aiqbench analysis
Oriole Networks and AMD are deploying a $68M testbed that replaces traditional electronic switches with photonic networking to achieve a ten-fold increase in AI inference throughput. This architecture directly addresses current infrastructure bottlenecks by reducing power consumption and cooling demands while scaling to meet complex AI workload requirements. The project validates the commercial viability of optical circuit switching as a necessary evolution for high-performance data centers.
How Oriole & AMD Built a $68M AI Inference Testbed
Oriole Networks & AMD are building a $68M AI inference testbed, deploying a pure photonic network with AMD Instinct GPUs and EPYC CPUs.
A £50 million ($68 million) investment is driving the creation of a new AI inference testbed in the UK, built around pure photonic networking. Oriole Networks is deploying the first large-scale AI system leveraging this approach, integrating its PRISM photonic network with AMD Instinct GPUs and AMD EPYC CPUs as part of the UK ARIA Scaling Inference Lab. The system aims to…
Excerpt shown under the publisher's RSS terms · 62 words · full text and figures are on the publisher's site
Related coverage
From Sports to Safety: Benchmarking Proactive Risk Inference in MLLMs
arXiv · Aug 7, 2026
TERRA: Task-Oriented Edge AI for Regional Fire Detection with Identity-Free Reporting
arXiv · Oct 31, 2026
HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference
arXiv · Aug 4, 2026
Phase-Aware CNN for Real-Time 5G/6G Channel Estimation with Hardware-in-the-loop Validation
arXiv · Aug 19, 2026