A cutting-edge AI acceleration platform powered by light rather than electricity could revolutionize how AI is trained and deployed.
Using photonic integrated circuits made from advanced III-V semiconductors, researchers have developed a system that vastly outperforms traditional silicon GPUs in both energy efficiency and speed. This technology could not only lower energy costs but also scale AI to new levels of performance, potentially transforming everything from data centers to future smart systems.
The AI Boom and Its Infrastructure Challenges
Artificial intelligence (AI) is rapidly transforming a wide range of industries. Powered by deep learning and vast datasets, AI systems require enormous computing power to train and operate. Today, most of this work relies on graphical processing units (GPUs), but their high energy consumption and limited scalability pose significant challenges. To support future growth in AI, more efficient and sustainable hardware solutions are needed.
A Leap Forward: Photonic Circuits for AI
A recent study published in the IEEE Journal of Selected Topics in Quantum Electronics introduces a promising alternative: an AI acceleration platform built on photonic integrated circuits (PICs). These optical chips offer better scalability and energy efficiency than traditional, GPU-based systems. Led by Dr. Bassem Tossoun, Senior Research Scientist at Hewlett Packard Labs, the research shows how PICs that incorporate III-V compound semiconductors can run AI workloads faster and with far less energy.
Unlike conventional hardware, which uses electronic distributed neural networks (DNNs), this new approach uses optical neural networks (ONNs), circuits that compute with light instead of electricity. Because they operate at the speed of light and minimize energy loss, ONNs hold great potential for accelerating AI more efficiently.
"While silicon photonics are easy to manufacture, they are difficult to scale for complex integrated circuits. Our device platform can be used as the building blocks for photonic accelerators with far greater energy efficiency and scalability than the current state-of-the-art," explains Dr. Tossoun.
The team used a heterogeneous integration approach to fabricate the hardware. This included the use of silicon photonics along with III-V compound semiconductors that functionally integrate lasers and optical amplifiers to reduce optical losses and improve scalability. III-V semiconductors facilitate the creation of PICs with greater density and complexity. PICs utilizing these semiconductors can run all operations required for supporting neural networks, making them prime candidates for next-generation AI accelerator hardware.
How the Platform Was Fabricated
The fabrication started with silicon-on-insulator (SOI) wafers that have a 400 nm-thick silicon layer. Lithography and dry etching were followed by doping for metal oxide semiconductor capacitor (MOSCAP) devices and avalanche photodiodes (APDs). Next, selective growth of silicon and germanium was performed to form absorption, charge, and multiplication layers of the APD. III-V compound semiconductors (such as InP or GaAs) were then integrated onto the silicon platform using die-to-wafer bonding. A thin gate oxide layer (Al₂O₃ or HfO₂) was added to improve device efficiency, and finally a thick dielectric layer was deposited for encapsulation and thermal stability.
A New Frontier in AI Hardware
"The heterogeneous III/V-on-SOI platform provides all essential components required to develop photonic and optoelectronic computing architectures for AI/ML acceleration. This is particularly relevant for analog ML photonic accelerators, which use continuous analog values for data representation," Dr. Tossoun notes.
This unique photonic platform can achieve wafer-scale integration of all of the various devices required to build an optical neural network on one single photonic chip, including active devices such as on-chip lasers and amplifiers, high-speed photodetectors, energy-efficient modulators, and non-volatile phase shifters. This enables the development of TONN-based accelerators with a footprint-energy efficiency that is 2.9 × 10² times greater than other photonic platforms and 1.4 × 10² times greater than the most advanced digital electronics.
Transforming AI with Light-Speed Efficiency
This is indeed a breakthrough technology for AI/ML acceleration, reducing energy costs, improving computational efficiency, and enabling future AI-driven applications in various fields. Going forward, this technology will enable datacenters to accommodate more AI workloads and help solve several optimization problems.
The platform will be addressing computational and energy challenges, paving the way for robust and sustainable AI accelerator hardware in the future!
Reference: "Large-Scale Integrated Photonic Device Platform for Energy-Efficient AI/ML Accelerators" by Bassem Tossoun, Xian Xiao, Stanley Cheung, Yuan Yuan, Yiwei Peng, Sudharsanan Srinivasan, George Giamougiannis, Zhihong Huang, Prerana Singaraju, Yanir London, Matěj Hejda, Sri Priya Sundararajan, Yingtao Hu, Zheng Gong, Jongseo Baek, Antoine Descos, Morten Kapusta, Fabian Böhm, Thomas Van Vaerenbergh, Marco Fiorentino, Geza Kurczveil, Di Liang and Raymond G. Beausoleil, 9 January 2025, IEEE Journal of Selected Topics in Quantum Electronics.
