Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376106601> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4376106601 abstract "<p>Convolutional Neural Networks has (CNN) have been widely used in various Internet-of-Things (IoT) applications to offer smart solutions in our daily lives. Many hardware accelerators were proposed to speed up CNN, so that it can be used in the IoT sensor nodes. Recently, octave convolution was proposed to remove spatial redundancy from input feature maps, thus reducing the CNN computation and memory cost. Although octave CNN is an attractive candidate for IoT applications, it cannot replace regular CNN, which is already widely used in many applications. Hence, it is desirable to have a hardware accelerator that can flexibly support both regular and octave convolution. In this work, we present the first compact and flexible CNN accelerator on an Field-Programmable-Gate-Array (FPGA), which supports normal, pointwise and depthwise convolutions for state-of-the-art octave convolution, as well as the existing regular convolution. To ensure efficient accelerator utilization, a novel adaptive scheduling scheme is presented to schedule the number of computation tasks based on varying feature map dimensions across CNN layers. A novel integration technique is presented to execute the varying computational patterns in octave convolution due to multiple branching in a single computation unit. An efficient memory scheme and execution scheduling for octave convolution are also proposed to overlap the long data fetch time with the on-going octave computation for better overall computation performance. Comparing to other state-of-the-art work, our proposed accelerator achieved 1.98x higher computation density for MobileNetV2 implementation on XC7ZU9EG, as well as about 83.9% lesser power for ResNet-50 implementation on VU9P. </p>" @default.
- W4376106601 created "2023-05-12" @default.
- W4376106601 creator A5009152648 @default.
- W4376106601 creator A5016964173 @default.
- W4376106601 creator A5032505982 @default.
- W4376106601 creator A5072449504 @default.
- W4376106601 creator A5091917621 @default.
- W4376106601 date "2023-05-10" @default.
- W4376106601 modified "2023-09-30" @default.
- W4376106601 title "A Compact and Flexible FPGA Accelerator for Regular and Octave Convolutional Neural Networks" @default.
- W4376106601 doi "https://doi.org/10.36227/techrxiv.22769546.v1" @default.
- W4376106601 hasPublicationYear "2023" @default.
- W4376106601 type Work @default.
- W4376106601 citedByCount "0" @default.
- W4376106601 crossrefType "posted-content" @default.
- W4376106601 hasAuthorship W4376106601A5009152648 @default.
- W4376106601 hasAuthorship W4376106601A5016964173 @default.
- W4376106601 hasAuthorship W4376106601A5032505982 @default.
- W4376106601 hasAuthorship W4376106601A5072449504 @default.
- W4376106601 hasAuthorship W4376106601A5091917621 @default.
- W4376106601 hasBestOaLocation W43761066011 @default.
- W4376106601 hasConcept C113775141 @default.
- W4376106601 hasConcept C11413529 @default.
- W4376106601 hasConcept C120665830 @default.
- W4376106601 hasConcept C121332964 @default.
- W4376106601 hasConcept C138885662 @default.
- W4376106601 hasConcept C154945302 @default.
- W4376106601 hasConcept C162324750 @default.
- W4376106601 hasConcept C173608175 @default.
- W4376106601 hasConcept C206729178 @default.
- W4376106601 hasConcept C21547014 @default.
- W4376106601 hasConcept C2776401178 @default.
- W4376106601 hasConcept C41008148 @default.
- W4376106601 hasConcept C41895202 @default.
- W4376106601 hasConcept C42935608 @default.
- W4376106601 hasConcept C45347329 @default.
- W4376106601 hasConcept C45374587 @default.
- W4376106601 hasConcept C459310 @default.
- W4376106601 hasConcept C50644808 @default.
- W4376106601 hasConcept C68339613 @default.
- W4376106601 hasConcept C81363708 @default.
- W4376106601 hasConcept C85841341 @default.
- W4376106601 hasConcept C9390403 @default.
- W4376106601 hasConceptScore W4376106601C113775141 @default.
- W4376106601 hasConceptScore W4376106601C11413529 @default.
- W4376106601 hasConceptScore W4376106601C120665830 @default.
- W4376106601 hasConceptScore W4376106601C121332964 @default.
- W4376106601 hasConceptScore W4376106601C138885662 @default.
- W4376106601 hasConceptScore W4376106601C154945302 @default.
- W4376106601 hasConceptScore W4376106601C162324750 @default.
- W4376106601 hasConceptScore W4376106601C173608175 @default.
- W4376106601 hasConceptScore W4376106601C206729178 @default.
- W4376106601 hasConceptScore W4376106601C21547014 @default.
- W4376106601 hasConceptScore W4376106601C2776401178 @default.
- W4376106601 hasConceptScore W4376106601C41008148 @default.
- W4376106601 hasConceptScore W4376106601C41895202 @default.
- W4376106601 hasConceptScore W4376106601C42935608 @default.
- W4376106601 hasConceptScore W4376106601C45347329 @default.
- W4376106601 hasConceptScore W4376106601C45374587 @default.
- W4376106601 hasConceptScore W4376106601C459310 @default.
- W4376106601 hasConceptScore W4376106601C50644808 @default.
- W4376106601 hasConceptScore W4376106601C68339613 @default.
- W4376106601 hasConceptScore W4376106601C81363708 @default.
- W4376106601 hasConceptScore W4376106601C85841341 @default.
- W4376106601 hasConceptScore W4376106601C9390403 @default.
- W4376106601 hasLocation W43761066011 @default.
- W4376106601 hasOpenAccess W4376106601 @default.
- W4376106601 hasPrimaryLocation W43761066011 @default.
- W4376106601 hasRelatedWork W156843270 @default.
- W4376106601 hasRelatedWork W2042026112 @default.
- W4376106601 hasRelatedWork W2116951845 @default.
- W4376106601 hasRelatedWork W2357202006 @default.
- W4376106601 hasRelatedWork W2565158842 @default.
- W4376106601 hasRelatedWork W2757410581 @default.
- W4376106601 hasRelatedWork W2767899175 @default.
- W4376106601 hasRelatedWork W2770717529 @default.
- W4376106601 hasRelatedWork W2949649078 @default.
- W4376106601 hasRelatedWork W2185731423 @default.
- W4376106601 isParatext "false" @default.
- W4376106601 isRetracted "false" @default.
- W4376106601 workType "article" @default.