Curated by THEOUTPOST
On Fri, 4 Oct, 12:06 AM UTC
2 Sources
[1]
Logic with light: Introducing diffraction casting, optical-based parallel computing
Increasingly complex applications such as artificial intelligence require ever more powerful and power-hungry computers to run. Optical computing is a proposed solution to increase speed and power efficiency but has yet to be realized due to constraints and drawbacks. A new design architecture, called diffraction casting, seeks to address these shortcomings. It introduces some concepts to the field of optical computing that might make it more appealing for implementation in next-generation computing devices. Whether it's the smartphone in your pocket or the laptop on your desk, all current computer devices are based on electronic technology. But this has some inherent drawbacks; in particular, they necessarily generate a lot of heat, especially as they increase in performance, not to mention that fabrication technologies are approaching the fundamental limits of what is theoretically possible. As a result, researchers explore alternative ways to perform computation that can tackle these problems and ideally offer some new functionality or features too. One possibility lies in an idea that has existed for several decades but has yet to break through and become commercially viable, and that's in optical computing. Essentially, optical computing leverages the speed of light waves and their ability to interact in complex ways with different optical materials without generating any heat. Add to this the fact that a broad range of light waves can pass through materials simultaneously without affecting each other and you can in theory produce a massively parallel, high-speed and power-efficient computer. "In the 1980s, researchers in Japan explored an optical computing method called shadow casting, which could perform some simple logical operations. But their implementation was based on relatively bulky geometric optical forms, perhaps analogous to the vacuum tubes used in early digital computers. They worked in principle, but they lacked flexibility and ease of integration to make something useful," said Associate Professor Ryoichi Horisaki from the Information Photonics Lab at the University of Tokyo. "We introduce an optical computing scheme called diffraction casting which improves upon shadow casting. Shadow casting is based on light rays interacting with different geometries, whereas diffraction casting is based on properties of the light wave itself, which results in more spatially efficient, functionally flexible optical elements that are extensible in ways you'd expect and require for a universal computer. "We ran numerical simulations which yielded very positive results, using small 16-by-16 pixel black-and-white images as inputs, smaller than icons on a smartphone screen." Horisaki and his team propose an all-optical system, that is, one that only converts the final output to something electronic and digital; prior to that stage, every step of the system is optical. Their work has been published in Advanced Photonics. Their idea is to take an image as a source of data -- which naturally suggests this system could be used for image processing, but other kinds of data, especially that used in machine learning systems, could also be represented graphically -- and combine that source image with a series of other images representing stages in logic operations. Think of it like layers in an image editing application such as Adobe Photoshop: There is an input layer -- source image -- which can have layers placed on top, which obscure, manipulate or transmit something from the layer beneath. The output -- top layer -- is essentially processed by the combination of these layers. In this case, these layers will have light passed through them casting an image (hence the "casting" in diffraction casting) on a sensor, which will then become digital data for storage or presentation to the user. "Diffraction casting is just one building block in a hypothetical computer based around this principle and it might be best to think of it as an additional component rather than a full replacement of existing systems, akin to the way graphical processing units are specialized components for graphics, gaming and machine learning workloads," said lead author Ryosuke Mashiko. "I anticipate it will take around 10 years to become commercially available, as much work has to be done on the physical implementation, which, although grounded in real work, has yet to be constructed. "At present, we can demonstrate the usefulness of diffraction casting in performing the 16 basic logic operations at the heart of much information processing, but there's also scope for extending our system into another upcoming area of computing that goes beyond the traditional, and that's in quantum computing. Time will tell."
[2]
Logic with light: Introducing diffraction casting, optical-based parallel computing
Increasingly complex applications such as artificial intelligence require ever more powerful and power-hungry computers to run. Optical computing is a proposed solution to increase speed and power efficiency but has yet to be realized due to constraints and drawbacks. A new design architecture, called diffraction casting, seeks to address these shortcomings. It introduces some concepts to the field of optical computing that might make it more appealing for implementation in next-generation computing devices. Whether it's the smartphone in your pocket or the laptop on your desk, all current computer devices are based on electronic technology. But this has some inherent drawbacks; in particular, they necessarily generate a lot of heat, especially as they increase in performance, not to mention that fabrication technologies are approaching the fundamental limits of what is theoretically possible. As a result, researchers explore alternative ways to perform computation that can tackle these problems and ideally offer some new functionality or features too. One possibility lies in an idea that has existed for several decades but has yet to break through and become commercially viable, and that's in optical computing. Essentially, optical computing leverages the speed of light waves and their ability to interact in complex ways with different optical materials without generating any heat. Add to this the fact that a broad range of light waves can pass through materials simultaneously without affecting each other and you can in theory produce a massively parallel, high-speed and power-efficient computer. "In the 1980s, researchers in Japan explored an optical computing method called shadow casting, which could perform some simple logical operations. But their implementation was based on relatively bulky geometric optical forms, perhaps analogous to the vacuum tubes used in early digital computers. They worked in principle, but they lacked flexibility and ease of integration to make something useful," said Associate Professor Ryoichi Horisaki from the Information Photonics Lab at the University of Tokyo. "We introduce an optical computing scheme called diffraction casting which improves upon shadow casting. Shadow casting is based on light rays interacting with different geometries, whereas diffraction casting is based on properties of the light wave itself, which results in more spatially efficient, functionally flexible optical elements that are extensible in ways you'd expect and require for a universal computer. We ran numerical simulations which yielded very positive results, using small 16-by-16 pixel black-and-white images as inputs, smaller than icons on a smartphone screen." Horisaki and his team propose an all-optical system, that is, one that only converts the final output to something electronic and digital; prior to that stage, every step of the system is optical. Their idea is to take an image as a source of data -- which naturally suggests this system could be used for image processing, but other kinds of data, especially that used in machine learning systems, could also be represented graphically -- and combine that source image with a series of other images representing stages in logic operations. Think of it like layers in an image editing application such as Adobe Photoshop: You have an input layer -- source image -- which can have layers placed on top, which obscure, manipulate or transmit something from the layer beneath. The output -- top layer -- is essentially processed by the combination of these layers. In this case, these layers will have light passed through them casting an image (hence the "casting" in diffraction casting) on a sensor, which will then become digital data for storage or presentation to the user. "Diffraction casting is just one building block in a hypothetical computer based around this principle and it might be best to think of it as an additional component rather than a full replacement of existing systems, akin to the way graphical processing units are specialized components for graphics, gaming and machine learning workloads," said lead author Ryosuke Mashiko. "I anticipate it will take around 10 years to become commercially available, as much work has to be done on the physical implementation, which, although grounded in real work, has yet to be constructed. At present, we can demonstrate the usefulness of diffraction casting in performing the 16 basic logic operations at the heart of much information processing, but there's also scope for extending our system into another upcoming area of computing that goes beyond the traditional, and that's in quantum computing. Time will tell."
