A comprehensive framework for cell-aware diagnosis of customer returns

d'Hondt, P.; Mhamdi, S.; Girard, Patrick; Virazel, Arnaud; Ladhar, Aymen

doi:10.1016/j.microrel.2022.114595

Cited by 2 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, defects in SoCs may also occur in sequential standard cells of logic blocks. In this section, we show how the previous diagnosis flow can handle sequential cells and related defects by adding new information to the training dataset [54].…”

Section: Diagnosis Of Defects In Sequential Cellsmentioning

confidence: 99%

“…The CA diagnosis flow described in Section 4.2.2 and targeting defects in both combinational and sequential cells of customer returns has been implemented in a Python program. For validation purpose, authors in [16,[49][50][51][52][53][54] have experimented the proposed flow in three different ways: • First, they conducted experiments on ITC'99 benchmark circuits with defect injection campaigns targeting combinational cells in each circuit. Various results are reported in [16,[49][50][51][52][53] to show the superiority of the framework when compared to commercial diagnosis solutions.…”

Section: Industrial Case Studiesmentioning

confidence: 99%

“…• Next, they considered a test chip developed by STMicroelectronics and designed using a 28 nm FDSOI technology, and they conducted two defect injection campaigns targeting sequential cells [54]. Results are reported in subsection 5.1 and also demonstrate the effectiveness of the diagnosis framework.…”

Section: Industrial Case Studiesmentioning

confidence: 99%

“…Authors in [54] A first simulated case study was done with a static defect injection campaign. All possible static defects were successively injected into three scan flip-flops (SFF) of a single full-scan digital block.…”

Section: Simulated Test Case Studiesmentioning

confidence: 99%

“…Next, a silicon case study was performed on a customer return designed with a 28 nm FDSOI technology from STMicroelectronics [54]. The test conditions used to run the experiments were as follows: a nominal supply voltage of 0.83 V, a scan test frequency of 10 MHz, a launch-to-capture clock speed (for the dynamic CA test sequence application) adjusted with respect to the nominal clock frequency of the circuit, and a temperature of 25°C.…”

Section: Silicon Test Case Studymentioning

confidence: 99%

See 4 more Smart Citations

Defect Diagnosis Techniques for Silicon Customer Returns

Girard¹,

Bosio²,

Ladhar³

et al. 2023

Frontiers of Quality Electronic Design (QED)

View full text Add to dashboard Cite

This chapter provides an overview of the various approaches and techniques proposed so far for defect diagnosis in silicon customer returns. It focuses on diagnosis of defects in logic blocks of SoCs. After some backgrounds on test and fault diagnosis, the chapter presents the various test scenarios used in practice during customer return diagnosis. A discussion on the quality required by the test sequences used during customer return is also proposed. Then, the chapter reviews the stateof-the-art techniques existing to identify defects at the cell level (called intra-cell or cell-aware diagnosis). A summary of conventional approaches is first proposed. Then, the latest Machine Learning (ML) -based cell-aware diagnosis techniques are reviewed. Effectiveness of existing ML techniques is shown through industrial case studies and corresponding diagnosis results in terms of accuracy and resolution. The chapter ends with a discussion on the future directions in this field.

show abstract

Section: Diagnosis Of Defects In Sequential Cellsmentioning

confidence: 99%

Section: Industrial Case Studiesmentioning

confidence: 99%

Section: Industrial Case Studiesmentioning

confidence: 99%

Section: Simulated Test Case Studiesmentioning

confidence: 99%

Section: Silicon Test Case Studymentioning

confidence: 99%

See 3 more Smart Citations

Defect Diagnosis Techniques for Silicon Customer Returns

Girard¹,

Bosio²,

Ladhar³

et al. 2023

Frontiers of Quality Electronic Design (QED)

View full text Add to dashboard Cite

show abstract

Machine Learning Support for Cell-Aware Diagnosis

Ladhar¹,

Virazel

2023

Machine Learning Support for Fault Diagnosis of System-on-Chip

View full text Add to dashboard Cite

This chapter will provide an overview of the various machine learning approaches and techniques proposed to support cell-aware generation, test, and diagnosis. The chapter will focus on the generation of the cell-aware models and their usage for diagnosis. After some backgrounds on conventional approaches to generate and diagnose cell-aware defects, the chapter will present a learning-based solution to generate cell-aware models. Then, the chapter will present a ML-based cell-aware diagnosis technique. Effectiveness of existing techniques will be shown through industrial case studies and corresponding diagnosis results in terms of accuracy and resolution. The chapter will conclude by a discussion on the future directions in this field.

show abstract

A comprehensive framework for cell-aware diagnosis of customer returns

Cited by 2 publications

References 27 publications

Defect Diagnosis Techniques for Silicon Customer Returns

Defect Diagnosis Techniques for Silicon Customer Returns

Machine Learning Support for Cell-Aware Diagnosis

Contact Info

Product

Resources

About