Matches in SemOpenAlex for { <https://semopenalex.org/work/W2019575743> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2019575743 abstract "Modern nanoscale processes exhibit stochastic behavior that can no longer be ignored. Statistical error compensation (SEC) has shown significant benefits in achieving energy efficiency and error resiliency by embracing the stochastic nature of the underlying process. Approximate computing (AC), on the other hand, employs deterministic designs that produce imprecise results to achieve energy efficiency. In this paper, we bridge the two design paradigms by utilizing SEC and AC in the design of a machine learning accelerator core. ANT, a form of SEC, was applied to an AC based stereo image matching implementation in a 45 nm process. Simulation results show that ANT combined with AC achieves energy savings of 44% compared to a conventional system, and 32.7% compared to an AC only system, while its performance degradation is less than 4%. This result shows that embracing the stochasticity of the architecture is crucial in achieving high energy efficiency, and that AC and ANT are synergistic." @default.
- W2019575743 created "2016-06-24" @default.
- W2019575743 creator A5057014407 @default.
- W2019575743 creator A5084602988 @default.
- W2019575743 date "2014-12-01" @default.
- W2019575743 modified "2023-10-16" @default.
- W2019575743 title "Energy-efficient accelerator architecture for stereo image matching using approximate computing and statistical error compensation" @default.
- W2019575743 cites W1533950919 @default.
- W2019575743 cites W1992809240 @default.
- W2019575743 cites W2005865544 @default.
- W2019575743 cites W2013800675 @default.
- W2019575743 cites W2017819499 @default.
- W2019575743 cites W2018493976 @default.
- W2019575743 cites W2067017781 @default.
- W2019575743 cites W2105751395 @default.
- W2019575743 cites W2106484393 @default.
- W2019575743 cites W2107884096 @default.
- W2019575743 cites W2109233612 @default.
- W2019575743 cites W2113231699 @default.
- W2019575743 cites W2113592437 @default.
- W2019575743 cites W2118331018 @default.
- W2019575743 cites W2133255058 @default.
- W2019575743 cites W2135089667 @default.
- W2019575743 cites W2150100620 @default.
- W2019575743 cites W2151646056 @default.
- W2019575743 cites W2153848924 @default.
- W2019575743 cites W2156425544 @default.
- W2019575743 cites W2164918853 @default.
- W2019575743 cites W2169282664 @default.
- W2019575743 cites W2169868734 @default.
- W2019575743 cites W2296253867 @default.
- W2019575743 cites W3141620748 @default.
- W2019575743 cites W4239289553 @default.
- W2019575743 cites W4255029913 @default.
- W2019575743 doi "https://doi.org/10.1109/globalsip.2014.7032077" @default.
- W2019575743 hasPublicationYear "2014" @default.
- W2019575743 type Work @default.
- W2019575743 sameAs 2019575743 @default.
- W2019575743 citedByCount "2" @default.
- W2019575743 countsByYear W20195757432016 @default.
- W2019575743 countsByYear W20195757432018 @default.
- W2019575743 crossrefType "proceedings-article" @default.
- W2019575743 hasAuthorship W2019575743A5057014407 @default.
- W2019575743 hasAuthorship W2019575743A5084602988 @default.
- W2019575743 hasConcept C105795698 @default.
- W2019575743 hasConcept C11171543 @default.
- W2019575743 hasConcept C11413529 @default.
- W2019575743 hasConcept C115961682 @default.
- W2019575743 hasConcept C123657996 @default.
- W2019575743 hasConcept C142362112 @default.
- W2019575743 hasConcept C153349607 @default.
- W2019575743 hasConcept C154945302 @default.
- W2019575743 hasConcept C15744967 @default.
- W2019575743 hasConcept C165064840 @default.
- W2019575743 hasConcept C186370098 @default.
- W2019575743 hasConcept C2780023022 @default.
- W2019575743 hasConcept C31972630 @default.
- W2019575743 hasConcept C33923547 @default.
- W2019575743 hasConcept C41008148 @default.
- W2019575743 hasConceptScore W2019575743C105795698 @default.
- W2019575743 hasConceptScore W2019575743C11171543 @default.
- W2019575743 hasConceptScore W2019575743C11413529 @default.
- W2019575743 hasConceptScore W2019575743C115961682 @default.
- W2019575743 hasConceptScore W2019575743C123657996 @default.
- W2019575743 hasConceptScore W2019575743C142362112 @default.
- W2019575743 hasConceptScore W2019575743C153349607 @default.
- W2019575743 hasConceptScore W2019575743C154945302 @default.
- W2019575743 hasConceptScore W2019575743C15744967 @default.
- W2019575743 hasConceptScore W2019575743C165064840 @default.
- W2019575743 hasConceptScore W2019575743C186370098 @default.
- W2019575743 hasConceptScore W2019575743C2780023022 @default.
- W2019575743 hasConceptScore W2019575743C31972630 @default.
- W2019575743 hasConceptScore W2019575743C33923547 @default.
- W2019575743 hasConceptScore W2019575743C41008148 @default.
- W2019575743 hasLocation W20195757431 @default.
- W2019575743 hasOpenAccess W2019575743 @default.
- W2019575743 hasPrimaryLocation W20195757431 @default.
- W2019575743 hasRelatedWork W1966244124 @default.
- W2019575743 hasRelatedWork W1995188412 @default.
- W2019575743 hasRelatedWork W2005185696 @default.
- W2019575743 hasRelatedWork W2008343303 @default.
- W2019575743 hasRelatedWork W2065134433 @default.
- W2019575743 hasRelatedWork W2121821935 @default.
- W2019575743 hasRelatedWork W2128391139 @default.
- W2019575743 hasRelatedWork W2391245565 @default.
- W2019575743 hasRelatedWork W2577364290 @default.
- W2019575743 hasRelatedWork W2786306966 @default.
- W2019575743 isParatext "false" @default.
- W2019575743 isRetracted "false" @default.
- W2019575743 magId "2019575743" @default.
- W2019575743 workType "article" @default.