AI-based timing error modelling: a case study on a pipelined floating-point core

Styliani Tompazi*, Georgios Karakonstantis

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The adoption of aggressively down-scaled voltages along with worsening process variations render nanometer devices prone to timing errors that threaten system functionality [1] , [2]. Recent studies tried to predict timing errors using machine learning (ML), while considering some workload characteristics [3] , [4] , [5]. However, successfully training such models is challenging, since traditionally acquired samples are insufficient, especially in operating regions where timing errors occur rarely.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE 30th Symposium on Computer Arithmetic, ARITH 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages110
Number of pages1
ISBN (Electronic)9798350319224
ISBN (Print)9798350319231
DOIs
Publication statusPublished - 19 Mar 2024
Event30th IEEE Symposium on Computer Arithmetic, ARITH 2023 - Portland, United States
Duration: 04 Sept 202306 Sept 2023

Publication series

NameProceedings - IEEE Symposium on Computer Arithmetic (ARITH)
ISSN (Print)1063-6889
ISSN (Electronic)2576-2265

Conference

Conference30th IEEE Symposium on Computer Arithmetic, ARITH 2023
Country/TerritoryUnited States
CityPortland
Period04/09/202306/09/2023

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'AI-based timing error modelling: a case study on a pipelined floating-point core'. Together they form a unique fingerprint.

Cite this