Cornelis, a firm specializing in networking solutions for AI chips, announced on Monday that it has secured $205 million in a funding round led by IAG Capital Partners.
Additionally, the company unveiled a new product named Active Compute Fabric, which is designed to optimize GPU resource utilization by reducing the downtime that occurs while waiting for data. This networking technology aims to enable simultaneous data processing and transmission among chips.
Founded in 2020 as a spin-off from Intel, Cornelis is positioning itself as a competitor to Nvidia by providing an open architecture. This allows clients to integrate various GPU and accelerator hardware with Cornelis’ networking solutions. While Nvidia processors can function on different networking frameworks, they are primarily designed to work seamlessly with Nvidia’s own software, creating a streamlined experience for users who opt for their complete GPU ecosystem. Cornelis is emerging amidst a new generation of AI infrastructure innovators seeking to challenge Nvidia’s stronghold on the market.
The company has begun distributing its current product and is also developing an updated version, which is scheduled for launch later this year.
