Artificial Intelligence in Semiconductor Production : Sustaining Moore’s Law

Sammanfattning

The semiconductor industry has since the 1960s been following the pace set by Moore’s Law. In recent years, artificial intelligence, specifically machine learning and deep learning, has started to become commonly used in the semiconductor industry. This thesis aims to examine how artificial intelligence is being used in the production processes of semiconductors and how the effects of using it will lead to the continuation of Moore’s Law. The study focuses on three areas where artificial intelligence is being used in production which are chip design, defect inspection, and predictive maintenance. Through a literature review, the thesis highlights the advantages found by the integration of artificial intelligence in the three areas. Artificial intelligence in chip design leads to an optimized design process resulting in improved power, performance, and area metrics. Additionally, artificial intelligence enhances defect inspection by identifying defects more precisely and reducing false positives. Predictive maintenance powered by artificial intelligence leads to a maximized runtime while reducing unscheduled downtime by predicting equipment failure. The findings indicate that artificial intelligence contributes to the efficiency and reliability of semiconductor production. Moreover, it allows increase in costs while improving performance and thereby supporting the continuation of Moore’s Law.