English

A US research team has developed a new type of photonic memory computing device

188
2024-10-24 11:36:03
See translation

Recently, a research team from the University of California, Santa Barbara has successfully developed a new type of photonic memory computing device that integrates non reciprocal magneto-optical technology. This device achieves high-speed, high-energy efficiency, and ultra-high durability photon computing by utilizing the non reciprocal phase shift phenomenon. The research findings, titled "Integrated non recurrent magneto optics with ultra high endurance for photonic in memory computing," were published in Nature Photonics.

Photon computing has become one of the important directions for the future development of artificial intelligence and machine learning due to its advantages of high speed and low energy consumption. However, the current photon processing architecture faces challenges such as slow storage array update speed, high energy consumption, and insufficient durability. The non reciprocal magneto-optical technology proposed by the research team has successfully solved these bottlenecks by integrating cerium doped yttrium iron garnet with silicon micro ring resonators. By utilizing the non reciprocal phase shift properties of this material, researchers have demonstrated fast programming (1 nanosecond), low energy consumption (143 femjoules per bit), and excellent durability (programmable 2.4 billion cycles) of photonic memory cells.

 


Figure a. Schematic diagram of computing architecture and unit devices; d. Schematic diagram of memory unit.


The core of this technology is to encode optical weights through the non reciprocal phase shift effect generated by magneto-optical materials in micro ring resonators. Unlike existing photon weights based on thermal or plasmonic dispersion effects, non reciprocal magneto-optical weights not only improve programming speed, but also significantly enhance the device's fatigue resistance and multi-level storage capability. The research team also pointed out that the photon computing platform using this new architecture is expected to provide higher computational efficiency for matrix vector multiplication (MVM) in artificial intelligence.

The photon memory unit demonstrated in this study can update weights at a very high programming speed with high-speed response and low energy consumption, greatly reducing the overall energy burden of the system. Especially in applications such as deep learning that require large-scale computing, this technology can significantly reduce the computational bottleneck of traditional electrical architectures through non-volatile, multi bit storage, further promoting the development of future computing architectures towards more efficient and green directions.

Based on the future development prospects of this technology, researchers believe that by further optimizing the integration of materials, such as utilizing spin orbit torque or spin torque transfer effects, it is possible to achieve higher switching efficiency. In addition, with the advancement of single-chip integration technology between cerium doped yttrium iron garnet and silicon photonic devices, this technology has enormous potential for future applications in fields such as photon computing and magnetic storage.

Source: Opticsky

Related Recommendations
  • Improved spectrometer color filter array for software calibration without the need for laser

    Hackaday will launch cool projects that may stimulate others to expand and enhance it, and even move in a completely new direction. This is the way the most advanced technology continues to evolve. This DIY spectrometer project is a great example of this spirit. It comes from Michael Prathofer, who was inspired by Les Wright's PySpectrometer, a simple device pieced together by a pocket spectrom...

    2024-05-28
    See translation
  • Laser Photonics wins a large order from Lufthansa Technologies subsidiary

    Recently, American laser cleaning system developer Laser Photonics announced that the company has successfully secured an order for a cleaning technology laser cleaning system from Lufthansa Technik Puerto Rico, a technology subsidiary of Lufthansa, the largest aviation group in Europe.Lufthansa Technik is the world's largest independent provider dedicated to providing maintenance, repair, and com...

    2023-12-19
    See translation
  • Shandong Zhancheng Intelligent Manufacturing Laser Cutting Equipment is Popular Overseas

    The high-end laser cutting machine developed and produced by Dongying Lijin Zhancheng Laser Intelligent Manufacturing Company has become popular in overseas markets this spring. This equipment can not only use laser to quickly cut steel, but also freely swing on steel, "showing" beautiful pictures. The laser travels like a paintbrush flying, and the hard steel plate has been hollowed out into be...

    03-21
    See translation
  • Laser chip manufacturer Shijia Photon will make a profit of 65 million yuan in 2024

    Shijia Photon disclosed its 2024 annual performance forecast on the evening of January 17th, expecting to achieve a revenue of 1.074 billion yuan in 2024, a year-on-year increase of 42.36%; Net profit attributable to the parent company was 65 million yuan, with a loss of 47.55 million yuan in the same period last year; Deducting non net profit is expected to be 48.1 million yuan, with a loss of 66...

    01-21
    See translation
  • Micro optical technology based on metasurfaces has become a hot topic

    Introduction and application of a micro optical platform using metasurfacesMetasurfaces are artificial materials that excel in manipulating perception. Due to the fact that metasurfaces can reduce the size of lenses to one thousandth of traditional lenses, they have attracted great attention as optical components for miniaturization of next-generation virtual reality, augmented reality, and LiDAR ...

    2024-02-02
    See translation