Minimum Operating Voltage Prediction in Production Test Using Accumulative Learning

We propose a new methodology to predict minimum operating voltage (V min ) for production chips. In addition, we propose two new key features to improve the prediction accuracy. Our proposed accumulative learning can reduce the impact of lot-to-lot variations. Experimental results on two 7nm industr...

Full description

Saved in:
Bibliographic Details
Main Authors: Kuo, Yen-Ting, Lin, Wei-Chen, Chen, Chun, Hsieh, Chao-Ho, Li, James Chien-Mo, Jia-Wei Fang, Eric, Hsueh, Sung S.-Y.
Format: Conference Proceeding
Language:English
Subjects:
Chip Performance Prediction
Conferences
Industries
Machine Learning
Process variation
Ring oscillators
Semiconductor device modeling
Training
Training data
Voltage
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a new methodology to predict minimum operating voltage (V min ) for production chips. In addition, we propose two new key features to improve the prediction accuracy. Our proposed accumulative learning can reduce the impact of lot-to-lot variations. Experimental results on two 7nm industry designs (about 1.2M chips from 142 lots) show that we can achieve above 95% good prediction. Our methodology can save 75% test time compared with traditional testing. To implement this method, we will need to have a separate test flow for the initial training and accumulative training.
ISSN:2378-2250
DOI:10.1109/ITC50571.2021.00012