Back to home
Technology

Photonic Chip With A 2D Programmable Waveguide (Boston U., UC Irvine, Yale)

Source

SemiEngineering

Published

TL;DR

AI Generated

Researchers from Boston University, UC Irvine, and Yale University have published a technical paper on "Arbitrary control over multimode wave propagation for machine learning." They introduced a device with a 2D programmable waveguide that allows for rapid reprogramming of wave propagation, enabling neural network inference without digital pre-processing or post-processing. The device offers a reduction in device area and scaling benefits for photonic processors, potentially revolutionizing photonic chip technology. The study showcases the potential of two-dimensional programmable waveguides in enhancing computational efficiency and performance in machine learning applications.

Read Full Article

Similar Articles

Quantum photonics roadmap — how Xanadu and PsiQuantum are looking to transfer qubits through beams of light

Quantum photonics roadmap — how Xanadu and PsiQuantum are looking to transfer qubits through beams of light

Quantum photonics is explored as a method for transferring qubits through light beams, focusing on Xanadu and PsiQuantum. Xanadu, aiming for a Nasdaq listing, uses continuous-variable encoding, while PsiQuantum employs a dual-rail encoding approach. Quantum photonics offers advantages like room temperature operation and less susceptibility to interference but faces challenges such as photon loss. Xanadu and PsiQuantum are working towards fault-tolerant quantum computing, with Xanadu demonstrating advancements in GKP qubits and PsiQuantum aiming for a 1 million-plus qubit design. Both companies are navigating the complexities of quantum mechanics and the capital-intensive nature of quantum technology development.

Tom's Hardware
SemiEngineering

Silicon Photonics Lights The Way To More Efficient Data Centers

Silicon photonics is paving the way for more efficient data centers by potentially increasing bandwidth density and reducing power consumption, particularly driven by AI workloads. However, challenges such as process compatibility, thermal issues, and mechanical stress arise due to the use of various materials in photonic interconnects. Integrated electro-optical I/O modules are the desired outcome, but design and process complexities need to be addressed. The article delves into the technical aspects of silicon photonics, including the components involved, such as light sources, modulators, waveguides, and photodetectors, as well as the challenges of integrating optical and electronic components for efficient data transmission.

SemiEngineering
Squishy Photonic Switches Promise Fast Low Power Logic

Squishy Photonic Switches Promise Fast Low Power Logic

A new type of photonic device utilizes a liquid crystal droplet injected between soft, polymer pillars to create an all-optical logic system. This innovative technology offers fast processing speeds and low power consumption. The liquid crystal-based switches show promise for applications in flexible circuits and photonics, providing a novel approach to optical switching.

IEEE Spectrum
SemiEngineering

The Specialty Device Surge Part 2: The Process Control Challenges Of MEMS, Co-Packaged Optics, And More

The article discusses the challenges faced by manufacturers in producing specialty devices like MEMS, co-packaged optics, SiC, GaN power devices, and more as they scale up and diversify. These devices require unique materials, architectures, and process steps, leading to complex manufacturing and process control challenges. For example, MEMS devices rely on specific materials and processes for functionality, while power devices like SiC and GaN face hurdles like crystalline defects and thickness uniformity. Photonics and co-packaged optics introduce further complexity, requiring precision in waveguides, microlenses, and assembly processes. Advanced metrology and inspection solutions are crucial for achieving high-volume production of these specialty devices.

SemiEngineering

We use cookies

We use cookies to ensure you get the best experience on our website. For more information on how we use cookies, please see our cookie policy.