IIT Hyderabad researchers develop low power chips

Researchers at the Indian Institute of Technology (IIT) Hyderabad have developed low power chips that can be used in Artificial Intelligence (AI) powered devices. These researchers have developed magnetic quantum-dot cellular automata (MQCA) based nanomagnetic logic architectural design methodology of approximate arithmetic circuits, according to a release shared by the institute.

The researchers are working towards resource constrained magnetic chips for ultra low power portable AI applications. Many systems such as speech and face recognition systems and IoT enabled devices for remote health monitoring normally require highly computationally and energy-intensive neural networks making it difficult to to perform these computations on the portable hand-held devices.

"We now aim for a bigger goal by porting some power-hungry AI applications on such indigenously developed ultra-low-power computing platform,” said Santhosh Sivasubramani, one of the researchers in the team. The other researchers in the team at IIT Hyderabad include Amit Acharyya, associate professor and Chandrajit Pal, post-doctoral research fellow.


The IIT Hyderabad researchers from the Advanced Embedded Systems and IC Design Laboratory, Department of Electrical Engineering, have conducted research in this area. “Performing AI computing on edge with approximate nanomagnetic logic deployed on the magnetic ICs is an attempt towards the futuristic computations,” Acharyya said.