Photonic Computing Innovations

The way we move data inside our chips is hitting a limit… Moving data with electrons is simply too heavy for the next generation of computing. Every time we push electricity through metal wires it creates friction. If we try to make chips move data any faster the resistance creates enough heat to melt the silicon. This is why AI power consumption is spiraling. Lightmatter found the solution…. Their platform called Passage replaces copper wires with Silicon Photonics. Instead of electricity it uses beams of light moving through microscopic glass tunnels. • Zero Mass: Photons move with no resistance and virtually no heat. • 100x Faster: Their M1000 chip moves 114 Terabits of data per second. This dwarfs traditional electronic interconnects. • Green AI: We can finally scale AI models to be 1000x smarter without overloading the global power grid. The future of computing is not just about smaller transistors. It is about moving at the speed of light!! 📚 Resources and Learn More • Lightmatter Official Press: “Lightmatter Unveils Passage M1000 Photonic Superchip” (March 2025). • Hot Chips 2025 Presentation: Darius Bunandar, “Passage M1000: 3D Photonic Interposer for AI.” • Lightmatter Technical Blog: “Seeing is Believing: A Technical Deep Dive into Lightmatter Hardware” (September 2025). • HPCwire Analysis: “Lightmatter Aims to Leapfrog I/O Limitations with 3D Photonic Interconnect” (December 2025). #techexplained #futuretech #ai

Researchers from Columbia University and Cornell University recently reported a 3D-photonic transceiver that features 80 channels on a single chip and consumes only 120fJ/bit from its electro-optic front ends. The #transceiver achieves low energy consumption through low-capacitance 3D connections between photonics and co-designed #CMOS electronics. Each channel has a relatively low data rate of 10Gbps, allowing the transceiver's electronics to operate with high sensitivity and minimal energy consumption. The large array of channels compensates for the low per-channel data rates, delivering a high aggregate data rate of 800Gbps in a compact transceiver area of only 0.15mm2 (@5.3Tbps/mm2). In addition, having many low-data-rate channels relaxes signal processing and time multiplexing of data streams native to the processor. Furthermore, wavelength-division-multiplexing (#WDM) sources for numerous data streams are becoming available with the advent of chip-scale microcombs. The EIC is bonded to the PIC based on a 15μm spacing and a 10μm bump diameter (@25μm pitch) in an array of 2,304 bonds. This process mitigates two potential failure risks: 1) excessive tin causing flow and electrical short to adjacent bonds and 2) insufficient tin leading to brittle bonds. 👇Figure 1: a) An illustration of the 3D-integrated photonic-electronic system combining arrays of electronic cells with arrays of photonic devices. b) A microscope image of the 80-channel photonic device arrays with an inset of two transmitter and two receiver cells. c) Microscope images of the photonic and electronic chips. The active photonic circuits occupy an area outlined in white, while the outer photonic chip area is used to fan out the optical/electrical lanes for fiber coupling and wire bonding. The blue overlay shows a four-channel transmitter and receiver #waveguide path; the disk and ring overlays are not to scale. An inset shows a diagram of the fiber-to-chip edge coupler, consisting of a silicon nitride (Si3N4) inverse taper and escalator to silicon. d) A scanning electron microscope image of the bonded electronic and photonic chip cross-section. e) An image of the wire-bonded transceiver die bonded to a printed circuit board and optically coupled to a fiber array with a US dime for scale. f) A cross-sectional diagram of the electronic and photonic chips and their associated material stacks. Both chips consist of a crystalline silicon substrate, doped-silicon devices and metal interconnection layers. Daudlin, S. et al. Three-dimensional photonic integration for ultra-low-energy, high-bandwidth interchip data links. Nat. Photon. (2025).👉https://lnkd.in/gpeVGZna #SemiconductorIndustry #Semiconductor #Semiconductors #AI #HPC #Datacenter #Optics #Photonics #SiliconPhotonics #Optical #Networking #OCI #Ethernet #Infrastructure #Interconnect #CloudAI #AICluster AIM Photonics TSMC Defense Advanced Research Projects Agency (DARPA) #FiberCoupling #SiP

