The world demand for faster, more energy-efficient information processing is growing exponentially. While much processing is done in the cloud today, there is significant motivation for moving it to the “edge”, where sensors and integrated processing hardware work together to develop intelligent responses. Conventional digital processing hardware cannot keep up with this demand, and so researchers are considering alternatives that take inspiration from the brain, where massively connected networks of artificial neurons and synapses process information with extremely high energy efficiency. The new hardware devices, architectures and algorithms being developed have entirely new functionality, which requires creation of a whole new set of measurement techniques and protocols. This program is aimed at developing the necessary device-level and circuit-level measurements and theory to support the evolution of this technology from laboratory research to commercial application.
The Alternative Computing Group focuses on three main areas of next-generation computing hardware research: