Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945497771> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2945497771 abstract "The growing popularity of Convolutional Neural Networks (CNNs) has led to the search for efficient computational platforms to enable these algorithms. Resistive random-access memory (ReRAM)-based architectures offer a promising alternative to commonly used GPU-based platforms for CNN training. However, backpropagation in CNNs is susceptible to the limited precision of ReRAMs. As a result, training CNNs on ReRAMs affects the final accuracy of learned model. In this work, we propose REGENT, a heterogeneous architecture that combines ReRAM arrays with GPU cores, and exploits the benefits provided by 3D integration along with a high-throughput yet energy efficient Network-on-Chip (NoC) for training CNNs. We also propose a bin-packing based framework that maps CNN layers and then optimize the placement of computing elements to meet the targeted design objectives. Experimental evaluations indicate that REGENT improves full-system EDP by 55.7% on average compared to conventional GPU-only platforms for training CNNs." @default.
- W2945497771 created "2019-05-29" @default.
- W2945497771 creator A5033021422 @default.
- W2945497771 creator A5033880864 @default.
- W2945497771 creator A5055445718 @default.
- W2945497771 creator A5069190300 @default.
- W2945497771 creator A5078441163 @default.
- W2945497771 creator A5083581319 @default.
- W2945497771 date "2019-03-01" @default.
- W2945497771 modified "2023-10-05" @default.
- W2945497771 title "REGENT: A Heterogeneous ReRAM/GPU-based Architecture Enabled by NoC for Training CNNs" @default.
- W2945497771 cites W1483973329 @default.
- W2945497771 cites W2048266589 @default.
- W2945497771 cites W2104492856 @default.
- W2945497771 cites W2106562406 @default.
- W2945497771 cites W2112796928 @default.
- W2945497771 cites W2130820665 @default.
- W2945497771 cites W2141973190 @default.
- W2945497771 cites W2248832573 @default.
- W2945497771 cites W2399958287 @default.
- W2945497771 cites W2518281301 @default.
- W2945497771 cites W2613989746 @default.
- W2945497771 cites W2736068458 @default.
- W2945497771 cites W2760063890 @default.
- W2945497771 cites W2811080765 @default.
- W2945497771 cites W3101558675 @default.
- W2945497771 cites W4255992566 @default.
- W2945497771 doi "https://doi.org/10.23919/date.2019.8714802" @default.
- W2945497771 hasPublicationYear "2019" @default.
- W2945497771 type Work @default.
- W2945497771 sameAs 2945497771 @default.
- W2945497771 citedByCount "14" @default.
- W2945497771 countsByYear W29454977712019 @default.
- W2945497771 countsByYear W29454977712020 @default.
- W2945497771 countsByYear W29454977712021 @default.
- W2945497771 countsByYear W29454977712022 @default.
- W2945497771 countsByYear W29454977712023 @default.
- W2945497771 crossrefType "proceedings-article" @default.
- W2945497771 hasAuthorship W2945497771A5033021422 @default.
- W2945497771 hasAuthorship W2945497771A5033880864 @default.
- W2945497771 hasAuthorship W2945497771A5055445718 @default.
- W2945497771 hasAuthorship W2945497771A5069190300 @default.
- W2945497771 hasAuthorship W2945497771A5078441163 @default.
- W2945497771 hasAuthorship W2945497771A5083581319 @default.
- W2945497771 hasConcept C118524514 @default.
- W2945497771 hasConcept C147789679 @default.
- W2945497771 hasConcept C154945302 @default.
- W2945497771 hasConcept C173608175 @default.
- W2945497771 hasConcept C17525397 @default.
- W2945497771 hasConcept C182019814 @default.
- W2945497771 hasConcept C185592680 @default.
- W2945497771 hasConcept C18903297 @default.
- W2945497771 hasConcept C2778077734 @default.
- W2945497771 hasConcept C41008148 @default.
- W2945497771 hasConcept C81363708 @default.
- W2945497771 hasConcept C86803240 @default.
- W2945497771 hasConceptScore W2945497771C118524514 @default.
- W2945497771 hasConceptScore W2945497771C147789679 @default.
- W2945497771 hasConceptScore W2945497771C154945302 @default.
- W2945497771 hasConceptScore W2945497771C173608175 @default.
- W2945497771 hasConceptScore W2945497771C17525397 @default.
- W2945497771 hasConceptScore W2945497771C182019814 @default.
- W2945497771 hasConceptScore W2945497771C185592680 @default.
- W2945497771 hasConceptScore W2945497771C18903297 @default.
- W2945497771 hasConceptScore W2945497771C2778077734 @default.
- W2945497771 hasConceptScore W2945497771C41008148 @default.
- W2945497771 hasConceptScore W2945497771C81363708 @default.
- W2945497771 hasConceptScore W2945497771C86803240 @default.
- W2945497771 hasLocation W29454977711 @default.
- W2945497771 hasOpenAccess W2945497771 @default.
- W2945497771 hasPrimaryLocation W29454977711 @default.
- W2945497771 hasRelatedWork W1558545464 @default.
- W2945497771 hasRelatedWork W1984303163 @default.
- W2945497771 hasRelatedWork W2117014006 @default.
- W2945497771 hasRelatedWork W2372170743 @default.
- W2945497771 hasRelatedWork W2735477435 @default.
- W2945497771 hasRelatedWork W3016958897 @default.
- W2945497771 hasRelatedWork W3181746755 @default.
- W2945497771 hasRelatedWork W4233815414 @default.
- W2945497771 hasRelatedWork W4283379348 @default.
- W2945497771 hasRelatedWork W4312417841 @default.
- W2945497771 isParatext "false" @default.
- W2945497771 isRetracted "false" @default.
- W2945497771 magId "2945497771" @default.
- W2945497771 workType "article" @default.