-
- News
- Books
Featured Books
- pcb007 Magazine
Latest Issues
Current IssueIn Pursuit of Perfection: Defect Reduction
For bare PCB board fabrication, defect reduction is a critical aspect of a company's bottom line profitability. In this issue, we examine how imaging, etching, and plating processes can provide information and insight into reducing defects and increasing yields.
Voices of the Industry
We take the pulse of the PCB industry by sharing insights from leading fabricators and suppliers in this month's issue. We've gathered their thoughts on the new U.S. administration, spending, the war in Ukraine, and their most pressing needs. It’s an eye-opening and enlightening look behind the curtain.
The Essential Guide to Surface Finishes
We go back to basics this month with a recount of a little history, and look forward to addressing the many challenges that high density, high frequency, adhesion, SI, and corrosion concerns for harsh environments bring to the fore. We compare and contrast surface finishes by type and application, take a hard look at the many iterations of gold plating, and address palladium as a surface finish.
- Articles
- Columns
Search Console
- Links
- Media kit
||| MENU - pcb007 Magazine
IEEE Study Leverages Silicon Photonics for Scalable and Sustainable AI Hardware
April 14, 2025 | PRNewswireEstimated reading time: 2 minutes
The emergence of AI has profoundly transformed numerous industries. Driven by deep learning technology and Big Data, AI requires significant processing power for training its models. While the existing AI infrastructure relies on graphical processing units (GPUs), the substantial processing demands and energy expenses associated with its operation remain key challenges.
A recent study published in IEEE Journal of Selected Topics in Quantum Electronics demonstrates a novel AI acceleration platform based on photonic integrated circuits (PICs), which offer superior scalability and energy efficiency compared to conventional GPU-based architectures. The study, led by Dr. Bassem Tossoun, a Senior Research Scientist at Hewlett Packard Labs, demonstrates how PICs leveraging III-V compound semiconductors can efficiently execute AI workloads. Unlike traditional AI hardware that relies on electronic distributed neural networks (DNNs), photonic AI accelerators utilize optical neural networks (ONNs), which operate at the speed of light with minimal energy loss.
"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.
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.
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. Going forward, the photonic platform 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.
Suggested Items
Maxar Space Systems Selected to Build High-Power EchoStar XXVI Satellite Share
06/02/2025 | BUSINESS WIREMaxar Space Systems, a trusted partner in satellite design and manufacturing, today announced it has been awarded a contract by EchoStar Corporation to manufacture EchoStar XXVI, a high-power geostationary communications satellite based on the Maxar 1300™ platform.
OSI Systems Receives $47 Million Services Order for Security Inspection Systems
05/30/2025 | BUSINESS WIREOSI Systems, Inc. announced that its Security division received a $47 million order from a U.S. based customer to provide ongoing maintenance service for its installed base of Rapiscan® inspection systems that are utilized for screening baggage, cargo and vehicles.
Imec Unveils Record-Low Loss 300mm RF Silicon Interposer for Sub-THz Systems
05/27/2025 | ImecAt the IEEE ECTC 2025 conference, imec – a world-leading research and innovation hub in nanoelectronics and digital technologies – highlights the exceptional performance and flexibility of its 300mm RF silicon interposer platform.
Qualcomm, Xiaomi Expand Collaboration with Multi-Year Agreement
05/23/2025 | Qualcomm Technologies, Inc.Qualcomm Technologies, Inc. and Xiaomi Corporation are celebrating 15 years of collaboration and have executed a multi-year agreement.
ASMPT Presents Central Platform for Data Exchange in Electronics Manufacturing
05/21/2025 | ASMPTWith WORKS Integration, ASMPT SMT Solutions, the market and technology leader in SMT, provides a central integration platform through which all its hardware and software solutions can communicate with each other.