Matches in SemOpenAlex for { <https://semopenalex.org/work/W3195194131> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3195194131 abstract "The recent breakthroughs and prohibitive complexities of Deep Neural Networks (DNNs) have excited extensive interest in domain specific DNN accelerators, among which optical DNN accelerators are particularly promising thanks to their unprecedented potential of achieving superior performance-per-watt. However, the development of optical DNN accelerators is much slower than that of electrical DNN accelerators. One key challenge is that while many techniques have been developed to facilitate the development of electrical DNN accelerators, techniques that support or expedite optical DNN accelerator design remain much less explored, limiting both the achievable performance and the innovation development of optical DNN accelerators. To this end, we develop the first-of-its-kind framework dubbed O-HAS, which for the first time demonstrates automated Optical Hardware Accelerator Search for boosting both the acceleration efficiency and development speed of optical DNN accelerators. Specifically, our O-HAS consists of two integrated enablers: (1) an O-Cost Predictor, which can accurately yet efficiently predict an optical accelerator's energy and latency based on the DNN model parameters and the optical accelerator design; and (2) an O-Search Engine, which can automatically explore the large design space of optical DNN accelerators and identify the optimal accelerators (i.e., the micro-architectures and algorithm-to-accelerator mapping methods) in order to maximize the target acceleration efficiency. Extensive experiments and ablation studies consistently validate the effectiveness of both our O-Cost Predictor and O-Search Engine as well as the excellent efficiency of O-HAS generated optical accelerators." @default.
- W3195194131 created "2021-08-30" @default.
- W3195194131 creator A5019582323 @default.
- W3195194131 creator A5034614246 @default.
- W3195194131 creator A5061572132 @default.
- W3195194131 creator A5075140744 @default.
- W3195194131 creator A5079226021 @default.
- W3195194131 date "2021-11-01" @default.
- W3195194131 modified "2023-09-30" @default.
- W3195194131 title "O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed" @default.
- W3195194131 cites W2030343671 @default.
- W3195194131 cites W2032531286 @default.
- W3195194131 cites W2118658415 @default.
- W3195194131 cites W2289252105 @default.
- W3195194131 cites W2518281301 @default.
- W3195194131 cites W2752849906 @default.
- W3195194131 cites W2940862705 @default.
- W3195194131 cites W2945546236 @default.
- W3195194131 cites W2974263490 @default.
- W3195194131 cites W3016633211 @default.
- W3195194131 cites W3042493405 @default.
- W3195194131 cites W3098600872 @default.
- W3195194131 cites W3107308400 @default.
- W3195194131 cites W3118265437 @default.
- W3195194131 cites W3128451613 @default.
- W3195194131 doi "https://doi.org/10.1109/iccad51958.2021.9643442" @default.
- W3195194131 hasPublicationYear "2021" @default.
- W3195194131 type Work @default.
- W3195194131 sameAs 3195194131 @default.
- W3195194131 citedByCount "3" @default.
- W3195194131 countsByYear W31951941312022 @default.
- W3195194131 countsByYear W31951941312023 @default.
- W3195194131 crossrefType "proceedings-article" @default.
- W3195194131 hasAuthorship W3195194131A5019582323 @default.
- W3195194131 hasAuthorship W3195194131A5034614246 @default.
- W3195194131 hasAuthorship W3195194131A5061572132 @default.
- W3195194131 hasAuthorship W3195194131A5075140744 @default.
- W3195194131 hasAuthorship W3195194131A5079226021 @default.
- W3195194131 hasBestOaLocation W31951941312 @default.
- W3195194131 hasConcept C117896860 @default.
- W3195194131 hasConcept C119599485 @default.
- W3195194131 hasConcept C120665830 @default.
- W3195194131 hasConcept C121332964 @default.
- W3195194131 hasConcept C127413603 @default.
- W3195194131 hasConcept C13164978 @default.
- W3195194131 hasConcept C154945302 @default.
- W3195194131 hasConcept C168834538 @default.
- W3195194131 hasConcept C189166818 @default.
- W3195194131 hasConcept C2742236 @default.
- W3195194131 hasConcept C41008148 @default.
- W3195194131 hasConcept C42935608 @default.
- W3195194131 hasConcept C46686674 @default.
- W3195194131 hasConcept C74650414 @default.
- W3195194131 hasConcept C76155785 @default.
- W3195194131 hasConcept C82876162 @default.
- W3195194131 hasConcept C9390403 @default.
- W3195194131 hasConceptScore W3195194131C117896860 @default.
- W3195194131 hasConceptScore W3195194131C119599485 @default.
- W3195194131 hasConceptScore W3195194131C120665830 @default.
- W3195194131 hasConceptScore W3195194131C121332964 @default.
- W3195194131 hasConceptScore W3195194131C127413603 @default.
- W3195194131 hasConceptScore W3195194131C13164978 @default.
- W3195194131 hasConceptScore W3195194131C154945302 @default.
- W3195194131 hasConceptScore W3195194131C168834538 @default.
- W3195194131 hasConceptScore W3195194131C189166818 @default.
- W3195194131 hasConceptScore W3195194131C2742236 @default.
- W3195194131 hasConceptScore W3195194131C41008148 @default.
- W3195194131 hasConceptScore W3195194131C42935608 @default.
- W3195194131 hasConceptScore W3195194131C46686674 @default.
- W3195194131 hasConceptScore W3195194131C74650414 @default.
- W3195194131 hasConceptScore W3195194131C76155785 @default.
- W3195194131 hasConceptScore W3195194131C82876162 @default.
- W3195194131 hasConceptScore W3195194131C9390403 @default.
- W3195194131 hasLocation W31951941311 @default.
- W3195194131 hasLocation W31951941312 @default.
- W3195194131 hasOpenAccess W3195194131 @default.
- W3195194131 hasPrimaryLocation W31951941311 @default.
- W3195194131 hasRelatedWork W2074831258 @default.
- W3195194131 hasRelatedWork W2160069347 @default.
- W3195194131 hasRelatedWork W2351404747 @default.
- W3195194131 hasRelatedWork W2521029662 @default.
- W3195194131 hasRelatedWork W2531676558 @default.
- W3195194131 hasRelatedWork W2600063918 @default.
- W3195194131 hasRelatedWork W2759844239 @default.
- W3195194131 hasRelatedWork W3011776263 @default.
- W3195194131 hasRelatedWork W4300585894 @default.
- W3195194131 hasRelatedWork W4363649491 @default.
- W3195194131 isParatext "false" @default.
- W3195194131 isRetracted "false" @default.
- W3195194131 magId "3195194131" @default.
- W3195194131 workType "article" @default.