AI Tech / news
Cornelis Raises $205M to Challenge Nvidia With Open AI Networking Fabric
AI networking developer Cornelis has raised $205 million in a round led by IAG Capital Partners and unveiled Active Compute Fabric, technology aimed at cutting GPU idle time.
The funding was announced Monday, alongside a product called Active Compute Fabric, a networking technology designed to address a common inefficiency: graphics processors spending significant stretches waiting for data to arrive.
Cornelis builds networking technology intended to help AI chips communicate more effectively. Its approach lets chips process and transmit information simultaneously, rather than pausing computation while data moves across the system.
The company spun off from Intel in 2020 and positions itself against Nvidia by offering an open architecture. Customers can pair the Cornelis networking fabric with a range of GPU and accelerator hardware rather than committing to a single vendor's components.
Nvidia's chips can technically operate on other networking fabrics, but they are optimized for Nvidia's own software, which makes using the company's full GPU stack easier and more attractive for many buyers.
Cornelis has already begun shipping its product and is developing a next generation that is expected to be released later this year. The round was led by IAG Capital Partners.