Share
Share
Copy Link
Researchers at the University of Tokyo have introduced diffraction casting, a novel optical computing architecture that promises to revolutionize AI and parallel processing with improved speed and energy efficiency.
Researchers at the University of Tokyo have unveiled a groundbreaking optical computing architecture called diffraction casting, which could potentially revolutionize the field of artificial intelligence and parallel processing. This innovative approach aims to address the growing demand for more powerful and energy-efficient computing solutions in an era of increasingly complex AI applications 12.
As AI and other computationally intensive applications continue to evolve, traditional electronic-based computers are reaching their limits. These systems generate significant heat as they increase in performance, and fabrication technologies are approaching fundamental theoretical boundaries. This has prompted researchers to explore alternative computing methods that can overcome these constraints while offering new functionalities 12.
Optical computing has long been considered a potential solution to the limitations of electronic systems. By leveraging the properties of light waves, optical computers can theoretically achieve:
Despite these advantages, optical computing has yet to become commercially viable due to various constraints and drawbacks 12.
The new diffraction casting method builds upon an earlier optical computing technique called shadow casting, which was explored by Japanese researchers in the 1980s. While shadow casting demonstrated the potential for performing simple logical operations, it relied on bulky geometric optical forms that lacked flexibility and ease of integration 12.
Associate Professor Ryoichi Horisaki from the Information Photonics Lab at the University of Tokyo explains:
"Diffraction casting improves upon shadow casting by basing its operations on the properties of light waves themselves, rather than on light rays interacting with different geometries. This results in more spatially efficient and functionally flexible optical elements that are extensible in ways necessary for a universal computer" 12.
The diffraction casting system proposed by Horisaki and his team is an all-optical architecture that only converts the final output to electronic and digital form. The process involves:
This approach is particularly well-suited for image processing and could potentially be applied to other types of data used in machine learning systems that can be represented graphically 12.
The research team has conducted numerical simulations using small 16-by-16 pixel black-and-white images as inputs, yielding positive results. Lead author Ryosuke Mashiko emphasizes that diffraction casting should be viewed as a building block in a hypothetical computer system, potentially serving as a specialized component similar to how GPUs are used for graphics, gaming, and machine learning workloads 12.
While the technology shows great promise, Mashiko estimates that it may take around 10 years for diffraction casting to become commercially available. The team has demonstrated the usefulness of diffraction casting in performing the 16 basic logic operations fundamental to information processing, and they see potential for extending the system into the realm of quantum computing 12.
As the field of optical computing continues to evolve, diffraction casting represents a significant step forward in addressing the growing demands of AI and other computationally intensive applications. The coming years will likely see further developments in this exciting area of research, potentially reshaping the landscape of computing technology.
MIT researchers have created a new photonic chip that can perform all key computations of a deep neural network optically, achieving ultrafast speeds and high energy efficiency. This breakthrough could revolutionize AI applications in various fields.
4 Sources
4 Sources
An international team of researchers has developed a novel method for photonic in-memory computing, potentially revolutionizing optical computing with improved speed, efficiency, and robustness.
2 Sources
2 Sources
Scientists have developed a microscopic AI chip that uses light to process data from fiber-optic cables, promising faster computations with significantly less energy consumption than traditional electronic systems.
3 Sources
3 Sources
Scientists discover luminescent nanocrystals with unique optical bistability, potentially revolutionizing AI and data processing through faster, more energy-efficient optical computing methods.
2 Sources
2 Sources
IBM Research unveils co-packaged optics technology that could dramatically improve data center efficiency for AI workloads, potentially reducing energy consumption and accelerating model training times.
9 Sources
9 Sources
The Outpost is a comprehensive collection of curated artificial intelligence software tools that cater to the needs of small business owners, bloggers, artists, musicians, entrepreneurs, marketers, writers, and researchers.
© 2025 TheOutpost.AI All rights reserved