"The startup has come up with "metasurface modulators" with optical properties that enable it to serve as a tensor core processor for doing matrix vector multiplication - math that is at the heart of a lot of AI work (particularly inferencing), currently performed by specialized GPUs and TPUs that use traditional silicon gates and transistors."
"By fitting thousands of these modulators on a chip, Neurophos claims, its "optical processing unit" is significantly faster than the silicon GPUs currently used en masse at AI data centers, and far more efficient at inferencing (running trained models), which can be a fairly expensive task."
Metamaterials research that once produced a limited invisibility cloak at Duke University evolved into photonics advances for electromagnetism and computing. Neurophos, spun out of Duke and Metacept, created metasurface modulators whose optical properties act as tensor-core processors for matrix-vector multiplication, a core operation in AI inference. Thousands of modulators can be placed on a chip to form an optical processing unit that the company claims outperforms and out-efficiencies conventional silicon GPUs during inference. The startup raised $110 million in Series A funding from investors including Gates Frontier and Microsoft’s M12. Photonic chips promise higher performance and lower heat, but optical components remain larger than silicon counterparts.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]