DOI: 10.1109/JSTQE.2025.3527904
News
Your Voice May Reveal How Fast Your Brain Is Aging
Researchers have developed a machine-learning “speech clock” that estimates age from subtle patterns in how people speak and what they say. It is possible that people’s voices may contain certain signals of aging that [...]
Optogenetics Pioneers Win 2026 Nobel Prize in Physiology or Medicine
The 2026 Nobel Prize in Physiology or Medicine has been awarded to Peter Hegemann, Georg Nagel, and Karl Deisseroth for the development of optogenetics, a revolutionary technology that uses light to control individual neurons [...]
Molecular Manufacturing: The Future of Nanomedicine – From NanoappsMedical Inc.
This book explores the revolutionary potential of atomically precise manufacturing technologies to transform global healthcare, as well as practically every other sector across society. This forward-thinking volume examines how envisaged Factory@Home systems might enable the cost-effective [...]
What is ‘American Covid’ and how bad is it?
Cases of so-called ‘American Covid’ are on the rise in the UK. The strain is officially called XFG, or ‘Stratus’, and is the most common variant in North America, hence the name. It might soon [...]
Researcher at Russian plague laboratory dies of ‘unknown’ infection
Russian authorities have imposed "anti-epidemic measures" after a laboratory worker at an institute in Siberia dedicated to studying the plague and other infectious diseases died of a mysterious illness. The researcher, a 28-year-old female [...]
GHCE Concept
From the preface of the book Global Health Care Equivalency in the Age of Nanotechnology, Nanomedicine and Artificial Intelligence, Edited by Frank Boehm: Since the publication of my first book (Nanomedical Device and Systems [...]
A Surprising Brain Signal Could Explain Why Eating Less Protein Extends Lifespan
A new paper suggests that limiting protein intake triggers a coordinated response throughout the body that may help explain how protein restriction affects healthy aging. Animals respond to protein restriction, or reduced protein in [...]
Back and shoulder surgery is often worse than useless
Millions of operations should be scrapped SIX IN TEN Britons have surgery at some point. So do lots of Americans, at a cost of perhaps $500bn a year, a third of all spending on [...]
Cocaine plays with mind, hijacks brain circuit, drives increasingly rigid and repetitive behavior
Researchers have found that cocaine hijacks brain circuit, which to drive increasingly rigid and repetitive behavior. The brain circuit that normally participates in selecting natural mouth and face movements, but which becomes disproportionately engaged [...]
Injectable nanodevices could provide effective treatment for drug-resistant glioblastoma
The brain cancer glioblastoma is one of the most aggressive and treatment-resistant cancers known to medicine, carrying a median survival of just 12-15 months, even with the best available care. Now, researchers at the [...]
New Treatment Cuts “Bad” Cholesterol in Half for a Full Year
A single infusion of an experimental CRISPR-Cas9 therapy was reported to safely lower LDL cholesterol by 52.5% and triglycerides by 47.8%, as measured 12 months after treatment. What if one infusion could keep cholesterol [...]
Too Much RNA Can Drain a Cell’s Energy, Scientists Discover
A virus may cripple a cell’s power supply simply by producing too much of a molecule the cell needs to survive. New research from the Texas A&M College of Veterinary Medicine and Biomedical Sciences [...]
West African scientists warn of weakening health systems and urge stronger outbreak detection
LOME, Togo (AP) — West African laboratory scientists called on governments Friday to strengthen capacity to detect disease outbreaks to avoid another major outbreak, saying health systems across the region are becoming weaker. Participants [...]
A Little-Known Protein Could Point to a New Way To Treat Alzheimer’s
A study suggests that increasing SORLA protein levels could help treat Alzheimer’s disease and other disorders involving tau protein. Increasing SORLA, a protein with a protective role in the brain, helped mice withstand damage [...]
Cancer’s Hidden Antioxidant Shield Helps It Escape the Immune System
Blocking an antioxidant protein that tumors use to suppress immune attacks improved cancer immunotherapy responses in mice. Cancer cells can release antioxidants that interfere with the immune cells trying to kill them. Researchers have [...]
Scientists Find a Berry Compound That Helps Muscle Cells Burn Fat
Pterostilbene, a compound found naturally in some foods, affects how skeletal muscles process fats by stabilizing a protein called PPARδ and increasing its signaling activity. Pterostilbene, a natural compound found in blueberries, grapes, and [...]
