Researchers from the National University of Singapore (NUS) have developed a method to transfer bits across a silicon chip up to five times more efficiently than standard setups.
Said NUS professor Massimo Alioto, "Our silicon chip demonstration sets a new standard for power efficiency, without modifying the building blocks, such as transmitters and receivers, that are typically used in these setups, allowing its easy adoption in existing designs.
"Given that power, performance and cost are all fundamental drivers of artificial intelligence applications, our invention simplifies the integration of next-generation intelligent systems."
The researchers developed a network-on-chip that dramatically reduces power consumption without a significant loss in quality.
The invention is a key development toward the demonstration of a full "computer vision system" in which all components are energy-quality scalable and simultaneously adjusted to operate at the lowest power while maintaining an acceptable level of accuracy.
From NUS News (Singapore)
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA