SparseTrain: Exploiting Dataflow Sparsity for Efficient Convolutional Neural Networks Training
This addresses efficiency issues in CNN training for AI practitioners, though it appears incremental as it builds on existing sparsity exploitation methods.
The paper tackles the problem of high computational resource requirements for training Convolutional Neural Networks (CNNs) by proposing SparseTrain, which exploits sparsity through a pruning algorithm, sparse dataflow, and accelerator architecture, achieving about 2.7× speedup and 2.2× energy efficiency improvement on AlexNet/ResNet compared to original training.
Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity. It mainly involves three levels of innovations: activation gradients pruning algorithm, sparse training dataflow, and accelerator architecture. By applying a stochastic pruning algorithm on each layer, the sparsity of back-propagation gradients can be increased dramatically without degrading training accuracy and convergence rate. Moreover, to utilize both \textit{natural sparsity} (resulted from ReLU or Pooling layers) and \textit{artificial sparsity} (brought by pruning algorithm), a sparse-aware architecture is proposed for training acceleration. This architecture supports forward and back-propagation of CNN by adopting 1-Dimensional convolution dataflow. We have built %a simple compiler to map CNNs topology onto \textit{SparseTrain}, and a cycle-accurate architecture simulator to evaluate the performance and efficiency based on the synthesized design with $14nm$ FinFET technologies. Evaluation results on AlexNet/ResNet show that \textit{SparseTrain} could achieve about $2.7 \times$ speedup and $2.2 \times$ energy efficiency improvement on average compared with the original training process.