Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200967142> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3200967142 abstract "Convolutional Neural Networks (CNNs) have demonstrated impressive performance in recent times and have shown a wide range of applicability. The deployment of CNNs on resource-constrained edge devices for inference still proves challenging due to the computation, memory, energy, and band-width requirements of CNNs. To address these issues, FPGAs are commonly used to implement CNNs because of their high flexibility and low power consumption. The Winograd convolution algorithm can be used to further reduce the computation requirements of a convolution operation. This paper proposes the Winograd Offline-Runtime Decomposition Algorithm (WORDA), which provides an efficient approach to performing Winograd convolution to achieve low computation latency. In this work, WORDA is used to design convolution layers for CNN accelerators on FPGA for two CNN architectures, namely LeNet and AlexNet, using Vivado HLS (High Level Synthesis). The state-of-the-art comparison shows a 58.3% decrease in latency while only incurring a constant increase in BRAMs, no change in DSPs, and a 122% increase in flip-flops (FFs) and lookup tables (LUTs) usage when using filters of size 5 × 5." @default.
- W3200967142 created "2021-09-27" @default.
- W3200967142 creator A5034599612 @default.
- W3200967142 creator A5062045820 @default.
- W3200967142 creator A5070802892 @default.
- W3200967142 date "2021-08-09" @default.
- W3200967142 modified "2023-10-16" @default.
- W3200967142 title "WORDA: A Winograd Offline-Runtime Decomposition Algorithm for Faster CNN Inference" @default.
- W3200967142 cites W1487564550 @default.
- W3200967142 cites W2172654076 @default.
- W3200967142 cites W2325939864 @default.
- W3200967142 cites W2466675884 @default.
- W3200967142 cites W2618530766 @default.
- W3200967142 cites W2625954420 @default.
- W3200967142 cites W2801550278 @default.
- W3200967142 cites W2904795057 @default.
- W3200967142 cites W2913221350 @default.
- W3200967142 cites W2945913827 @default.
- W3200967142 cites W2951909318 @default.
- W3200967142 cites W2964525696 @default.
- W3200967142 cites W2981994035 @default.
- W3200967142 cites W2982618776 @default.
- W3200967142 doi "https://doi.org/10.1109/mwscas47672.2021.9531783" @default.
- W3200967142 hasPublicationYear "2021" @default.
- W3200967142 type Work @default.
- W3200967142 sameAs 3200967142 @default.
- W3200967142 citedByCount "0" @default.
- W3200967142 crossrefType "proceedings-article" @default.
- W3200967142 hasAuthorship W3200967142A5034599612 @default.
- W3200967142 hasAuthorship W3200967142A5062045820 @default.
- W3200967142 hasAuthorship W3200967142A5070802892 @default.
- W3200967142 hasConcept C113775141 @default.
- W3200967142 hasConcept C11413529 @default.
- W3200967142 hasConcept C149635348 @default.
- W3200967142 hasConcept C154945302 @default.
- W3200967142 hasConcept C173608175 @default.
- W3200967142 hasConcept C2776214188 @default.
- W3200967142 hasConcept C3826847 @default.
- W3200967142 hasConcept C41008148 @default.
- W3200967142 hasConcept C42935608 @default.
- W3200967142 hasConcept C45347329 @default.
- W3200967142 hasConcept C45374587 @default.
- W3200967142 hasConcept C50644808 @default.
- W3200967142 hasConcept C76155785 @default.
- W3200967142 hasConcept C81363708 @default.
- W3200967142 hasConcept C82876162 @default.
- W3200967142 hasConceptScore W3200967142C113775141 @default.
- W3200967142 hasConceptScore W3200967142C11413529 @default.
- W3200967142 hasConceptScore W3200967142C149635348 @default.
- W3200967142 hasConceptScore W3200967142C154945302 @default.
- W3200967142 hasConceptScore W3200967142C173608175 @default.
- W3200967142 hasConceptScore W3200967142C2776214188 @default.
- W3200967142 hasConceptScore W3200967142C3826847 @default.
- W3200967142 hasConceptScore W3200967142C41008148 @default.
- W3200967142 hasConceptScore W3200967142C42935608 @default.
- W3200967142 hasConceptScore W3200967142C45347329 @default.
- W3200967142 hasConceptScore W3200967142C45374587 @default.
- W3200967142 hasConceptScore W3200967142C50644808 @default.
- W3200967142 hasConceptScore W3200967142C76155785 @default.
- W3200967142 hasConceptScore W3200967142C81363708 @default.
- W3200967142 hasConceptScore W3200967142C82876162 @default.
- W3200967142 hasLocation W32009671421 @default.
- W3200967142 hasOpenAccess W3200967142 @default.
- W3200967142 hasPrimaryLocation W32009671421 @default.
- W3200967142 hasRelatedWork W2317796602 @default.
- W3200967142 hasRelatedWork W2770717529 @default.
- W3200967142 hasRelatedWork W2902363683 @default.
- W3200967142 hasRelatedWork W2952735458 @default.
- W3200967142 hasRelatedWork W3005273712 @default.
- W3200967142 hasRelatedWork W3151612890 @default.
- W3200967142 hasRelatedWork W4200264518 @default.
- W3200967142 hasRelatedWork W4319662858 @default.
- W3200967142 hasRelatedWork W4321637356 @default.
- W3200967142 hasRelatedWork W3116497574 @default.
- W3200967142 isParatext "false" @default.
- W3200967142 isRetracted "false" @default.
- W3200967142 magId "3200967142" @default.
- W3200967142 workType "article" @default.