Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386205080> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4386205080 endingPage "108" @default.
- W4386205080 startingPage "94" @default.
- W4386205080 abstract "CNN-based inference engine’s performance and efficiency always depend on the computational and dataflow-control complexity. Instead of considering a 2-dimensional (2D) feature array for processing, a 3D array of features/weights would improve the dataflow movement & memory computation. The optimum 8 × 8 × 32 3D-feature array size was chosen based on the factor of on-chip memory requirement, data reuse, and PE utilization. Using the optimum 8 × 8 × 32 feature array, seven different combinations of data-flow scheduling strategies were analyzed by varying row, column, and depth-wise parameters on the workload model using a MATLAB environment. From the analysis, strategy-V (depth-wise parallel & row/column-wise sequence) is found to be the best with a 4 × 8 processor array. Compared to the state-of-the-art processor strategy, strategy-V achieves the data transfer rate (off-chip to on-chip) and on-chip memory requirement of 3.3 times (higher) and 16 times (lesser) with a small overhead of processor cost." @default.
- W4386205080 created "2023-08-28" @default.
- W4386205080 creator A5032050619 @default.
- W4386205080 creator A5078330247 @default.
- W4386205080 creator A5092703739 @default.
- W4386205080 date "2023-01-01" @default.
- W4386205080 modified "2023-09-25" @default.
- W4386205080 title "Analysis of Optimum 3-Dimensional Array and Fast Data Movement for Efficient Memory Computation in Convolutional Neural Network Models" @default.
- W4386205080 cites W2117696986 @default.
- W4386205080 cites W2289252105 @default.
- W4386205080 cites W2593564159 @default.
- W4386205080 cites W2604319603 @default.
- W4386205080 cites W2625457103 @default.
- W4386205080 cites W2800017313 @default.
- W4386205080 cites W2808463410 @default.
- W4386205080 cites W2901167238 @default.
- W4386205080 cites W2905515056 @default.
- W4386205080 cites W2950656546 @default.
- W4386205080 cites W2987129023 @default.
- W4386205080 cites W3004127905 @default.
- W4386205080 cites W3048860076 @default.
- W4386205080 cites W3084937280 @default.
- W4386205080 cites W3135869264 @default.
- W4386205080 doi "https://doi.org/10.1007/978-3-031-39811-7_8" @default.
- W4386205080 hasPublicationYear "2023" @default.
- W4386205080 type Work @default.
- W4386205080 citedByCount "0" @default.
- W4386205080 crossrefType "book-chapter" @default.
- W4386205080 hasAuthorship W4386205080A5032050619 @default.
- W4386205080 hasAuthorship W4386205080A5078330247 @default.
- W4386205080 hasAuthorship W4386205080A5092703739 @default.
- W4386205080 hasConcept C111919701 @default.
- W4386205080 hasConcept C11413529 @default.
- W4386205080 hasConcept C154945302 @default.
- W4386205080 hasConcept C161824985 @default.
- W4386205080 hasConcept C165005293 @default.
- W4386205080 hasConcept C173608175 @default.
- W4386205080 hasConcept C2776189500 @default.
- W4386205080 hasConcept C2779960059 @default.
- W4386205080 hasConcept C41008148 @default.
- W4386205080 hasConcept C45374587 @default.
- W4386205080 hasConcept C489000 @default.
- W4386205080 hasConcept C76155785 @default.
- W4386205080 hasConcept C77088390 @default.
- W4386205080 hasConcept C81363708 @default.
- W4386205080 hasConcept C96324660 @default.
- W4386205080 hasConceptScore W4386205080C111919701 @default.
- W4386205080 hasConceptScore W4386205080C11413529 @default.
- W4386205080 hasConceptScore W4386205080C154945302 @default.
- W4386205080 hasConceptScore W4386205080C161824985 @default.
- W4386205080 hasConceptScore W4386205080C165005293 @default.
- W4386205080 hasConceptScore W4386205080C173608175 @default.
- W4386205080 hasConceptScore W4386205080C2776189500 @default.
- W4386205080 hasConceptScore W4386205080C2779960059 @default.
- W4386205080 hasConceptScore W4386205080C41008148 @default.
- W4386205080 hasConceptScore W4386205080C45374587 @default.
- W4386205080 hasConceptScore W4386205080C489000 @default.
- W4386205080 hasConceptScore W4386205080C76155785 @default.
- W4386205080 hasConceptScore W4386205080C77088390 @default.
- W4386205080 hasConceptScore W4386205080C81363708 @default.
- W4386205080 hasConceptScore W4386205080C96324660 @default.
- W4386205080 hasLocation W43862050801 @default.
- W4386205080 hasOpenAccess W4386205080 @default.
- W4386205080 hasPrimaryLocation W43862050801 @default.
- W4386205080 hasRelatedWork W157064208 @default.
- W4386205080 hasRelatedWork W1572523360 @default.
- W4386205080 hasRelatedWork W1594844924 @default.
- W4386205080 hasRelatedWork W1973387129 @default.
- W4386205080 hasRelatedWork W2047588290 @default.
- W4386205080 hasRelatedWork W2047780266 @default.
- W4386205080 hasRelatedWork W2168876575 @default.
- W4386205080 hasRelatedWork W3120511008 @default.
- W4386205080 hasRelatedWork W3131083367 @default.
- W4386205080 hasRelatedWork W3205626426 @default.
- W4386205080 isParatext "false" @default.
- W4386205080 isRetracted "false" @default.
- W4386205080 workType "book-chapter" @default.