IIT Guwahati's ‘LEAP’ Framework Set to Accelerate Progress in the Semiconductor Industry

IIT Guwahati researchers have developed 'LEAP,' a ML framework for Electronic Design Automation, with implications for the semiconductor industry, crucial for electronic devices like smartphones and computers.

IIT Guwahati's ‘LEAP’ Framework

Researchers at the Indian Institute of Technology (IIT) Guwahati have achieved a breakthrough in Electronic Design Automation (EDA) by developing an innovative machine learning (ML) framework called ‘LEAP’. This state-of-the-art solution significantly improves the design process of Integrated Circuits (ICs), a vital component in the $600 billion semiconductor industry that drives today’s electronic devices.

LEAP optimises the design process by estimating delays for various configurations and narrowing down the choices to the top ten for each node, in contrast to the traditional method that typically evaluates around 250 configurations. This focused approach streamlines the workflow and significantly boosts overall efficiency. Their LEAP framework streamlines the technology mapping process within EDA. Rather than evaluating thousands of potential configurations, LEAP intelligently identifies and prioritizes the most promising options, reducing the number of configurations the mapping tool must consider by over 50%.

To address these challenges, Prof. Chandan Karfa, Associate Professor and Dr. Sukanta Bhattacharjee, Assistant Professor, Department of Computer Science and Engineering, IIT Guwahati along with their BTech students Chandrabhushan Reddy Chigarapally, Harshwardhan Nitin Bhakkad, have leveraged machine learning to improve efficiency in IC design. The other collaborator is Dr. Animesh Basak Chowdhury of New York University USA.

Regarding the research, Prof. Chandan Karfa said, "Our framework not only speeds up the mapping process but also improves the performance of the circuits. We have reduced the runtime of the EDA tool by 50% and achieved a 2% reduction in clock period without increasing the area required for the circuits, making our solution a significant advancement in electronic design automation."

This research has significant real-world implications for the semiconductor industry, which is crucial for developing electronic devices like smartphones and computers. By optimizing the design process for ICs through the LEAP framework, researchers can reduce design time and enhance performance. This leads to faster, more efficient electronic devices with lower energy consumption, benefiting consumers and driving innovation across multiple technology sectors.

In extensive testing on 21 different designs, the LEAP framework demonstrated a 50% improvement in runtime while reducing the number of configurations checked by over 51%. Compared to exhaustive mapping methods, LEAP achieves similar performance results while using 63% fewer configurations, significantly improving the runtime of the open-source ABC EDA tool.

Read More

• IIT Guwahati Celebrates Silver Jubilee Reunion for Inaugural Class of 1995-1999
• IIT Guwahati Drives Educational Innovation in Meghalaya with Rashtriya Avishkar Abhiyan