Cisco amps up Silicon One line, delivers new systems and optics for AI networking

Cisco is significantly ratcheting up the speed of its Silicon One family with the introduction of a 102.4 Terabit/sec chip and switch family, and it’s adding advanced software features designed for customers that need to support serious AI clusters.

The new Silicon One G300 is a 102.4 Tbps switching silicon. It includes a feature called Intelligent Collective Networking, which supports shared packet buffers, path-based load balancing, and proactive network telemetry to handle large-scale, bursty data center traffic, AI training, inference, and real-time agentic workloads.

“The G300 is enabling the next wave of industry-standard Ethernet switching for AI networks. It supports 1.6T Ethernet ports with on chip integrated 200 Gbps SerDes, developed in-house at Cisco, for low power consumption and high performance with longer reach. It has high radix scaling for up to 512 ports, enabling a ‘flatter’ network with the ability to connect more compute resources closer to the edge of the network,” said Nick Kucharewski, senior vice president and general manager for Cisco’s silicon development organization. “This lets operators connect a larger number of GPUs at the closest physical proximity, reducing compute latency, simplifying the network, and maximizing the efficiency of AI training and inference workloads.

In simulations, the chip’s larger packet buffer achieved a 33% increase in network throughput, Kucharewski said. This allows for higher GPU interconnect traffic without the need to increase network capacity, build larger networks, or add more switches—resulting in lower CapEx per deployed GPU, he said. Other simulations show a 28% reduction in job completion time compared to advanced packet spray implementations, significantly increasing AI compute efficiency, he said.

The chip will be at the heart of two new fixed form 64-port switches: the 3RU air-cooled 8133 and Cisco’s first commercially available water-cooled switch, the 2RU 8132. Both are aimed at hyperscaler, neocloud and enterprise customers, Kevin Wollenweber, senior vice president and general manager of data center and internet infrastructure, told Network World.

“We want to offer the building blocks for everyone from hyperscalers, service providers, neoclouds, sovereign clouds and enterprises to evolve their networks to handle the extraordinary bandwidth and performance requirements of AI along with energy efficiency and automation across data centers,” Wollenweber said.

Those building blocks include the new G300 as well as the G200 51.2 Tbps chip, which is aimed at spine and aggregation applications, and the G100 25.6 Tbps chip, which is aimed at leaf operations.

Expanded portfolio of Silicon One P200-powered systems

Cisco in October rolled out the P200 Silicon One chip and the high-end, 51.2 Tbps 8223 router aimed at distributed AI workloads. That system supports Octal Small Form-Factor Pluggable (OSFP) and Quad Small Form-Factor Pluggable Double Density (QSFP-DD) optical form factors that help the box support geographically dispersed AI clusters.

Cisco grew the G200 family this week with the addition of the 8122X-64EF-O, a 64x800G switch that will run the SONiC OS and includes support for Cisco 800G Linear Pluggable Optics (LPO) connectivity. LPO components typically set up direct links between fiber optic modules, eliminating the need for traditional components such as a digital signal processor.

Cisco said its P200 systems running IOS XR software now better support core routing services to allow data-center-to-data-center links and data center interconnect applications.

In addition, Cisco introduced a P200-powered 88-LC2-36EF-M line card, which delivers 28.8T of capacity.

“Available for both our 8-slot and 18-slot modular systems, this line card enables up to an unprecedented 518.4T of total system bandwidth, the highest in the industry,” wrote Guru Shenoy, senior vice president of the Cisco provider connectivity group, in a blog post about the news. “When paired with Cisco 800G ZR/ZR+ coherent pluggable optics, these systems can easily connect sites over 1,000 kilometers apart, providing the high-density performance needed for modern data center interconnects and core routing.”

Nexus One platform updates

To help customers better control and manage their data centers, Cisco enhanced its Nexus One management platform to oversee AI fabric implementations.

Cisco said the new version of Nexus One includes support for Cisco N9000 systems and a variety of network fabrics, including Nexus Hyperfabric, Cisco ACI, SONiC and others with a unified management plane to centralize operations and visibility through the Nexus Dashboard.

Nexus One now includes job-aware, network-to-GPU visibility that correlates network telemetry with AI GPU-based workload behavior.

“With native Splunk platform integration coming in March, customers will be able to analyze network telemetry directly where data resides—without having to move it to external platforms. This is an essential capability for sovereign cloud deployments and compliance-sensitive environments where data locality is paramount,” Cisco stated.