Our work on realizing on-chip photonic machine learning using a new kind of device - in which the multimode propagation and interference of waves can be controlled - came out online in Nature Physics today. Paper: https://lnkd.in/eAfXGa4W (open access) Twitter thread explaining the work from when the preprint came out: https://lnkd.in/e5svpUsC The key ideas are: (1) it is possible to reprogram the refractive-index distribution of a slab waveguide if you make it out of an electro-optic material, grow a photoconductive layer on top of it, and shine light with the desired pattern onto the photoconductor; (2) you can train the pattern you shine onto the photoconductor so that the input to the slab waveguide containing the vector to classify is linearly transformed to an output vector containing the classification result (obtained in postprocessing by using argmax). We're excited about the possible future directions, including using this device in multilayer neural networks, and inverse design of reconfigurable photonic devices besides photonic neural networks. Congratulations to co-first-author Martin Stein for getting this project over the finish line, Logan Wright for his ingenuity and leadership in this work, and all the other co-authors! I'd also like to acknowledge our co-author and dear colleague, Dr. Tatsuhiro Onodera, who passed away last year; you can read his description of this work in his own words at https://lnkd.in/eBrB2RbZ.

Xanadu Unveils World’s First Scalable, Networked Photonic Quantum Computer Prototype Canada-based quantum computing company Xanadu has announced a groundbreaking achievement in the development of photonic quantum computers, unveiling the world’s first scalable and networked prototype. This marks a significant milestone in computing technology, as it brings closer the possibility of harnessing photons for fault-tolerant quantum computations. The Advantages of Photonic Quantum Computing Unlike classical computers that rely on electrons, photons—light particles that travel at 300,000 km/s—offer unparalleled speed and efficiency for processing information. Photons: • Travel faster than electrons, enabling high-speed data processing. • Are chargeless, making them less susceptible to interference from their environment. • Enable scalability, as they can be manipulated using mirrors, beam splitters, and optical fibers. However, photons’ lack of electric charge also makes them difficult to integrate with traditional electronic circuits, necessitating entirely new architectures for computation. Xanadu’s Photonic Quantum Computer: Aurora Xanadu’s prototype, called Aurora, is a 12-qubit photonic quantum computer that integrates all the essential subsystems for universal and fault-tolerant quantum computation. Aurora stands out as the first practical demonstration of a networked photonic quantum architecture. Key features of Aurora: 1. Scalability: Built using four independent photonic processing subsystems, Aurora is designed to scale efficiently with additional components. 2. Networking: Capable of connecting with other systems to form larger, distributed quantum networks. 3. Fault Tolerance: Developed with mechanisms to mitigate errors, making it suitable for real-world applications. Significance and Applications Xanadu’s photonic quantum computer has the potential to revolutionize industries and scientific research, particularly in areas such as: • Cryptography: Enhancing secure communication systems. • Material Science: Accelerating the discovery of advanced materials. • Optimization Problems: Solving complex logistical challenges. • Artificial Intelligence: Improving machine learning algorithms and data processing. The Road Ahead While Aurora represents a major leap forward, challenges remain, including increasing the number of qubits and ensuring long-term stability. Xanadu’s success could inspire further advancements in photonic quantum technologies, paving the way for faster, more efficient, and more scalable quantum systems. This breakthrough positions Xanadu as a leader in quantum innovation and highlights the growing potential of photonic quantum computing to transform the future of technology.

