GPMS TRANSPORTAL APPLIED AI COURSES

• This course introduces how AI can enhance chip design, focusing on automation in layout planning, circuit optimization, and predicting chip behavior. It covers fundamental AI principles applied to semiconductors and practical tools for chip design using AI technologies.
• Level: Basic - Mandatory - Introduction
• Prerequisites: Basic understanding of electronics and semiconductors. No coding experience needed; will be built during the course.
• Assessments: Micro Assessment weekly, Full Assessment in the final week.

---

Week 1 - Fundamentals of Chip Design with AI

Learning Outcome

Students will learn how AI is integrated into the chip design process, with an emphasis on design automation.

1.1 Introduction to Chip Design and its challenges.
1.2 Role of AI in Semiconductor Design (Layout, Routing).
1.3 Overview of tools used in AI-driven chip design (E.g., AI-enhanced Electronic Design Automation - EDA).

Practical Component
Practical demos on AI algorithms used in chip design tools. Students will simulate basic design changes using AI software.

---

Week 2 - AI for Circuit Optimization and Validation

Learning Outcome

Students will understand how AI helps in optimizing circuits for performance, power consumption, and area (PPA).

2.1 Power, Performance, and Area (PPA) optimization in chip design.
2.2 AI for automating validation processes.
2.3 Machine Learning algorithms for design rule checks.

Practical Component
Hands-on exercises optimizing a circuit design using AI-based techniques for PPA.

---

Week 3 - Machine Learning for Chip Layout and Floorplanning

Learning Outcome

Understanding AI's role in automating the layout process, including placement, routing, and congestion prediction.

3.1 Machine learning models for predicting floorplan efficiency.
3.2 AI-enhanced tools for placement and routing.
3.3 Optimization using deep learning in chip design.

Practical Componenet
Students will use AI tools to improve floorplan efficiency and perform routing tasks.

---

Week 4 - AI-Powered Simulation and Performance Prediction

Learning Outcome

Learn how AI simulates chip performance and predicts behavior under various conditions.

4.1 AI-driven performance prediction models.
4.2 Machine learning for electrical simulation.
4.3 Using AI to predict thermal behavior and power consumption.

Practical Componenet
Apply AI models to predict chip performance in different real-world scenarios.

---

Week 5 - AI-Driven Chip Testing and Failure Prediction

Learning Outcome

Learn how AI assists in testing chips for defects, faults, and failures before production.

5.1 Using AI for defect detection in chip design.
5.2 Machine learning for failure prediction based on simulation data.
5.3 Automated testing and validation of chip designs.

Practical Component
Hands-on learning using AI for automated testing and defect detection in a virtual chip design.

---

Week 6 - CCapstone Project and Assessment

Learning Outcome

Students will work on a complete chip design project, integrating AI tools for optimization, testing, and simulation.

6.1 Integrating AI tools in the full chip design flow.
6.2 Self-assessment and peer review.
6.3 Final project presentation and feedback.

Practical Component
Students will complete a full chip design cycle using AI tools, including layout, optimization, testing, and performance prediction.

---