Error resilient and energy efficient MRF message-passing-based stereo matching

Eric P. Kim, Jungwook Choi, Naresh R. Shanbhag, Rob A. Rutenbar

Research output: Contribution to journalArticlepeer-review

Abstract

Message-passing-based inference algorithms have immense importance in real-world applications. In this paper, error resiliency of a message passing based Markov random field (MRF) stereo matching hardware is explored and enhanced through the application of statistical error compensation. Error resiliency is of particular interest for subnanometer and postsilicon devices. The inherent robustness of iteration-based MRF inference algorithms is explored and shows that small errors are tolerable, while large errors degrade the performance significantly. Based on these error characteristics, algorithmic noise tolerance (ANT) has been applied at the arithmetic, iteration, and system levels. Introducing timing errors via voltage overscaling, at the arithmetic level, results show that the ANT-based hardware can tolerate an error rate of 21.3%, with performance degradation of only 3.5% at an overhead of 97.4%, compared with an error-free hardware with an energy savings of 39.7%. To reduce compensation complexity, iteration and system-level compensation was explored. Results show that, compared with arithmetic level, system-level compensation reduces overhead to 59%, while maintaining stereo matching performance with only 2.5% degradation with 16% additional power savings. These results are verified via FPGA emulation with timing errors induced within the message passing unit via relaxed synthesis.

Original languageEnglish (US)
Article number2437331
Pages (from-to)897-908
Number of pages12
JournalIEEE Transactions on Very Large Scale Integration (VLSI) Systems
Volume24
Issue number3
DOIs
StatePublished - Mar 2016

Keywords

  • Algorithmic noise tolerance (ANT)
  • Error resilience
  • Markov random field (MRF)
  • Message passing
  • Stereo matching

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Error resilient and energy efficient MRF message-passing-based stereo matching'. Together they form a unique fingerprint.

Cite this