The explosive growth in computation and energy cost of artificial intelligence has spurred interest in alternative computing modalities to conventional electronic processors. Photonic processors, which use photons instead of electrons, promise optical neural networks with ultralow latency and power consumption. However, existing optical neural networks, limited by their designs, have not achieved the recognition accuracy of modern electronic neural networks. In a recent work published in Science Advances, we bridge this gap by embedding parallelized optical computation into flat camera optics that perform neural network computations during capture, before recording on the sensor. We leverage large kernels and propose a spatially varying convolutional network learned through a low-dimensional reparameterization. We instantiate this network inside the camera lens with a nanophotonic array with angle-dependent responses. The resulting setup is extremely simple: just replace a camera lens with our flat optics!! Combined with a lightweight electronic back-end of about 2K parameters, our reconfigurable nanophotonic neural network achieves 72.76% accuracy on CIFAR-10, surpassing AlexNet (72.64%), and advancing optical neural networks into the deep learning era. The paper can be found at: https://lnkd.in/gXUcn33Y

🔴 Researchers from imec, EPFL, KTH Royal Institute of Technology, and Tyndall National Institute present the blueprint for next-generation integrated photonics in #MicrosystemsAndNanoengineering. The paper "Integrated silicon photonic MEMS" proves that combining micro electromechanical systems with standard foundry processes will define the next decade of #SiliconPhotonics and #OpticalComputing. While silicon photonics has emerged as a mature technology for high data rate communications and autonomous vehicle sensing, the material's weak electro-optic effects remain a bottleneck. Traditional thermo-optic tuning devices demand continuous power consumption and result in large footprints. This comprehensive research proves that integrating MEMS directly into silicon photonic circuits is the ultimate solution. 1️⃣ Overcoming Material Limits: #PhotonicMEMS & #EnergyEfficiency By replacing bulky traditional modulators with silicon photonic MEMS, the architecture drastically reduces the device footprint. Furthermore, it introduces bistable phase switches that enable nonvolatile photonic circuits, eliminating the need for continuous static power consumption. 2️⃣ Wafer Level Scalability: #Foundry & #Packaging The true breakthrough lies in manufacturability. The research highlights the successful implementation of wafer-level hermetically sealed packaging. This ensures that these advanced MEMS components can be produced with high yield and high volume capacity using standardized silicon foundries. 3️⃣ Reconfigurable Architectures: #OpticalRouting & #QuantumInformation This scalable integration provides access to fully reconfigurable coupled resonator optical waveguides. It unlocks optimized library components for complex optical routing, paving the way for advanced photonic accelerated computing and quantum information processing. 💡 My Take: As the demands of AI and data centers push optical communication to its limits, the massive power consumption of thermo-optic tuning in traditional silicon photonics is no longer sustainable. By physically moving microscopic silicon structures using MEMS, we can route light with near-zero static power. This research is a massive wake-up call for the industry. Transitioning from solid-state thermal tuning to wafer-scale integrated photonic MEMS is not just an incremental hardware update, it is a mandatory architectural revolution required to build energy-efficient, large-scale optical networks. 👇 Link in the comments #AdvancedPackaging #HardwareArchitecture #Metrology #3DIC #DataCenter #AIHardware #Telecommunications #Optoelectronics Intel TSMC Samsung Electronics GlobalFoundries NVIDIA Broadcom Marvell Technology Cisco Applied Materials ASML Lam Research Lumentum Coherent Corp. Infinera STMicroelectronics

🚀 Excited to share our latest publication on neuromorphic photonic computing in collaboration with University of Strathclyde! In this work, we introduce a novel approach to all-optical spiking processing and reservoir computing using passive silicon microring resonators (MRRs)—no pump-and-probe methods required. This simplification not only streamlines the architecture but also boosts efficiency. ✨ Key innovations: Deterministic optical spiking via excitatory signal injection at negative wavelength detuning High-contrast, prompt spiking events ideal for chip-integrated photonic neural networks A single MRR-based spiking reservoir computer that classifies the Iris dataset with 92% accuracy using just 48 virtual nodes and an average of 3 spikes per sample This work opens up new possibilities for sparse, low-power, high-speed photonic computing, especially in edge applications where efficiency is paramount. 🔬 We're excited about the potential of MRR-based neuromorphic frameworks to reshape the future of light-enabled sensing and AI. 📄 Read the full paper https://lnkd.in/dJ6waR-d #NeuromorphicComputing #PhotonicAI #ReservoirComputing #SiliconPhotonics #SpikingNeuralNetworks #EdgeAI #MRR #OpticalComputing #ResearchInnovation

