WRA: A 2.2-to-6.3 TOPS highly unified dynamically reconfigurable accelerator using a novel Winograd decomposition algorithm for convolutional neural networks

C Yang, Y Wang, X Wang… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
As convolutional neural networks (CNNs) become more and more diverse and complicated,
acceleration of CNNs increasingly encounters a bottleneck of balancing performance …
被引用次数：43 相关文章

[引用][C] WRA: A 2.2-to-6.3 TOPS Highly Unified Dynamically Reconfigurable Accelerator Using a Novel Winograd Decomposition Algorithm for Convolutional Neural …

C Yang, Y Wang, X Wang, L Geng - … on Circuits and Systems I: Regular …, 2019 - cir.nii.ac.jp
WRA: A 2.2-to-6.3 TOPS Highly Unified Dynamically Reconfigurable Accelerator Using a Novel
Winograd Decomposition Algorithm for Convolutional Neural Networks | CiNii Research CiNii …