Cornelis, an AI chip interconnect company, raised $205M in Series C funding to compete with Nvidia's accelerator ecosystem dominance.

Cornelis, a company developing networking technology to help AI chips communicate more effectively, announced Monday that it has raised $205 million in a funding round led by IAG Capital Partners. The company also unveiled Active Compute Fabric, a networking solution designed to address the significant amount of GPU time currently wasted waiting for data to arrive. By enabling chips to process and send information simultaneously, the fabric aims to maximize hardware utilization.

Spun out of Intel in 2020, Cornelis competes with Nvidia by offering an open architecture, allowing customers to pair a variety of GPU and accelerator hardware with Cornelis’ networking fabric. Although Nvidia chips can technically operate on third-party networks, they are optimized for Nvidia’s own software, making it significantly easier and more attractive for customers to adopt Nvidia’s full GPU stack. Cornelis is part of a new wave of AI infrastructure companies emerging to break apart Nvidia’s market dominance, piece by piece—or chip by chip.

Cornelis has already begun shipping its product and is developing a new generation, expected to be released later this year.