This Chip Computes With Light, Breaking the 10 GHz Barrier for AI

Researchers have developed an optical computing system that performs feature extraction for quantitative trading with unprecedentedly low latency. Many advanced artificial intelligence (AI) systems, including those used in surgical robotics and high-speed financial trading, rely on processing large streams of raw data to identify important features almost instantly. However, traditional digital processors are reaching their physical limits. These electronic systems struggle to deliver the speed and data capacity that next-generation, data-heavy applications demand, resulting in slower performance and higher latency. Researchers believe the key to overcoming these limitations may come from using light instead of electricity. This emerging approach, known as optical computing, uses light to carry out complex computations with extraordinary speed. One of the most promising technologies in this field involves optical diffraction operators, thin, plate-like components that calculate as light travels through them.