High-Speed, Efficient Photonic Memories "The researchers used a magneto-optical material, cerium-substituted yttrium iron garnet (YIG), the optical properties of which dynamically change in response to external magnetic fields. By employing tiny magnets to store data and control the propagation of light within the material, they pioneered a new class of magneto-optical memories. The innovative platform leverages light to perform calculations at significantly higher speeds and with much greater efficiency than can be achieved using traditional electronics. This new type of memory has switching speeds 100 times faster than those of state-of-the-art photonic integrated technology. They consume about one-tenth the power, and they can be reprogrammed multiple times to perform different tasks. While current state-of-the-art optical memories have a limited lifespan and can be written up to 1,000 times, the team demonstrated that magneto-optical memories can be rewritten more than 2.3 billion times, equating to a potentially unlimited lifespan." #optical #photonic

⚡️ Photonic processors to accelerate AI 🌟 Overview Researchers at MIT have created a breakthrough photonic processor that can execute the key operations of deep neural networks optically, on a chip. This innovation opens the door to unprecedented speed and energy efficiency, solving challenges that have held photonic computing back for years. 🤓 Geek Mode The heart of this advancement is the nonlinear optical function unit (NOFU), which enables nonlinear operations—essential for deep learning—directly on the photonic chip. Previously, photonic systems had to convert optical signals to electronic ones for these tasks, losing speed and efficiency. NOFUs solve this by using a small amount of light to generate electric current within the chip, maintaining ultra-low latency and energy consumption. The result? A deep neural network that trains and operates in the optical domain, with computations taking less than half a nanosecond. 💼 Opportunity for VCs This photonic processor isn't just a fascinating technical achievement; it’s a platform play. The ability to scale this technology using commercial foundry processes makes it manufacturable at scale and primed for real-world integration. For VCs, the implications are vast. Think lidar systems, real-time AI training, high-speed telecommunications, and even astronomical research—all demanding ultra-fast, energy-efficient computation. Startups and spinouts leveraging this tech could redefine edge computing, optical AI hardware, and next-gen telecommunications. 🌍 Humanity-Level Impact Beyond enabling faster AI, this chip represents a shift in how we think about computation itself. Energy efficiency at this scale could dramatically reduce the environmental footprint of AI, a growing concern as models become more resource-intensive. Additionally, real-time, low-power AI could unlock applications in disaster response, autonomous navigation, and scientific discovery, accelerating progress in areas that directly improve lives. It’s a step toward a future where technology works not only faster but smarter and more sustainably. Innovations like these highlight the extraordinary potential of human creativity—turning the impossible into the inevitable. The light-driven future of AI is closer than we think. 📄 Original paper: https://lnkd.in/ga8Bvubk #DeepTech #VentureCapital #AI #Photonics

Silicon photonics is quietly becoming the backbone of AI infrastructure. AI clusters are now network-bound. Electrical I/O can’t keep up with the bandwidth and power demands of modern accelerators. Light can. The shift is already happening. STMicroelectronics announced a photonics chip co-developed with AWS, moving toward production right now. Meanwhile, the optical transceiver market is expected to triple by 2030. Europe is positioning itself seriously: - SCINTIL Photonics raised €50M with NVIDIA and Bosch on the cap table - Salience Labs closed $30M to build photonic switches for AI fabrics - iPRONICS pulled in €20M for programmable optical networking - EFFECT Photonics and SMART Photonics are scaling the foundry layer Behind this, the €400M PIXEurope pilot line program and a growing investor base are pushing industrialization forward. The strategic signal: hyperscalers are co-developing with European fabs, not just buying off-the-shelf. A critical layer of the AI infrastructure stack is being rebuilt, and Europe has a window to own part of it. Full landscape in the infographic 👇