AI-Enabled VLSI Testing​

This course was developed as a MEST Micro-Certificate. MEST Micro-Certificates offer short, self-paced learning opportunities through focused training modules and webinars on specialized technical topics. Participants who successfully complete the program requirements earn a certificate of completion.

These programs are designed for U.S. citizens, including Department of War and other government personnel, government-affiliated employees, industry professionals, college students, and faculty.


VLSI testing is the process of detecting defects that typically occur during or after the manufacturing of integrated circuits (ICs). This hands-on course certificate introduces participants to AI-assisted VLSI testing, covering the integration of artificial intelligence across key stages of the testing process. Participants will explore AI-driven automatic test pattern generation, test pattern optimization and test point insertion. Through practical examples and guided activities, the workshop will demonstrate how AI can improve test efficiency, fault coverage, and automation in modern VLSI testing workflows.

VLSI testing seeks to identify manufacturing defects and ensure that fabricated integrated circuits operate according to their intended design specifications. Automatic Test Pattern Generation (ATPG) plays a central role in this process by generating input patterns that detect modeled faults within a circuit. In this course, we will discuss the foundational concepts of VLSI testing, explore AI-assisted test pattern generation, and examine machine learning-based approaches for test pattern optimization. Additionally, the course will explore how AI can complement conventional commercial ATPG tools by generating candidate patterns for hard-to-detect faults and reducing redundant test patterns while preserving fault coverage. The course includes a series of hands-on simulation and implementation exercises that provide practical experience with the key concepts discussed.

This course is divided into 3 modules:

  • Unit 1: Basics of VLSI Testing: This section introduces the fundamentals of VLSI testing, including stuck-at fault models, fault detection, and basic ATPG, with hands-on test generation using Synopsys TestMAX.

  • Unit 2: Automatic Test Pattern Generation Using AI: This section explains role of Artificial Intelligence (AI) in addressing the limitations of traditional ATPG test pattern generation techniques. This includes a demonstration on how AI models can assist in identifying hard-to-detect faults and generating test input patterns that improve fault detection.

  • Unit 3: AI-based Test Pattern Optimization: This section focuses on reducing the size and complexity of test sets while preserving fault coverage. Trainees will explore techniques for identifying redundant or low-value test patterns and selecting compact subsets of patterns using machine learning models.statistical metrics, including the uniqueness and reliability of the PUF.

Format: Online, asynchronous
Platform: nanoHUB Learning Management System
Estimated Time: 10-12 hours
Level: Advanced Undergraduate/Graduate Student
Prerequisites:

  • A basic understanding of circuits, logic gates, and VLSI testing is required.

  • A basic understanding of Linux systems is recommended.

  • Familiarity with machine learning concepts is helpful but not required.

  • A basic knowledge of Tcl scripting is required.

  • Experience with commercial ATPG or EDA tools such as Synopsys TestMAX or TetraMAX is helpful but not required.

Instructor: Associate Professor Ujjwal Guin, Auburn University


Course Objectives:

  1. Design AI models for VLSI testing

  2. Analyze test coverage metrics

  3. Explain the integration of AI into VLSI test flow

 

Request Course Enrollment

To enroll in this course, you must have a nanoHUB account. Create one here: https://nanohub.org/register/
Request membership in the MEST group in nanoHUB at https://nanohub.org/groups/mest

Next
Next

Introduction to Large Language Models (LLMs)