Cisco and NVIDIA introduce 400G optics for AI networking with fourfold bandwidth density
Cisco and NVIDIA announced a partnership at the Open Compute Project Global Summit 2026 to develop an open industry specification for 400G-per-lane pluggable optics. The new design aims to deliver four times the bandwidth density of previous modules while improving energy efficiency, targeting AI workloads in data centers and cloud services.
Key points
- Cisco and NVIDIA’s 400G optics offer four times the bandwidth density with lower power use for AI workloads
- Cisco’s G302 silicon and ‘Scale-Across’ architecture target data center efficiency and latency reduction
- SONiC OS and Live Protect (mid-2027) aim to ease small business adoption of AI infrastructure
Cisco’s Silicon One portfolio is expanding with G300-powered systems and the 1.6T G302 silicon, designed for top-of-rack deployments. The company also introduced the ‘Scale-Across’ architecture to reduce congestion and latency for distributed AI workloads. For small businesses, Cisco’s SONiC open-source operating system and the upcoming Live Protect feature (rolling out mid-2027) aim to simplify adoption and cybersecurity management. Microsoft’s Anand Ramakrishna praised NVIDIA’s P200 architecture for supporting cloud and high-performance services, highlighting industry collaboration.
The story so far
3 episodes →- Cisco and NVIDIA introduce 400G optics for AI networking with fourfold bandwidth densitythis story
Cisco and NVIDIA Unveil Groundbreaking 400G Optics to Boost AI Networking
Small Business Trends · 29 October 2026
Loading the full article…
This text was published by Small Business Trends and written by David Wilson. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Hardware & Compute
All →- PCBs and chip substrates may constrain consumer electronics supply, insiders say · 2 src
- Eclypsium and Nvidia team up to secure AI infrastructure firmware · 2 src
- SpaceX says it closed $40B debt for GPUs arriving in 2027 · 3 src
- KDnuggets lists five Docker containers for a home AI lab · 1 src
- Fujifilm plans fivefold increase in magnetic tape production for AI · 2 src
Comments
via GitHub Discussions