FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3171938963> ?p ?o ?g. }

• W3171938963 abstract "The recent research advances in deep learning have led to the development of small and powerful Convolutional Neural Network (CNN) architectures. Meanwhile Field Programmable Gate Arrays (FPGAs) has become a popular hardware target choice for their deployment, splitting into two main implementation categories: streaming hardware architectures and single computation engine design approaches. The streaming hardware architectures generally require implementing every layer as a discrete processing unit, and are suitable for smaller software models that could fit in their unfolded versions into resource-constrained targets. On the other hand, single computation engines can be scaled to fit into a device to execute CNN models of different sizes and complexities, however, the achievable performance of one-size-fits-all implementations may vary across CNNs with different workload attributes leading to inefficient utilization of hardware resources. By combing the advantages of both of the above methods, this work proposes a new design paradigm called semi-streaming architecture, where layer-specialized configurable engines are used for network realization. As a proof of concept this paper presents a set of five layer-specialized configurable processing engines for implementing 8-bit quantized MobilenevV2 CNN model. The engines are chained to partially preserve data streaming and tuned individually to efficiently process specific types of layers: normalized addition of residuals, depthwise, pointwise (expansion and projection), and standard 2D convolution layers capable of delivering 5.4GOp/s, 16GOp/s, 27.2GOp/s, 27.2GOp/s and 89.6GOp/s, respectively, with the overall energy efficiency of 5.32GOp/s/W at a 100MHz system clock, requiring total power of 6.2W on a XCZU7EV SoC FPGA." @default.
• W3171938963 created "2021-06-22" @default.
• W3171938963 creator A5010151984 @default.
• W3171938963 creator A5059003197 @default.
• W3171938963 date "2020-12-01" @default.
• W3171938963 modified "2023-09-23" @default.
• W3171938963 title "FPGA Implementation of MobileNetV2 CNN Model Using Semi-Streaming Architecture for Low Power Inference Applications" @default.
• W3171938963 cites W1677182931 @default.
• W3171938963 cites W1996901117 @default.
• W3171938963 cites W2094756095 @default.
• W3171938963 cites W2097117768 @default.
• W3171938963 cites W2396572963 @default.
• W3171938963 cites W2513568085 @default.
• W3171938963 cites W2554302513 @default.
• W3171938963 cites W2616014673 @default.
• W3171938963 cites W2893813411 @default.
• W3171938963 cites W2895540242 @default.
• W3171938963 cites W2905515056 @default.
• W3171938963 cites W2918817571 @default.
• W3171938963 cites W2963125010 @default.
• W3171938963 cites W2963163009 @default.
• W3171938963 cites W2964349401 @default.
• W3171938963 cites W3100220590 @default.
• W3171938963 cites W4242577057 @default.
• W3171938963 doi "https://doi.org/10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00046" @default.
• W3171938963 hasPublicationYear "2020" @default.
• W3171938963 type Work @default.
• W3171938963 sameAs 3171938963 @default.
• W3171938963 citedByCount "1" @default.
• W3171938963 countsByYear W31719389632022 @default.
• W3171938963 crossrefType "proceedings-article" @default.
• W3171938963 hasAuthorship W3171938963A5010151984 @default.
• W3171938963 hasAuthorship W3171938963A5059003197 @default.
• W3171938963 hasConcept C113775141 @default.
• W3171938963 hasConcept C118524514 @default.
• W3171938963 hasConcept C120314980 @default.
• W3171938963 hasConcept C149635348 @default.
• W3171938963 hasConcept C154945302 @default.
• W3171938963 hasConcept C2776221188 @default.
• W3171938963 hasConcept C41008148 @default.
• W3171938963 hasConcept C42935608 @default.
• W3171938963 hasConcept C81363708 @default.
• W3171938963 hasConcept C9390403 @default.
• W3171938963 hasConceptScore W3171938963C113775141 @default.
• W3171938963 hasConceptScore W3171938963C118524514 @default.
• W3171938963 hasConceptScore W3171938963C120314980 @default.
• W3171938963 hasConceptScore W3171938963C149635348 @default.
• W3171938963 hasConceptScore W3171938963C154945302 @default.
• W3171938963 hasConceptScore W3171938963C2776221188 @default.
• W3171938963 hasConceptScore W3171938963C41008148 @default.
• W3171938963 hasConceptScore W3171938963C42935608 @default.
• W3171938963 hasConceptScore W3171938963C81363708 @default.
• W3171938963 hasConceptScore W3171938963C9390403 @default.
• W3171938963 hasLocation W31719389631 @default.
• W3171938963 hasOpenAccess W3171938963 @default.
• W3171938963 hasPrimaryLocation W31719389631 @default.
• W3171938963 hasRelatedWork W1732210391 @default.
• W3171938963 hasRelatedWork W2110373273 @default.
• W3171938963 hasRelatedWork W2161839990 @default.
• W3171938963 hasRelatedWork W2295680811 @default.
• W3171938963 hasRelatedWork W2524802307 @default.
• W3171938963 hasRelatedWork W3003304268 @default.
• W3171938963 hasRelatedWork W3147787617 @default.
• W3171938963 hasRelatedWork W4285708690 @default.
• W3171938963 hasRelatedWork W4295855328 @default.
• W3171938963 hasRelatedWork W4319662858 @default.
• W3171938963 isParatext "false" @default.
• W3171938963 isRetracted "false" @default.
• W3171938963 magId "3171938963" @default.
• W3171938963 workType "article" @default.