Machine Intelligence in Design Automation

by Rohit Sharma

This book presents a hands-on approach for solving design automation problems with modern machine intelligence techniques by including step-by-step development of commercial grade design applications including resistance estimation, capacitance estimation, cell classification and others using dataset extracted from designs at 20nm. It walks the reader step by step in building solution flow for EDA problems with Python and Tensorflow.

Intended audience includes design automation engineers, managers, executives, research professionals, graduate students, Machine learning enthusiasts, CAD developers, mentors, and the merely inquisitive. It is organized to serve as a compendium to a beginner, a ready reference to intermediate and source for an expert.

221 pages, Paperback

Published March 13, 2018

About the author

Rohit Sharma is an engineer, author and entrepreneur. He has published over 10 papers in international conferences and journals. He has contributed to electronic design automation domain for over 20 years learning, improvising and designing solutions. He is passionate about many technical topics including machine learning, analysis, characterization, and modeling. It led him to architect guna - an advanced characterization software for modern nodes. He currently works for Paripath Inc. (www.paripath.com) - a company he founded.

Reviews

[Rohit Sharma · Rating 5 out of 5]

This is biased review. Consider yourself cautioned.

This book is motivated by a desire to fill the gap in use of machine intelligence in design automation; a topic largely absent from the press and academia. Machine Intelligence is advancing at a rapid pace and claim to this fame is that it is bound to enable an unprecedented degree of automation in every walk of life. Design automation, a field that has been automating semiconductor design for decades, continues to ignore machine learning.

[Josephine Charles · Rating 5 out of 5]

must have book for every VLSI and CAD enginee