A numerical optimization-based methodology for application robustification: Transforming applications for error tolerance

Joseph Sloan, David Kesler, Rakesh Kumar, Ali Rahimi

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

Abstract

There have been several attempts at correcting process variation induced errors by identifying and masking these errors at the circuit and architecture level [10,27]. These approaches take up valuable die area and power on the chip. As an alternative, we explore the feasibility of an approach that allows these errors to occur freely, and handle them in software, at the algorithmic level. In this paper, we present a general approach to converting applications into an error tolerant form by recasting these applications as numerical optimization problems, which can then be solved reliably via stochastic optimization. We evaluate the potential robustness and energy benefits of the proposed approach using an FPGA-based framework that emulates timing errors in the floating point unit (FPU) of a Leon3 processor [11]. We show that stochastic versions of applications have the potential to produce good quality outputs in the face of timing errors under certain assumptions. We also show that good quality results are possible for both intrinsically robust algorithms as well as fragile applications under these assumptions.

Original languageEnglish (US)
Title of host publicationProceedings of the 2010 IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2010
Pages161-170
Number of pages10
DOIs
StatePublished - 2010
Event2010 IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2010 - Chicago, IL, United States
Duration: Jun 28 2010Jul 1 2010

Publication series

NameProceedings of the International Conference on Dependable Systems and Networks

Other

Other2010 IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2010
CountryUnited States
CityChicago, IL
Period6/28/107/1/10

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'A numerical optimization-based methodology for application robustification: Transforming applications for error tolerance'. Together they form a unique fingerprint.

Cite this