, and custom silicon. The company stated that this strengthens its position in developing scalable optical platforms for data centers as the industry moves beyond 1.6T toward 3.2T connectivity.

We hope you enjoyed this article

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

Also, consider following us on social media:

AI Funding News 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.