Cisco systems launched a new chip and router designed to speed information through massive data centers on Tuesday. This new product will compete with the offerings of companies like Nvidia and Broadcom.
Cisco said its Silicon One G300 switch chip, expected to go on sale in the second half of the year, will help the chips that train and deliver AI systems talk to each other over hundreds of thousands of links.
The chip will power new Cisco N9000 and Cisco 8000 systems that push the frontier of AI networking in the data center, according to a press release. The systems feature innovative liquid cooling and support high-density optics to achieve new efficiency benchmarks and ensure customers get the most out of their GPU investments.
The company has also enhanced Nexus One to make it easier for enterprises to operate their AI networks on the premises or in the cloud, removing the complexity that can hold organizations back from scaling AI data centers.
READ: AMD, Cisco, and Humain form joint venture for AI infrastructure (
Martin Lund, executive vice president of Cisco’s common hardware group, told Reuters in an interview that the chip will be made from made with Taiwan Semiconductor Manufacturing Co’s 3 nanometer chipmaking technology, and will have several new “shock absorber” features designed to help networks of AI chips from bogging down when hit with large spikes of data traffic.
Cisco expects the chip to help some AI computing jobs get done 28% faster, in part by re-routing data around any problems in the network automatically, within microseconds. “This happens when you have tens of thousands, hundreds of thousands of connections – it happens quite regularly,” Lund said. “We focus on the total end-to-end efficiency of the network.”
Cisco says that Silicon One is the industry’s most scalable and programmable unified networking architecture, offering a complete portfolio of networking devices across AI, hyperscaler, data center, enterprise, and service provider use cases.
READ: Cisco unveils California lab and new quantum computing chip (
The company also said the G300 is highly programmable, enabling equipment to be upgraded for new network functionality even after it has been deployed. This allows Silicon One-based products to support emerging use cases and play multiple network roles, protecting long-term infrastructure investments. The security fused into the hardware allows customers to embrace holistic, at-speed security to keep clusters up and running, according to the company.
Networking has become a major competitive field in the AI industry. When Nvidia unveiled its newest systems last month, one of the six key chips in the system was a networking chip that competes with Cisco’s offerings. Broadcom is chasing the same market with its “Tomahawk” series of chips.