Friday, August 7, 2026
DarkSubscribe
AI Infrastructure · News & Analysis
HomeData CentersReport
Data Centers · Report

Cisco announced Silicon One G300 networking processor and optics optimized for dense AI datacenter and agentic workloads.

Networking infrastructure specializes for AI workloads, addressing dense GPU cluster bandwidth and latency requirements critical to deployment scale.
Official disclosureSlicast · February 10, 2026 · Global · Source: prnewswire.com
importance 75

Cisco announced on February 10, 2026, at Cisco Live EMEA the Silicon One G300, a 102.4 Tbps switching silicon designed for massive AI cluster buildouts. The silicon will power new Cisco N9000 and Cisco 8000 systems featuring innovative liquid cooling and support for high-density optics. The company also enhanced Nexus One to simplify AI network operations both on-premises and in the cloud. According to Jeetu Patel, President and Chief Product Officer, Cisco, "We are spearheading performance, manageability, and security in AI networking by innovating across the full stack - from silicon to systems and software. We're building the foundation for the future of infrastructure, supporting every type of customer—from hyperscalers to enterprises—as they shift to AI-powered workloads."

The Silicon One G300 represents a new standard for AI backend networking, designed to power massive, distributed AI clusters with high performance, security, and reliability. The silicon uniquely offers Intelligent Collective Networking, which combines a fully shared packet buffer, path-based load balancing, and proactive network telemetry. Martin Lund, Executive Vice President of Cisco's Common Hardware Group, explained that "the network becomes part of the compute itself. It's not just about faster GPUs – the network must deliver scalable bandwidth and reliable, congestion-free data movement." With Intelligent Collective Networking, Cisco delivers 33% increased network utilization and a 28% reduction in job completion time versus simulated non-optimized path selection, making AI data centers more profitable. The highly programmable silicon enables equipment upgrades for new functionality after deployment, and security is fused into the hardware for at-speed protection.

To address the diverse requirements of AI workloads, Cisco is introducing next-generation Cisco N9000 and Cisco 8000 fixed and modular Ethernet systems powered by Silicon One, alongside innovative optics designed for the extreme power and thermal demands of AI infrastructure. The company is advancing Nexus One with a unified management plane that integrates silicon, systems, optics, software, and programmable intelligence. New capabilities include AgenticOps for data center networking through AI Canvas, making troubleshooting easier through guided, human-in-the-loop conversations that turn complex issues into actionable resolutions.

The Silicon One G300, G300-powered systems, and optics will ship in 2026. Cisco is working with strategic technology partners including AMD, DDN, Intel, NetApp, NVIDIA, and VAST to combine cutting-edge networking, compute, and storage. Since its introduction in 2019, Cisco Silicon One has played critical roles in major networks around the world and spans use cases across AI, hyperscaler, data center, enterprise, and service provider environments.

Read the original
Cisco announced Silicon One G300 networking… · Slicast