Traditional processors from the likes of Intel, AMD, or Nvidia have well-known limitations around speed, energy efficiency, and electromagnetic interference. For instance, foundational chip makers ...
As spotted earlier today by Gizmodo, the international team achieved a data transfer rate of 301 terabits, or 301,000,000 megabits per second by accessing new wavelength bands normally unreachable in ...
Startup Akhetonics GmbH has raised €6 million in funding for its optical chip technology, which can perform digital, analog and quantum computations in the same system. TechCrunch reported the ...
MOUNTAIN VIEW, Calif. — Startup Lightbit Corp. here today (March 7, 2003) rolled out its first product–a pure-optical processor chip technology for use in handling multiple channels over optical fiber ...
Neurophos, a spinout from Duke University and Metacept Inc., announced it has raised $7.2M in a seed round to productize a breakthrough in both metamaterials and optical AI inference chips. The ...
A new technical paper titled “Massively parallel and universal approximation of nonlinear functions using diffractive processors” was published by researchers at UCLA. “Nonlinear computation is ...
HERZELIA, Israel — Lenslet Ltd., a start-up company developing a digital signal processor that works in the optical domain, has made a strategic co-operation agreement with Paltek Corp. of Japan for ...
UCLA researchers have conducted an in-depth analysis of nonlinear information encoding strategies for diffractive optical processors, offering new insights into their performance and utility. Their ...
Optical computing startup Lightelligence has developed a new GPU that outstrips the very best GPUs on the planet -- at least in the most challenging mathematical problems -- with the introduction of ...
Light waves, as they propagate through a medium, experience a temporal delay. This delay can unveil crucial information about the underlying structural and compositional characteristics. Quantitative ...
This article will look at a technology for AI inference processing using light rather than electrons from Lightmatter and combined with traditional CMOS including SRAM memory. This article is based ...