Automating Design for Yield: Silicon Learning to Predictive Models and Design Optimization

Srikanth Venkat Raman, Pongpachara Limpisathian, Pascal Meinerzhagen, Suriyaprakash Natarajan, Eric Yang

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

2 Scopus citations


We propose a framework to co-optimize Yield along with Power, Performance and Area (PPA) through the design flow from logic synthesis through placement and routing (APR). We accomplish this by learning from silicon using a combination of test/diagnosis, inline/metrology and Failure Analysis (FA) results to create predictive models using Machine Learning (ML) techniques that are then used during design. Simulation results across three different CPU and Graphics cores show promising results with projected yield improvements of 11-17% with no area and performance / timing penalty with respect to design targets but with tradeoffs to both static and dynamic power. Better joint exploration of the PPA space along with yield indicates it is possible to recover yield with close to iso-PPA with respect to design targets. Pre-silicon results show \sim 10.4% yield increase with iso-Area and-iso-performance and \sim 1% power penalty on a processor core.

Original languageEnglish
Title of host publication2020 IEEE International Test Conference, ITC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728191133
StatePublished - 1 Nov 2020
Externally publishedYes
Event2020 IEEE International Test Conference, ITC 2020 - Washington, United States
Duration: 1 Nov 20206 Nov 2020

Publication series

NameProceedings - International Test Conference
ISSN (Print)1089-3539


Conference2020 IEEE International Test Conference, ITC 2020
Country/TerritoryUnited States

Bibliographical note

Publisher Copyright:
© 2020 IEEE.


  • APR
  • Defect Avoidance
  • Design Optimization
  • Design-for-Manufacturability (DFM)
  • Design-for-Yield (DFY)
  • Diagnosis
  • Logic Synthesis
  • PPA
  • Yield Improvement


Dive into the research topics of 'Automating Design for Yield: Silicon Learning to Predictive Models and Design Optimization'. Together they form a unique fingerprint.

Cite this