FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2294282016> ?p ?o ?g. }

• W2294282016 abstract "Convolutional Neural Networks (CNNs) have gained popularity in many computer vision applications such as image classification, face detection, and video analysis, because of their ability to train and classify with high accuracy. Due to multiple convolution and fully-connected layers that are compute-/memory-intensive, it is difficult to perform real-time classification with low power consumption on today?s computing systems. FPGAs have been widely explored as hardware accelerators for CNNs because of their reconfigurability and energy efficiency, as well as fast turn-around-time, especially with high-level synthesis methodologies. Previous FPGA-based CNN accelerators, however, typically implemented generic accelerators agnostic to the CNN configuration, where the reconfigurable capabilities of FPGAs are not fully leveraged to maximize the overall system throughput. In this work, we present a systematic design space exploration methodology to maximize the throughput of an OpenCL-based FPGA accelerator for a given CNN model, considering the FPGA resource constraints such as on-chip memory, registers, computational resources and external memory bandwidth. The proposed methodology is demonstrated by optimizing two representative large-scale CNNs, AlexNet and VGG, on two Altera Stratix-V FPGA platforms, DE5-Net and P395-D8 boards, which have different hardware resources. We achieve a peak performance of 136.5 GOPS for convolution operation, and 117.8 GOPS for the entire VGG network that performs ImageNet classification on P395-D8 board." @default.
• W2294282016 created "2016-06-24" @default.
• W2294282016 creator A5003880169 @default.
• W2294282016 creator A5004249628 @default.
• W2294282016 creator A5004292742 @default.
• W2294282016 creator A5007690955 @default.
• W2294282016 creator A5016704219 @default.
• W2294282016 creator A5030130819 @default.
• W2294282016 creator A5051397079 @default.
• W2294282016 creator A5068840674 @default.
• W2294282016 date "2016-02-21" @default.
• W2294282016 modified "2023-10-18" @default.
• W2294282016 title "Throughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks" @default.
• W2294282016 cites W16066432 @default.
• W2294282016 cites W1995562189 @default.
• W2294282016 cites W2009832130 @default.
• W2294282016 cites W2016053056 @default.
• W2294282016 cites W2044535169 @default.
• W2294282016 cites W2048266589 @default.
• W2294282016 cites W2059343366 @default.
• W2294282016 cites W2094756095 @default.
• W2294282016 cites W2117130368 @default.
• W2294282016 cites W2117539524 @default.
• W2294282016 doi "https://doi.org/10.1145/2847263.2847276" @default.
• W2294282016 hasPublicationYear "2016" @default.
• W2294282016 type Work @default.
• W2294282016 sameAs 2294282016 @default.
• W2294282016 citedByCount "396" @default.
• W2294282016 countsByYear W22942820162016 @default.
• W2294282016 countsByYear W22942820162017 @default.
• W2294282016 countsByYear W22942820162018 @default.
• W2294282016 countsByYear W22942820162019 @default.
• W2294282016 countsByYear W22942820162020 @default.
• W2294282016 countsByYear W22942820162021 @default.
• W2294282016 countsByYear W22942820162022 @default.
• W2294282016 countsByYear W22942820162023 @default.
• W2294282016 crossrefType "proceedings-article" @default.
• W2294282016 hasAuthorship W2294282016A5003880169 @default.
• W2294282016 hasAuthorship W2294282016A5004249628 @default.
• W2294282016 hasAuthorship W2294282016A5004292742 @default.
• W2294282016 hasAuthorship W2294282016A5007690955 @default.
• W2294282016 hasAuthorship W2294282016A5016704219 @default.
• W2294282016 hasAuthorship W2294282016A5030130819 @default.
• W2294282016 hasAuthorship W2294282016A5051397079 @default.
• W2294282016 hasAuthorship W2294282016A5068840674 @default.
• W2294282016 hasConcept C111919701 @default.
• W2294282016 hasConcept C113775141 @default.
• W2294282016 hasConcept C114614502 @default.
• W2294282016 hasConcept C118021083 @default.
• W2294282016 hasConcept C118524514 @default.
• W2294282016 hasConcept C149635348 @default.
• W2294282016 hasConcept C154945302 @default.
• W2294282016 hasConcept C157764524 @default.
• W2294282016 hasConcept C2776277307 @default.
• W2294282016 hasConcept C2777187653 @default.
• W2294282016 hasConcept C2780149590 @default.
• W2294282016 hasConcept C33923547 @default.
• W2294282016 hasConcept C41008148 @default.
• W2294282016 hasConcept C42935608 @default.
• W2294282016 hasConcept C45347329 @default.
• W2294282016 hasConcept C50644808 @default.
• W2294282016 hasConcept C555944384 @default.
• W2294282016 hasConcept C74193536 @default.
• W2294282016 hasConcept C81363708 @default.
• W2294282016 hasConcept C9390403 @default.
• W2294282016 hasConceptScore W2294282016C111919701 @default.
• W2294282016 hasConceptScore W2294282016C113775141 @default.
• W2294282016 hasConceptScore W2294282016C114614502 @default.
• W2294282016 hasConceptScore W2294282016C118021083 @default.
• W2294282016 hasConceptScore W2294282016C118524514 @default.
• W2294282016 hasConceptScore W2294282016C149635348 @default.
• W2294282016 hasConceptScore W2294282016C154945302 @default.
• W2294282016 hasConceptScore W2294282016C157764524 @default.
• W2294282016 hasConceptScore W2294282016C2776277307 @default.
• W2294282016 hasConceptScore W2294282016C2777187653 @default.
• W2294282016 hasConceptScore W2294282016C2780149590 @default.
• W2294282016 hasConceptScore W2294282016C33923547 @default.
• W2294282016 hasConceptScore W2294282016C41008148 @default.
• W2294282016 hasConceptScore W2294282016C42935608 @default.
• W2294282016 hasConceptScore W2294282016C45347329 @default.
• W2294282016 hasConceptScore W2294282016C50644808 @default.
• W2294282016 hasConceptScore W2294282016C555944384 @default.
• W2294282016 hasConceptScore W2294282016C74193536 @default.
• W2294282016 hasConceptScore W2294282016C81363708 @default.
• W2294282016 hasConceptScore W2294282016C9390403 @default.
• W2294282016 hasLocation W22942820161 @default.
• W2294282016 hasOpenAccess W2294282016 @default.
• W2294282016 hasPrimaryLocation W22942820161 @default.
• W2294282016 hasRelatedWork W2100470915 @default.
• W2294282016 hasRelatedWork W2121567962 @default.
• W2294282016 hasRelatedWork W2142497937 @default.
• W2294282016 hasRelatedWork W2150194641 @default.
• W2294282016 hasRelatedWork W2371372853 @default.
• W2294282016 hasRelatedWork W2524802307 @default.
• W2294282016 hasRelatedWork W2544224778 @default.
• W2294282016 hasRelatedWork W4281927116 @default.
• W2294282016 hasRelatedWork W4319662858 @default.
• W2294282016 hasRelatedWork W1871493803 @default.
• W2294282016 isParatext "false" @default.
• W2294282016 isRetracted "false" @default.

• next