The MIT engineers hope that the LEGO-like design could help reduce waste by making devices easier to upgrade, by making it possible to simply clip on the latest sensors and processors.
According to MIT, the design comprises alternating layers of sensing and processing elements, along with LEDs that allow for the chip’s layers to communicate optically.
The AI chip’s design differs from other modular chips, which rely on conventional wiring to relay signals between layers.
The wired connections are difficult if not impossible to sever and rewire, making it impossible to reconfigure these kinds of stackable designs.
Instead of physical wires, the MIT design uses light to transmit information through the chip, which means the chip is reconfigurable, with layers that can be swapped out or stacked on, for example to add new sensors or updated processors.
“You can add as many computing layers and sensors as you want, such as for light, pressure, and even smell,” says Jihoon Kang, a MIT postdoctoral student and part of the team behind the chip. “We call this a LEGO-like reconfigurable AI chip because it has unlimited expandability depending on the combination of layers.”
The researchers think the design would be particularly suited to edge computing devices, such as self-sufficient sensors and other electronics that work independently from any central or distributed resources such as supercomputers or cloud-based computing.
“As we enter the era of the internet of things based on sensor networks, demand for multi-functioning edge-computing devices will expand dramatically,” says Jeehwan Kim, associate professor of mechanical engineering at MIT. “Our proposed hardware architecture will provide high versatility of edge computing in the future.”
The team’s results were published in Nature Electronics.