IIT-Guwahati researchers develop machine learning framework for semiconductor industry

Guwahati: Researchers at the Indian Institute of Technology, Guwahati (IIT-G) have developed an innovative machine learning framework named 'LEAP', marking a significant advancement in the field of Electronic Design Automation (EDA) used in the semiconductor industry.

The development of this cutting-edge solution enhances the design process of Integrated Circuits (ICs), a critical component in the $600 billion semiconductor industry that powers modern electronic devices, an official release said on Thursday.

Designing ICs involves navigating complex problems that can be challenging to solve and often yield less-than-ideal results.

A team of researchers, comprising Professor Chandan Karfa and Dr Sukanta Bhattacharjee of the Department of Computer Science and Engineering, along with BTech students Chandrabhushan Reddy Chigarapally and Harshwardhan Nitin Bhakkad, have leveraged machine learning to improve efficiency in IC design.

Another collaborator, Dr Animesh Basak Chowdhury of New York University, USA was also involved in the project.

The LEAP framework streamlines the technology mapping process within EDA, Karfa said.

"Rather than evaluating thousands of potential configurations, LEAP intelligently identifies and prioritises the most promising options, reducing the number of configurations the mapping tool must consider, by over 50 per cent," he said.

The framework not only speeds up the mapping process but also improves the performance of the circuits, he said.

LEAP estimates the delay for various configurations and selects only the top ten options for each node in the design, as compared to the traditional method, which typically evaluates around 250 configurations, Karfa said.

This targeted approach streamlines the workflow and enhances overall efficiency.

This research holds real-world implications for the semiconductor industry, which is essential for the development of electronic devices such as smartphones and computers.

It will lead to faster, more efficient electronic devices with lower energy consumption, ultimately benefiting consumers and driving innovation across various technology sectors.

The results of this work have been published in the ACM/IEEE International Conference on Computer-Aided Design (ICCAD 2024), the release added.