Back to Search Start Over

Reduce Computational Complexity for Convolutional Layers by Skipping Zeros

Authors :
Zhang, Zhiyi
Zhang, Pengfei
Xu, Zhuopin
Wang, Qi
Source :
IEEE International Conference on High Performance Computing, Data and Analytics 2023 (HiPC)
Publication Year :
2023

Abstract

Convolutional neural networks necessitate good algorithms to reduce complexity, and sufficient utilization of parallel processors for acceleration. Within convolutional layers, there are three types of operators: convolution used in forward propagation, deconvolution and dilated-convolution utilized in backward propagation. During the execution of these operators, zeros are typically added to tensors, leading to redundant calculations and unnecessary strain on hardware. To circumvent these inefficiencies, we propose the C-K-S algorithm, accompanied by efficient GPU implementations. C-K-S trims filters to exclude zero-padding. For deconvolution and dilated-convolution, C-K-S transforms sparse tensors into dense tensors, and standardizes the local computational rules to simplify the hardware control. The experimental results demonstrate that C-K-S offers good performance in terms of speed and convergence, surpassing the capabilities of PyTorch and cuDNN in certain scenarios.

Details

Database :
arXiv
Journal :
IEEE International Conference on High Performance Computing, Data and Analytics 2023 (HiPC)
Publication Type :
Report
Accession number :
edsarx.2306.15951
Document Type :
Working Paper