Optical switching
Oriole Networks photonic networking platform to be integrated with AMD GPUs/CPUs for next-gen AI data center fabrics
London, England based Oriole Networks today announced continued progress in its collaboration with AMD in support of the UK’s Advanced Research & Invention Agency (ARIA) Scaling Inference Lab. The initiative integrates Oriole’s photonic interconnect architecture with AMD Instinct GPUs and AMD EPYC CPUs to evaluate next-generation data center fabrics capable of addressing the performance, latency, and energy constraints inherent in large-scale AI workloads.
The multi-year collaboration is advancing toward deployment of what is positioned as the first production-scale, all-photonic AI network fabric. The system is designed to deliver ultra-low latency and deterministic transport characteristics at the system level, leveraging optical circuit switching to optimize east-west traffic flows across accelerator clusters. The primary objective is to demonstrate how optical interconnect technologies can support large-scale inference and distributed AI processing under stringent performance and energy constraints.
Oriole’s PRISM photonic networking platform [2.] replaces conventional electronic switching in the network core with nanosecond-scale optical circuit switching. In contrast to packet-switched electronic fabrics, this approach is intended to reduce forwarding overhead, lower core power consumption, and improve end-to-end transport efficiency for accelerator-dense workloads. AMD is contributing compute hardware and technical collaboration to support modeling and execution of large-scale network workloads relevant to frontier AI systems. However, PRISM is not built for any single chip vendor. It works across any accelerator platform, giving the wider industry a path to frontier-scale system-wide performance without the need for proprietary stacks.
Note 1. Oriole Networks is a photonic networking company, developing disruptive technologies for AI/ML and HPC networking that will revolutionize data centers. These technologies address AI’s biggest challenges – speed, latency, and sustainability. Our holistic approach replaces energy-hungry electrical switching with photonic switching. By using only light to move data in the network, our solution will increase the efficiency of LLM training and inference to unprecedented levels while dramatically reducing the energy consumption of data centers, currently putting a huge strain on energy grids. We can offer faster, more efficient, and more sustainable AI without sacrificing the planet.
Note 2. Oriole’s PRISM is a fully photonic network system designed to provide port-level, all-to-all connectivity, eliminating the need for electrical switches and dramatically reducing the number of optical transceivers needed in the network. This evolution greatly reduces power consumption and latency, increases bandwidth, and strengthens network resilience by eliminating single points of failure.
Image Credit: Oriole Networks
…………………………………………………………………………………………………………………………………………………………………………………………………………………………………………..
The deployment also represents the first commercial implementation of Oriole’s technology following an R&D-to-production transition completed in approximately three years. The company states that its xPU-agnostic architecture is intended to support heterogeneous accelerator environments and broader industry rollout beginning in 2027.
Photonic networking architecture:
PRISM is designed to route data optically rather than electrically, using photonic circuit paths in place of conventional electronic switching elements. As AI training and inference workloads scale, data center interconnect requirements increasingly exceed the efficiency limits of traditional switch-based architectures, particularly in terms of power dissipation, thermal load, and communication latency.
By eliminating electronic switching in the fabric core, the PRISM architecture seeks to reduce core network power consumption and limit buffering- and queuing-related delay. The use of optical circuit switching is consistent with ongoing industry interest in photonic interconnects, co-packaged optics, and optical disaggregation as potential enablers of high-density AI clusters.
The company reports that the architecture can substantially reduce GPU idle time and improve system-level utilization by shortening data movement paths between compute nodes. It also indicates potential reductions in cooling demand and associated water usage due to lower network power dissipation.
Quotes:
James Regan, CEO of Oriole, said: “A year ago, we were proving the physics; today, we’re proving the business. 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. This is what it looks like when photonic networking stops being a research curiosity and starts being the foundation of how serious AI infrastructure gets built. There’s a big problem now with electrical switches, which are basically bottlenecking AI traffic, and it’s going to get worse. What we do is we replace all the electrical switches.”
