Chisel: Reliability- and accuracy-aware optimization of approximate computational kernels

Sasa Misailovic, Michael Carbin, Sara Achour, Zichao Qi, Martin Rinard

Research output: Contribution to journalArticlepeer-review

Abstract

The accuracy of an approximate computation is the distance between the result that the computation produces and the corresponding fully accurate result. The reliability of the computation is the probability that it will produce an acceptably accurate result. Emerging approximate hardware platforms provide approximate operations that, inreturn for reduced energy consumption and/or increased performance, exhibit reduced reliability and/or accuracy. We present Chisel, asystem for reliability- and accuracy-aware optimization of approximate computational kernels that run on approximate hardware platforms. Given a combined reliability and/or accuracy specification, Chisel automatically selects approximate kernel operations to synthesize an approximate computation that minimizes energy consumption while satisfying its reliability and accuracy specification. We evaluate Chisel on five applications from the image processing, scientific computing, and financial analysis domains. The experimental results show that our implemented optimization algorithm enables Chisel to optimize our set of benchmark kernels to obtain energy savings from 8.7% to 19.8% compared to the original (exact) kernel implementations while preserving important reliability guarantees.

Original languageEnglish (US)
Pages (from-to)309-328
Number of pages20
JournalACM SIGPLAN Notices
Volume49
Issue number10
DOIs
StatePublished - Dec 31 2014
Externally publishedYes

Keywords

  • Approximate computing

ASJC Scopus subject areas

  • General Computer Science

Fingerprint

Dive into the research topics of 'Chisel: Reliability- and accuracy-aware optimization of approximate computational kernels'. Together they form a unique fingerprint.

Cite this