Photonic AI is now a commercial reality.
Up to this point, most of our AI has been driven with nVidia GPU's. (That's why nVidia stock is through the roof).
But here is the next generation: photonic AI. AI at the speed of light.
Where this matters, is during the training phase of AI. That's where the costs are - and you've probably heard, that training an AI takes the electricity of a small city.
But this new technology is clean and efficient, it runs at a tiny fraction of the juice required by an nVidia device. It does the same thing (lots of matrix multiplication), but uses light instead of transistors.
Well... the actual technology is very impressive. It combines new materials with the same kind of wafer-building process Intel uses, but it adds some tiny little lasers on the chip and some photonic "light amplifiers" that guide the light along the required pathways.
From the article:
The fabrication started with silicon-on-insulator (SOI) wafers that have a 400 nm-thick silicon layer. Lithography and dry etching were followed by doping for metal oxide semiconductor capacitor (MOSCAP) devices and avalanche photodiodes (APDs). Next, selective growth of silicon and germanium was performed to form absorption, charge, and multiplication layers of the APD. III-V compound semiconductors (such as InP or GaAs) were then integrated onto the silicon platform using die-to-wafer bonding. A thin gate oxide layer (Al₂O₃ or HfO₂) was added to improve device efficiency, and finally a thick dielectric layer was deposited for encapsulation and thermal stability.
Optical computing has matured, it's real now. Stuff like this is why the Terminator had those little red lights.
Up to this point, most of our AI has been driven with nVidia GPU's. (That's why nVidia stock is through the roof).
But here is the next generation: photonic AI. AI at the speed of light.
AI at the Speed of Light: How Silicon Photonics Are Reinventing Hardware
A cutting-edge AI acceleration platform powered by light rather than electricity could revolutionize how AI is trained and deployed. Using photonic integrated circuits made from advanced III-V semiconductors, researchers have developed a system that vastly outperforms traditional silicon GPUs in
scitechdaily.com
Where this matters, is during the training phase of AI. That's where the costs are - and you've probably heard, that training an AI takes the electricity of a small city.
But this new technology is clean and efficient, it runs at a tiny fraction of the juice required by an nVidia device. It does the same thing (lots of matrix multiplication), but uses light instead of transistors.
Well... the actual technology is very impressive. It combines new materials with the same kind of wafer-building process Intel uses, but it adds some tiny little lasers on the chip and some photonic "light amplifiers" that guide the light along the required pathways.
From the article:
The fabrication started with silicon-on-insulator (SOI) wafers that have a 400 nm-thick silicon layer. Lithography and dry etching were followed by doping for metal oxide semiconductor capacitor (MOSCAP) devices and avalanche photodiodes (APDs). Next, selective growth of silicon and germanium was performed to form absorption, charge, and multiplication layers of the APD. III-V compound semiconductors (such as InP or GaAs) were then integrated onto the silicon platform using die-to-wafer bonding. A thin gate oxide layer (Al₂O₃ or HfO₂) was added to improve device efficiency, and finally a thick dielectric layer was deposited for encapsulation and thermal stability.
Optical computing has matured, it's real now. Stuff like this is why the Terminator had those little red lights.
