Computer speeds have increased dramatically over the last two decades, with processing speeds today being 60,000 times faster. However, data transfer rates have lagged and have only improved 30-fold. Removing this gap and increasing the data transfer rate is vital to unlocking AI’s full potential. Researchers recently designed a light-based chip connection system that could eliminate this bottleneck. This new AI chip uses light instead of metal wiring to manipulate light and can calculate instantly compared to a traditional computer that has to interpret light. As light travels through the new AI chip, it significantly speeds up the transmission process of data and also reduces the power needed for a calculation to be completed. While being a groundbreaking design with many implications for numerous computing fields, the new light-manipulating AI chip faces significant problems, one of which is scaling it at the product level.
The project, led by the University of Michigan, is backed by a $2 million grant from the National Science Foundation’s Future of Semiconductors program. It brings together researchers from the University of Washington, the University of Pennsylvania, and Lawrence Berkeley National Laboratory, with guidance from industry leaders including Google, Hewlett Packard Enterprise, Microsoft, and Nvidia.
Source: ScitechDaily.com; Stardrive.org