Electronic Design Automation (EDA) tools are inherently complex, and integrating a machine learning framework like LEAP required a deep understanding of both EDA processes and machine learning algorithms. For the IIT Guwahati researchers, balancing the trade-offs between runtime efficiency and performance improvements was a significant challenge. The researchers had to ensure that reducing the runtime of EDA tools did not compromise the performance of the integrated circuits.
Prof. Chandan Karfa, Associate Professor, and Dr. Sukanta Bhattacharjee, Assistant Professor from the Department of Computer Science and Engineering at IIT Guwahati, along with their BTech students Chandrabhushan Reddy Chigarapally and Harshwardhan Nitin Bhakkad, have utilised machine learning to enhance efficiency in IC design.
Collaborating with Dr. Animesh Basak Chowdhury from New York University, USA, they developed the LEAP framework. LEAP significantly reduces the runtime of Electronic Design Automation (EDA) tools by 50%. This means that the design process becomes much faster and more efficient.
The framework also decreases the clock period by 2%, which improves the performance of the circuits without increasing the area required.
LEAP streamlines the technology mapping process within EDA by intelligently identifying and prioritizing the most promising configurations. This reduces the number of configurations the mapping tool must consider by over 50%.
This development is a significant advancement in the field of Electronic Design Automation, benefiting the $600 billion semiconductor industry by enhancing electronic device performance while reducing energy consumption.
Advertisements