ORSAS: An Output Row-Stationary Accelerator for Sparse Neural Networks

ORSAS: An Output Row-Stationary Accelerator for Sparse Neural Networks

Various pruning skills and network compression methods make modern neural networks sparse for both weights and activations. However, GPUs (graphics processing units) and most of the customized CNN (convolutional neural networks) accelerators have not taken advantage of the sparsity of neural network...

Full description

Bibliographic Details
Main Authors: Chenxiao Lin, Yuezhong Liu, Delong Shang
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Convolution dataflow
data compression
imbalance
halo effects
high utilization
sparse neural network accelerator
Online Access:https://ieeexplore.ieee.org/document/10114404/

Internet

https://ieeexplore.ieee.org/document/10114404/

Similar Items