Challenges in Machine Learning Techniques to Estimate Reliability from Transistors to Circuits

Victor M. Van Santen, Florian Klemme, Paul R. Genssler, Hussam Amrouch

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Transistor and circuit reliability estimations face various challenges in both traditional and machine learning (ML) based approaches. In this work, we provide an overview of the toughest challenges faced by traditional physics-based reliability estimations, such as exposing sensitive transistor data, unfeasible execution times, material defect interactions, etc. Similarly, challenges for ML-based approaches are also highlighted, such as the aging recovery and history effects and high training effort. We present multiple solutions to overcome these challenges, such as high-performance physics-based aging models, history-aware machine learning, and techniques to reduce training data sets. We highlight, for the first time, that circuit reliability estimation can be achieved by bypassing the transistor level with ML-generated degraded standard cell libraries. Our high-performance aging models and circuit simulators provide speedups ranging from 4000x to 240,000x, while our standard cell ML techniques achieve 99.9% accuracy in less than 1 second inference time.

Original languageEnglish
Title of host publication36th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2023
EditorsLuca Cassano, Mihalis Psarakis, Marcello Traiola, Alberto Bosio
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350315004
DOIs
StatePublished - 2023
Event36th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2023 - Juan-Les-Pins, France
Duration: 3 Oct 20235 Oct 2023

Publication series

NameProceedings - IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT
ISSN (Print)2576-1501
ISSN (Electronic)2765-933X

Conference

Conference36th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2023
Country/TerritoryFrance
CityJuan-Les-Pins
Period3/10/235/10/23

Keywords

  • Aging
  • Bias Temperature Instability
  • Circuit Reliability
  • Degradation
  • Hot-Carrier
  • Machine Learning
  • Reliability
  • Self-Heating
  • Transistor Reliability

Fingerprint

Dive into the research topics of 'Challenges in Machine Learning Techniques to Estimate Reliability from Transistors to Circuits'. Together they form a unique fingerprint.

Cite this