Qualcomm incorporated (20240320408). MACHINE-LEARNING-BASED INTEGRATED CIRCUIT TEST CASE SELECTION simplified abstract

MACHINE-LEARNING-BASED INTEGRATED CIRCUIT TEST CASE SELECTION

Organization Name

qualcomm incorporated

Inventor(s)

Gokce Sarar of San Diego CA (US)

Guillaume Shippee of La Jolla CA (US)

Rhys Buggy of Enniskerry (IE)

Santanu Pattanayak of Bangalore (IN)

Tushit Jain of Bangalore (IN)

Suman Kumar Gunnala of San Diego CA (US)

Kumar Raj of San Diego CA (US)

Vatsal Nimeshkumar Thakkar of Longmont CO (US)

MACHINE-LEARNING-BASED INTEGRATED CIRCUIT TEST CASE SELECTION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240320408 titled 'MACHINE-LEARNING-BASED INTEGRATED CIRCUIT TEST CASE SELECTION

The abstract of this patent application describes techniques and apparatus for testing integrated circuit designs. A method involves generating a coverage matrix for test cases and coverage points, selecting a subset of test cases for execution based on weights and a threshold value, and testing the integrated circuit based on the selected subset.

• Machine learning model trained on the coverage matrix provides weights for each test case.
• Subset of test cases selected for execution based on weights and threshold value.
• Integrated circuit testing based on the selected subset of test cases.

Potential Applications: - Quality assurance in integrated circuit design. - Optimization of testing processes for integrated circuits.

Problems Solved: - Efficient selection of test cases for integrated circuit testing. - Improved coverage and accuracy in testing procedures.

Benefits: - Enhanced reliability of integrated circuit designs. - Time and cost savings in testing processes.

Commercial Applications: Title: "Advanced Integrated Circuit Testing Technology for Enhanced Reliability" This technology can be utilized by semiconductor companies to improve the quality and efficiency of integrated circuit testing, leading to more reliable products and cost-effective manufacturing processes.

Questions about Integrated Circuit Testing Technology: 1. How does machine learning play a role in selecting test cases for integrated circuit testing? Machine learning models are trained on coverage matrices to assign weights to test cases, enabling the selection of a subset for execution based on these weights.

2. What are the potential advantages of using a subset of test cases for integrated circuit testing? By selecting a subset of test cases based on weights and a threshold value, testing processes can be optimized for efficiency and accuracy, leading to improved reliability in integrated circuit designs.

Original Abstract Submitted

certain aspects of the present disclosure provide techniques and apparatus for testing integrated circuit designs. an example method generally includes generating a coverage matrix associated with a plurality of test cases for an integrated circuit and coverage points associated with each test case of the plurality of test cases. a subset of the plurality of test cases is selected for execution based on weights associated with each test case of the plurality of test cases and a threshold weight value. generally, the weights associated with each test case comprise weights in a machine learning model trained based on the coverage matrix. the integrated circuit may be tested based on the selected subset of test cases.