Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783111446> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2783111446 abstract "To implement convolutional neural networks (CNN) in hardware, the state-of-the-art CNN accelerators pipeline computation and data transfer stages using an off-chip memory and simultaneously execute them on the same timeline. However, since a large amount of feature maps generated during the operation should be transmitted to the off-chip memory, the pipeline stage length is determined by the off-chip data transfer stage. Fusion architectures that can fuse multiple layers have been proposed to solve this problem, but applications such as super-resolution (SR) require a large amount of an on-chip memory because of the high resolution of the feature maps. In this paper, we propose a novel on-chip CNN accelerator for SR to optimize the CNN dataflow in the on-chip memory. First, the convolution loop optimization technique is proposed to prevent using a frame buffer. Second, we develop a combined convolutional layer processor to reduce the buffer size used to store the feature maps. Third, we explore how to perform low-cost multiply-and-accumulate operations in the deconvolutional layer used in SR. Finally, we propose a two-stage quantization algorithm to select the optimized hardware size for the limited number of DSPs to implement the on-chip CNN accelerator. We evaluate our proposed accelerator with FSRCNN, which is most popular as the CNN-based SR algorithm. Experimental results show that the proposed accelerator requires 9.21ms to achieve an output image with the 2560x1440 pixel resolution, which is 36 times faster than the conventional method. In addition, we reduce the on-chip memory usage and DSP usage by 4 times and 1.44 times, respectively, compared to the conventional methods." @default.
- W2783111446 created "2018-01-26" @default.
- W2783111446 creator A5032639277 @default.
- W2783111446 creator A5084904773 @default.
- W2783111446 date "2018-01-18" @default.
- W2783111446 modified "2023-09-27" @default.
- W2783111446 title "On-Chip CNN Accelerator for Image Super-Resolution." @default.
- W2783111446 cites W2094756095 @default.
- W2783111446 cites W2163605009 @default.
- W2783111446 cites W2584311934 @default.
- W2783111446 cites W54257720 @default.
- W2783111446 hasPublicationYear "2018" @default.
- W2783111446 type Work @default.
- W2783111446 sameAs 2783111446 @default.
- W2783111446 citedByCount "0" @default.
- W2783111446 crossrefType "posted-content" @default.
- W2783111446 hasAuthorship W2783111446A5032639277 @default.
- W2783111446 hasAuthorship W2783111446A5084904773 @default.
- W2783111446 hasConcept C11413529 @default.
- W2783111446 hasConcept C13164978 @default.
- W2783111446 hasConcept C138885662 @default.
- W2783111446 hasConcept C154945302 @default.
- W2783111446 hasConcept C165005293 @default.
- W2783111446 hasConcept C173608175 @default.
- W2783111446 hasConcept C199360897 @default.
- W2783111446 hasConcept C2776401178 @default.
- W2783111446 hasConcept C28855332 @default.
- W2783111446 hasConcept C3261483 @default.
- W2783111446 hasConcept C41008148 @default.
- W2783111446 hasConcept C41895202 @default.
- W2783111446 hasConcept C42935608 @default.
- W2783111446 hasConcept C43521106 @default.
- W2783111446 hasConcept C76155785 @default.
- W2783111446 hasConcept C81363708 @default.
- W2783111446 hasConcept C9390403 @default.
- W2783111446 hasConcept C96324660 @default.
- W2783111446 hasConceptScore W2783111446C11413529 @default.
- W2783111446 hasConceptScore W2783111446C13164978 @default.
- W2783111446 hasConceptScore W2783111446C138885662 @default.
- W2783111446 hasConceptScore W2783111446C154945302 @default.
- W2783111446 hasConceptScore W2783111446C165005293 @default.
- W2783111446 hasConceptScore W2783111446C173608175 @default.
- W2783111446 hasConceptScore W2783111446C199360897 @default.
- W2783111446 hasConceptScore W2783111446C2776401178 @default.
- W2783111446 hasConceptScore W2783111446C28855332 @default.
- W2783111446 hasConceptScore W2783111446C3261483 @default.
- W2783111446 hasConceptScore W2783111446C41008148 @default.
- W2783111446 hasConceptScore W2783111446C41895202 @default.
- W2783111446 hasConceptScore W2783111446C42935608 @default.
- W2783111446 hasConceptScore W2783111446C43521106 @default.
- W2783111446 hasConceptScore W2783111446C76155785 @default.
- W2783111446 hasConceptScore W2783111446C81363708 @default.
- W2783111446 hasConceptScore W2783111446C9390403 @default.
- W2783111446 hasConceptScore W2783111446C96324660 @default.
- W2783111446 hasLocation W27831114461 @default.
- W2783111446 hasOpenAccess W2783111446 @default.
- W2783111446 hasPrimaryLocation W27831114461 @default.
- W2783111446 hasRelatedWork W2202150804 @default.
- W2783111446 hasRelatedWork W2724189024 @default.
- W2783111446 hasRelatedWork W2743559954 @default.
- W2783111446 hasRelatedWork W2762651727 @default.
- W2783111446 hasRelatedWork W2791121285 @default.
- W2783111446 hasRelatedWork W2793186932 @default.
- W2783111446 hasRelatedWork W2894696827 @default.
- W2783111446 hasRelatedWork W2895914074 @default.
- W2783111446 hasRelatedWork W2899824860 @default.
- W2783111446 hasRelatedWork W2951898149 @default.
- W2783111446 hasRelatedWork W2955320564 @default.
- W2783111446 hasRelatedWork W3015208590 @default.
- W2783111446 hasRelatedWork W3047237654 @default.
- W2783111446 hasRelatedWork W3089266222 @default.
- W2783111446 hasRelatedWork W3093799822 @default.
- W2783111446 hasRelatedWork W3164019007 @default.
- W2783111446 hasRelatedWork W3183954477 @default.
- W2783111446 hasRelatedWork W3207050768 @default.
- W2783111446 hasRelatedWork W837176083 @default.
- W2783111446 hasRelatedWork W3117827199 @default.
- W2783111446 isParatext "false" @default.
- W2783111446 isRetracted "false" @default.
- W2783111446 magId "2783111446" @default.
- W2783111446 workType "article" @default.