Deep Learning Based Test Compression Analyzer

Cheng-Hung Wu; Yu Huang; Kuen-Jong Lee; Wu-Tung Cheng; Gaurav Veda; Sudhakar Reddy; Chun-Cheng Hu; Chong-Siao Ye

doi:10.1109/ATS47505.2019.000-9

Back

Conference proceeding

Deep Learning Based Test Compression Analyzer

Cheng-Hung Wu, Yu Huang, Kuen-Jong Lee, Wu-Tung Cheng, Gaurav Veda, Sudhakar Reddy, Chun-Cheng Hu and Chong-Siao Ye

2019 IEEE 28th Asian Test Symposium (ATS), Vol.2019-, pp.1-15

12/2019

DOI: 10.1109/ATS47505.2019.000-9

View Online

Abstract

With the increase in design complexity and test data volume, compressed tests together with on-chip test decompression hardware such as Embedded Deterministic Test (EDTTM) are widely used in industry in order to reduce test cost. One of the challenges of such Design-for-Test (DFT) technology is to determine a set of optimal parameters such as the number of scan chains, scan channels, power budget, etc. such that it can reach the highest test coverage with a minimum amount of test data volume whilst satisfying various other constraints. To achieve the optimal compression configuration quickly, in this work deep learning technology based on Tensorflow is explored to estimate the test coverage and the data volume for a design when employing EDT under a given set of circuit parameters. Based on the estimated data, the optimal test architecture is also predicted, yielding a more efficient approach compared to the currently used trial-and-error methods. To demonstrate the advantages of our deep learning approach over the currently used utility, we present experimental data for eight industrial designs.

Neurons

Circuit faults

Cost function

Deep learning

DFT Configuration

Inference algorithms

Test Compression

Training

Training data

Details

Title: Subtitle: Deep Learning Based Test Compression Analyzer
Creators: Cheng-Hung Wu - National Cheng Kung University
Yu Huang - Mentor Graphics
Kuen-Jong Lee - National Cheng Kung University
Wu-Tung Cheng - Mentor Graphics
Gaurav Veda - Mentor Graphics
Sudhakar Reddy - University of Iowa
Chun-Cheng Hu - National Cheng Kung University
Chong-Siao Ye - National Cheng Kung University
Resource Type: Conference proceeding
Publication Details: 2019 IEEE 28th Asian Test Symposium (ATS), Vol.2019-, pp.1-15
DOI: 10.1109/ATS47505.2019.000-9
ISSN: 1081-7735
eISSN: 2377-5386
Publisher: IEEE
Language: English
Date published: 12/2019
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984197550302771

Metrics

31 Record Views

See more details