Open access
Aug 2026
Flash-DWC: Making Depthwise Convolution Compute-Efficient on GPUs
By making DWC compute-efficient, Flash-DWC promotes the use of larger and more expressive filters and extends forward and backward propagation to both forward and backward propagation for efficient end-to-end training.
Zhiyi Zhang, Yang Zhao, Jing-Wei Sun et al.
· ACM Transactions on Architec... · 0 citations