CogniVision‎ > ‎

CogniVision News


Research Programme in Energy-autonomous always-on cognitive and attentive cameras for distributed real-time vision with milliwatt power consumption


HOME  |  SUB-PROJECTS  |  TEAM  |  IMPACT  |  NEWS  |  INDUSTRY ENGAGEMENT  |  CAREERS  |  CONTACTS  |  FOLLOW

Novel class of data converters that can be designed with fully-automated digital design flows for design turnaround time down to a few hours instead of months

posted May 21, 2020, 5:55 PM by Green IC group ‎(www.green-ic.org)‎

A new class of sensor interfaces cuts down the design effort from months to hours, reduces circuit complexity by at least 30 times, while being highly robust against wide fluctuations in power harvested from the environment.

The Green IC research group in the Department of Electrical and Computer Engineering at the National University of Singapore’s (NUS) Faculty of Engineering invented a novel class of Digital-to-Analog (DAC) and Analog-to-Digital Converters (ADC) that can be entirely designed with a fully-automated digital design methodology, thanks to its fully-digital architecture.

The NUS Green IC team: Dr Orazio Aiello (left) and Associate Professor Massimo Alioto (right)


Compared to traditional analog architectures and methodologies, the design turnaround time for these novel sensor interfaces is reduced from months to hours. The drastic reduction in the design effort is highly beneficial in cost-sensitive silicon systems, such as sensors for the Internet of Things (IoT). The novel data converter architecture also has very low complexity, reducing the silicon area and hence the manufacturing cost by at least 30 times, compared to conventional designs.

First microprocessor with energy-performance tradeoff wider than voltage scaling for faster operation and longer battery life

posted May 21, 2020, 5:42 PM by Green IC group ‎(www.green-ic.org)‎   [ updated May 21, 2020, 6:16 PM ]

A team of researchers from NUS have invented a novel class of reconfiguration techniques that adaptively extends both the minimum power consumption and the maximum performance of digital circuits, well beyond common voltage scaling. Such extended adaptation allows digital silicon chips to operate at lower power during normal use, and at higher performance level when necessary. 

This extends the battery life under uncertain power availability in systems powered by harvesters (e.g. solar cell) or rechargeable batteries, while delivering higher peak performance to carry out on-chip data analytics upon the occurrence of events of interest. This is a key enabler for applications such as Internet of Things (IoT), artificial intelligence (AI), wearables and biomedical devices. 


Assoc Prof Massimo Alioto (centre) and his team members Lin Longyang (left) and Saurabh Jain (right) showing off the prototyping boards 
for testing the silicon chips to demonstrate highly flexible power and performance, surpassing industry-standard voltage scaling.


“Our reconfiguration techniques introduce unprecedented adaptability to fluctuating power availability and performance demand. Compared to the industry-standard voltage scaling technique, measurements on several test chips in our lab have shown that such adaptation extends the battery life of a mobile or wearable device by 1.5 times, while doubling peak performance. Our techniques can also be used to further miniaturise the battery by the same factor, while maintaining the same battery life,” explained Associate Professor Massimo Alioto, from NUS Engineering. He is the leader of the NUS Green IC Group that is behind this technological breakthrough. 


Read more on: https://news.nus.edu.sg/research/enabling-battery-powered-silicon-chips-work-faster-and-longer

1-2 of 2