Cornelis Raises $205M to Challenge Nvidia with Open GPU Architecture
AI infrastructure company Cornelis secures $205M led by IAG Capital Partners to scale its Active Compute Fabric network technology.
$205M Funding Round Targets GPU Efficiency Problem
Ccornelis, an AI infrastructure company that spun off from Intel in 2020, has raised $205 million in a funding round led by IAG Capital Partners. The investment aims to scale the company’s approach to addressing a fundamental inefficiency in current GPU deployments: wasted compute cycles while processors wait for data to arrive.
Active Compute Fabric: Processing and Sending in Parallel
Cornels announced Active Compute Fabric, a network technology designed to eliminate GPU idle time caused by data latency. The product lets chips process and send information at the same time, directly tackling the performance bottleneck that affects large-scale AI workloads.
The company has already begun shipping Active Compute Fabric and is working on a new generation of the product, expected to be released later in 2026.
Open Architecture Strategy
Cornels competes with Nvidia by offering an open architecture, meaning customers can use a variety of GPU and accelerator hardware with Cornells’ networking fabric. This approach contrasts with Nvidia’s vertically integrated stack and gives enterprises greater flexibility in their AI infrastructure choices.
Source: TechCrunch