Download PDFOpen PDF in browser

Improving GPU Register File Reliability With a Comprehensive ISA Extension

EasyChair Preprint 4636

2 pagesDate: November 23, 2020

Abstract

This work proposes a comprehensive ISA extension to improve GPU reliability to transient effects. Three additional instructions are proposed, implemented, and combined with software-based datapath duplication. Modified program codes are compared to state-of-the-art software-based fault tolerance techniques in terms of execution time, the circuit area is evaluated against the original GPU architecture, and a fault injection campaign is performed to assess reliability. Results show that the proposed ISA extension improves the performance of software-based approaches while maintaining fault detection capabilities at negligible costs in the circuit area. This work can help engineers in designing more efficient and resilient GPU architectures.

Keyphrases: GPU, ISA extension, fault tolerance, hardening techniques

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:4636,
  author    = {Marcio Gonçalves and Josie Esteban Rodriguez Condia and Matteo Sonza Reorda and Luca Sterpone and Jose Rodrigo Azambuja},
  title     = {Improving GPU Register File Reliability With a Comprehensive ISA Extension},
  howpublished = {EasyChair Preprint 4636},
  year      = {EasyChair, 2020}}
Download PDFOpen PDF in browser