Argus-G: Comprehensive, low-cost error detection for GPGPU cores


Journal Article

© 2014 IEEE. We have developed and evaluated Argus-G, an error detection scheme for general purpose GPU (GPGPU) cores. Argus-G is a natural extension of the Argus error detection scheme for CPU cores, and we demonstrate how to modify Argus such that it is compatible with GPGPU cores. Using an RTL prototype, we experimentally show that Argus-G can detect the vast majority of injected errors at relatively low performance, area, and power costs.

Full Text

Duke Authors

Cited Authors

  • Nathan, R; Sorin, DJ

Published Date

  • January 1, 2015

Published In

Volume / Issue

  • 14 / 1

Start / End Page

  • 13 - 16

International Standard Serial Number (ISSN)

  • 1556-6056

Digital Object Identifier (DOI)

  • 10.1109/LCA.2014.2298391

Citation Source

  • Scopus