
at the speed of light.

A
spinoff
Neurophos
AI compute

Harness the Power of Light for AI
At Neurophos, we pioneer a revolutionary approach to AI computation, leveraging the vast potential of light. Our cutting-edge technology, powered by optical metasurfaces and silicon photonics, introduces a new era of ultra-fast, high-density AI inference that outstrips the capabilities of traditional silicon photonics.
Silicon Photonics: Speed Is Key
While our metasurface ensures high density, we haven't compromised on speed. We integrate high-speed silicon photonics to feed our metasurface in-memory processor, leveraging its high modulation speeds. The result is a fast, efficient vector-matrix multiplication engine that combines the density of the metasurface with the velocity of silicon photonics modulators.


High-Density Metasurface: Size Matters
Our metasurface elements function as optical in-memory compute elements that are thousands of times smaller than traditional silicon photonics modulators, allowing our architecture to process vastly larger matrices on chip. This results in an unprecedented increase in the computational density that provides a major advantage over conventional silicon photonics. In optical computing, energy efficiency is proportional to array size, so our processor is hundreds of times more efficient than the state of the art.
The Neurophos Advantage
At Neurophos, our mission is to deliver AI computation solutions that are not just faster, but more efficient and denser. Our unique approach combines the best of optical metasurfaces and silicon photonics, offering an AI inference acceleration solution that is poised to reshape the AI landscape. Join us as we light the way to the future of AI.
