.png){kind=icon}
Return
A Balanced Sparse Matrix Convolution Accelerator for Efficient CNN Training
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSI.2024.3430831.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Sparse Convolutional Neural Network (CNN) training is well known to be time-consuming due to significant off-chip memory traffic. To effectively deploy sparse training, existing accelerators store matrices in a compressed format to eliminate memory accesses for zeros; hence, accelerators are designed to process compressed matrices to avoid zero computations. We have observed that the compression rate is greatly affected by the sparsity in the matrices with different formats. Given the varying levels of sparsity in activations, weights, errors, and gradients matrices throughout the sparse training process, it becomes impractical to achieve consistently high compression rates using a singular compression method for the entire duration of the training. Moreover, random zeros in the matrices result in irregular computation patterns, further increasing execution time. To address these issues, we propose a balanced sparse matrix convolution accelerator design for efficient CNN training. Specifically, a dual matrix compression technique is developed that seamlessly combines two widely used sparse matrix compression formats with a control algorithm for lower memory traffic during training. Based on this compression technique, a two-level workload balancing technique is then designed to further reduce the execution time and energy consumption. Finally, an accelerator is implemented to support the proposed techniques. The cycle-accurate simulation results show that the proposed accelerator reduces the execution time by 34% and the energy consumption by 24% on average compared to existing sparse training accelerators.
Keywords:
Convolutional neural network
training
sparse matrix compression
memory traffic
load balancing
Journal
IF:
5.2
Papers:
9.8K
Citations:
2.2W
Organization
View more organizations
Cited Papers
Effect of hot pressing densification on the cellular structure of black agglomerated cork board
PREAI
ShareSave
ShareSaveShareSaveHardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights.png)
PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAIShareSaveShareSaveShareSave View more