Flexflow: A flexible dataflow accelerator architecture for convolutional neural networks

W Lu, G Yan, J Li, S Gong, Y Han… - 2017 IEEE International …, 2017 - ieeexplore.ieee.org
Convolutional Neural Networks (CNN) are very computation-intensive. Recently, a lot of
CNN accelerators based on the CNN intrinsic parallelism are proposed. However, we …
被引用次数：403 相关文章

[引用][C] FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks

W Lu, G Yan, J Li, S Gong, Y Han, X Li - 2017 IEEE International …, 2017 - cir.nii.ac.jp
FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks |
CiNii Research CiNii 国立情報学研究所 学術情報ナビゲータ[サイニィ] 詳細へ移動 検索フォーム …
[PDF] google.com

[PDF][PDF] Flexflow: A flexible dataflow accelerator architecture for convolutional neural networks

W Lu, G Yan, J Li, S Gong, Y Han… - 2017 IEEE International …, 2017 - drive.google.com
Convolutional Neural Networks (CNN) are very computation-intensive. Recently, a lot of
CNN accelerators based on the CNN intrinsic parallelism are proposed. However, we …

FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks

W Lu, G Yan, J Li, S Gong, Y Han, X Li - 2017 IEEE International …, 2017 - computer.org
Abstract Convolutional Neural Networks (CNN) are very computation-intensive. Recently, a
lot of CNN accelerators based on the CNN intrinsic parallelism are proposed. However, we …