The Tech Download: How chip companies are looking to use light to solve this major AI bottleneck
The article discusses the challenges faced by AI builders, particularly in data transfer efficiency. It highlights the potential of photonics technology to improve communication speeds between AI chips and systems. By using light instead of electrical signals, photonics could significantly enhance AI model performance.
- ▪AI builders are facing constraints like energy access and a memory chip crunch.
- ▪Photonics technology offers a solution by using light to transfer data between AI components.
- ▪Current AI server connectivity primarily relies on copper wires, which limits speed and increases energy costs.
Opening excerpt (first ~120 words) tap to expand
The AI boom is in many ways a hype cycle like no other. Sure, there are comparisons to draw between the dotcom surge of the late 90s and the mobile revolution of the noughties, but in terms of capital invested and lofty predictions on it causing huge societal shifts, it stands ahead of the rest. The speed of that progress comes with big hurdles. AI builders are having to grapple with constraints like access to the energy that will power the huge data centers, a memory chip crunch and, increasingly, the efficiency of transferring data between AI chips and systems. An emerging technology, known as photonics, offers a route to solving for the latter.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at CNBC — Tech.
Discussion
0 commentsMore from CNBC — Tech
