Researchers at the University of Wisconsin-Madison are developing powerful multi-duty computer chips by combining tasks that are normally kept separate by design. They are creating computer chips that can be configured to perform complex calculations and store huge amounts of information within the same integrated unit, all the while communicating efficiently with other chips.
Jing Li, an assistant professor of electrical and computer engineering at UW-Madison who is creating the new computer chips, calls them “liquid silicon”. “Liquid means software and silicon means hardware. It is a collaborative software/hardware technique,” she says. “You can have a supercomputer in a box if you want. We want to target a lot of very interesting and data-intensive applications, including facial or voice recognition, natural language processing, and graph analytics.”
As the researchers explain, there’s a huge bottleneck when traditional computers move data between memory and processors. However, the future computer chip will basically bridge the gap between computation and storage and therefore make the entire process more efficient.
The new chips incorporate memory, computation and communication into the same device using a layered design named monolithic 3D integration. Importantly, the device will be dynamic and flexible as it allows optimization.