“AMD is excited to collaborate with Oriole on the ARIA Scaling Inference Lab cluster,” said Madhu Rangarajan, corporate vice president, Compute and Enterprise AI business, AMD. “Oriole’s AI backend networking with nanosecond optical circuit switching represents a fundamentally different way to connect accelerators at scale. We are helping to validate how photonic fabrics can work alongside AMD compute to deliver the low-latency, high-bandwidth connectivity that AI Inference workloads demand.”
“Meeting the demands for modern AI requires rapidly identifying ways to improve the performance and cost-efficiency of large-scale AI clusters. ARIA is thrilled to collaborate with Oriole and AMD to demonstrate the benefits of this new technology and it’s exactly the type of collaboration, between innovative startups and industry leaders, that the Scaling Inference Lab was designed to foster,” said Suraj Bramhavar, Program Director at ARIA
Standards and interoperability context:
From a standards perspective, photonic AI fabrics remain an active area of industry development rather than a fully mature architectural class. Relevant technical domains include IEEE 802.3 optical Ethernet interfaces, ITU-T optical transport frameworks such as G.694 and G.709, and ecosystem work in optical interconnect and co-packaged optics initiatives.
A vendor-neutral, accelerator-agnostic photonic fabric may be of interest to standards and industry groups evaluating future data center interconnect models for AI and high-performance computing. The Oriole–AMD collaboration therefore provides an early reference point for assessing the operational characteristics, integration constraints, and interoperability implications of optical circuit-switched AI infrastructure.
……………………………………………………………………………………………………………………………………………………………………………………………………………………….
References:
Oriole to Deploy World’s First AI System with Pure Photonic Network to Supercharge Data Centers
https://www.fierce-network.com/cloud/oriole-networks-pushes-pure-photonic-networking-ai-data-centers
NTT’s IOWN is (finally) evolving to an All Photonics Network (APN); Physics based AI for enterprise OT
Goldman Sachs report: Optical Networking is the next mega trend in AI infrastructure
Hyperscaler design of networking equipment with ODM partners
Technavio: Silicon Photonics market estimated to grow at ~25% CAGR from 2024-2028
AT&T sets 1.6 Tbps long distance speed record on its white box based fiber optic network
AT&T claims it achieved a long distance world record top speed of 1.6Tb/s over a single wavelength across 296 km of its long haul fiber optic network (spanning Newark, New Jersey to Philadelphia, Pennsylvania). That is four times faster than its current top speed of 400Gb/s per wavelength!
The 1.6Tb/s wavelength carried two IEEE 802.3df-2024 standard-based 800 Gigabit Ethernet end-to-end circuits, an industry first. It is a full, uninterrupted data path utilizing a single light frequency across the entire fiber length between two endpoints. The single-carrier 1.6 Tb/s wavelength was transported alongside existing live customer traffic on 100Gb/s and 400Gb/s wavelengths.
Open-sourced white box switches were the network equipment used during the trial. The white boxes are designed using the Broadcom Jericho3 packet processor chip and can provide up to 18 x 800G network interface ports all within a 2RU platform. The (Israel based) DriveNets Network Cloud software-based solution is hardware-agnostic and runs open APIs on the white boxes to perform data and control plane functions, including routing at 800G. The use of white boxes and the disaggregation of the hardware and software control costs and facilitate faster innovation.
The two 800GbE signals from the white box were multiplexed to 1.6 Tb/s in Ciena’s WaveLogic 6 Extreme coherent optical transponder, which is the first coherent optical solution to use a 200Gbaud design and 3nm coherent DSP ASIC and to reach speeds up to 1.6 Tb/s on a single carrier. The WL6e technology reduces the space and power per transmitted bit by 50% compared to current 800G transponders. This trial is the first to demonstrate WL6e at 1.6Tb/s with standards compliant 800GbE clients.
In the Newark and Philadelphia offices, 800G DR8 pluggable transceivers from Coherent were installed in the white box router and WL6e transponder to create the cross-office connectivity between the packet and optical technologies. And 800GbE client signals, provided by Keysight’s AresOne-M 800GE testset, fed the white box through additional pairs of 800G DR8 pluggable client optics, allowing verification of end-to-end performance of the two 800GbE services from Newark to Philadelphia.
Quotes:
“Traffic on AT&T’s network continues to increase as consumers are using more connected devices,” said Mike Satterlee, vice president, Network Infrastructure and Services, AT&T. “We anticipate network traffic growth to double by 2028 and the technologies demonstrated in this trial will play a key role in AT&T’s continued efforts to keep up with increasing customer demand to send data, watch videos, and use streaming services.”
“This groundbreaking achievement with AT&T adds to a growing list of Ciena industry-firsts that push the boundaries of optical network speed and capacity,” said Dino DiPerna, senior vice president, Global Research and Development, Ciena. “Ciena’s WaveLogic 6 coherent optics will support AT&T’s next gen converged optical network and efforts to build a cloud-based and AI-ready network with greater scale, flexibility and efficiency.”
Verizon’s 1.6Tb/s on Metro Fiber Network:
AT&T’s announcement comes just a few months after arch-rival Verizon announced a 1.6 Tb/s milestone of its own. Verizon also, working with Ciena, achieved that peak speed on a single wavelength, but on its metro fiber (not long distance) network. Verizon is mainly looking to advance through M&A. Its proposed acquisition of Frontier Communications is still pending, with some Frontier shareholders insisting that the US$20 billion price tag undervalues the operator.
……………………………………………………………………………………………………………………………….
AT&T has spent the past six months demonstrating that it aims to build its way to fiber domination. It rolled out fiber to around 600,000 premises in the 4th quarter of last year, taking its total fiber footprint to 28.9 million locations; it is shooting for 50 million by the end of 2029.
References:
https://about.att.com/story/2025/data-transport.html
https://www.business.att.com/products/wavelength-services.html
https://www.telecoms.com/fibre/at-t-touts-1-6-tbps-fibre-speed-milestone-as-us-battle-continues
AT&T Highlights: 5G mid-band spectrum, AT&T Fiber, Gigapower joint venture with BlackRock/disaggregation traffic milestone
Nokia, Windstream Wholesale and Colt complete world’s first ultra-fast 800GbE optical and IP service trial
China Telecom with ZTE demo single-wavelength 1.2T bps hollow-core fiber transmission system over 100T bps
T-Mobile posts impressive wireless growth stats in 2Q-2024; fiber optic network acquisition binge to complement its FWA business
Bell Canada buying Ziply Fiber for C$7 billion; will become 3rd largest fiber ISP in U.S.
Light Counting on Silicon Photonics and Optical Switching at SC22
Silicon photonics continues to progress but is yet to be adopted for high-performance computing and server architectures, according to market research firm Light Counting.
However, the Super Compute 2022 (SC22) conference hosted two silicon photonics firsts:
- Professor Keren Bergman of Columbia University reported a working 5Tbit/s transmitter optical chiplet implemented using 80 channels and 3D packaging. The accompanying receiver chip is working and is being lab-tested.
- Ayar Labs demonstrated its 2Tbit/s TeraPHY chiplet in an end-to-end link, sending and receiving data.
During the panel discussion on high-performance computing and silicon photonics, Intel’s Fabrizio Petrini addressed head-on why optics had such a low profile at the show. “The reality is there is a lot of skepticism about this technology. The adoption is not going to happen anytime soon,” he said.
Systems designers don’t see the implications until they embrace this technology. But factors are aligning for change, and a transition point is being approached in how systems are built, he says; the implications for systems and disaggregation are enormous.
Optical switching is another technology that has been on the fringes of the market for decades. It was all the rage from 1998-2001, but then fizzled out as there weren’t any large scale commercial deployments of photonic switches.
LightCounting reported in August that Google had been using photonic circuit switching in its cloud resident data centers for several years. The 136×136 port optical circuit switch is Google’s own design.
At SC22, a start-up, Drut Technologies, demonstrated its interface card working with a photonic switch at the top of a SuperMicro server rack. The system allows the server’s CPUs to dynamically configure the resources they need (memory, GPUs) tailored for workloads.
