Tower Semiconductor & Nvidia team up on 1.6T silicon photonics for AI data centers
Tower Semiconductor and NVIDIA are teaming up to scale next-generation AI infrastructure with 1.6T optical modules for data centers. The collaboration centers on Tower’s advanced silicon photonics platform, designed to meet the growing bandwidth and performance demands of large-scale AI deployments.
For eeNews Europe readers, this news highlights how foundry technology and photonics are becoming critical enablers of AI systems, from hyperscale data centers to advanced networking. It also offers insight into where high-speed interconnect technology is heading as AI workloads continue to surge.
Silicon photonics meets AI networking
Tower Semiconductor announced that its silicon photonics (SiPho) technology will be used in 1.6T data center optical modules designed for NVIDIA networking protocols. According to the company, the platform enables up to double the data rate of previous silicon photonics solutions, delivering higher bandwidth and throughput for optical connectivity in AI infrastructure.
As AI models grow in size and complexity, data movement has become a key bottleneck. High-speed optical interconnects are increasingly required to link GPUs, accelerators, and memory across large clusters. Tower’s SiPho platform targets this challenge by supporting very high-speed data transceivers that can keep pace with next-generation AI systems.
“Tower Semiconductor is proud to deliver advanced, high-speed technologies that support demanding data center and AI requirements,” said Russell Ellwanger, CEO of Tower Semiconductor. “We continue to invest significantly across our SiGe and silicon photonics platforms to support the ecosystem with industry-leading performance, scalability, and manufacturability, enabling customers to advance next-generation data center architectures.”
NVIDIA collaboration and ecosystem impact
From NVIDIA’s perspective, the collaboration is part of a broader push to build scalable, energy-efficient networking for AI at scale. Optical links are seen as essential to connect thousands of processors with minimal latency and power consumption.
“The exponential growth of AI is driving the need for a new class of high-speed, scalable networking to connect AI infrastructure,” said Gilad Shainer, Senior Vice President, Networking, NVIDIA. “NVIDIA is collaborating with Tower Semiconductor to advance the ecosystem, enabling more efficient AI infrastructure through next-generation silicon photonics and accelerating AI applications at scale.”
Tower positions itself as a key foundry partner for companies developing AI infrastructure, data center networking equipment, and advanced telecom systems. Its SiPho platform is optimized specifically for high-speed optical interconnects, complementing its established strengths in analog, RF, and SiGe technologies.
Foundry strategy for next-gen data centers
The move underlines a broader trend in the semiconductor industry: foundries are no longer just manufacturing partners, but active technology enablers shaping system-level performance. By focusing on manufacturability and scalability alongside speed, Tower aims to help customers bring advanced optical modules into volume production for future AI data centers.
As 1.6T optical modules move closer to deployment, collaborations like this one signal how silicon photonics is becoming a cornerstone technology for AI-driven data center architectures.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
