UK photonic networking startup Oriole Networks has deployed what it describes as the world’s first large-scale AI system running on a pure photonic network, marking the company’s first commercial use of its technology.
Built in collaboration with AMD, the deployment operates inside the UK Advanced Research and Invention Agency’s Scaling Inference Lab, a £50 million ($66.6 million) government-backed testbed targeting bottlenecks in large-scale AI workloads.
The system pairs Oriole’s PRISM networking platform with AMD Instinct GPUs and AMD EPYC CPUs. PRISM routes data as photons rather than electrical signals, replacing electronic switches at the core of the data center network with nanosecond-scale optical circuit switching. Conventional data center networks rely on electronic switches that draw heavy power and produce substantial heat, a constraint that has grown critical as AI workloads push thousands of chips to exchange data trillions of times per second.
“A year ago, we were proving the physics, today, we’re proving the business,” said Chief Executive James Regan. “Our collaboration with AMD has moved from concept to deployment to a system an order of magnitude larger and the data proves this is already driving performance increases at pace.”
Oriole says removing electronic switches cuts core network power consumption by 81% and drops GPU idle time from roughly 60% today to under 1%. Cooling demands and water use also fall as a result. PRISM is not locked to any single chip vendor and runs across accelerator platforms, giving customers a vendor-neutral alternative to proprietary networking stacks. Oriole said its designs are now locked for wider industry rollout in 2027.
AMD’s corporate vice president of compute and enterprise AI said Oriole’s nanosecond optical switching represents a fundamentally different approach to connecting accelerators at scale and that AMD is helping validate how photonic fabrics deliver the low-latency, high-bandwidth connectivity AI inference demands.
Founded in 2023 as a University College London spinout, Oriole went from research to production in three years. The company has raised approximately $35 million to date from investors including Plural, UCL Technology Fund, Clean Growth Fund, XTX Ventures, and Dorilton Ventures. Chief Executive James Regan said the deployment proves the business case alongside the physics.
