SparseTrain: Exploiting Dataflow Sparsity for Efficient Convolutional Neural Networks Training

07/21/2020
by   Pengcheng Dai, et al.
1

Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, 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 natural sparsity (resulted from ReLU or Pooling layers) and 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 CNNs topology onto 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 SparseTrain could achieve about 2.7 × speedup and 2.2 × energy efficiency improvement on average compared with the original training process.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

research
09/02/2019

SPRING: A Sparsity-Aware Reduced-Precision Monolithic 3D CNN Accelerator Architecture for Training and Inference

CNNs outperform traditional machine learning algorithms across a wide ra...
research
06/01/2018

Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training

Exploiting sparsity enables hardware systems to run neural networks fast...
research
06/15/2021

S2Engine: A Novel Systolic Architecture for Sparse Convolutional Neural Networks

Convolutional neural networks (CNNs) have achieved great success in perf...
research
02/18/2018

Efficient Sparse-Winograd Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are computationally intensive, whic...
research
09/16/2021

Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs

Machine/deep-learning (ML/DL) based techniques are emerging as a driving...
research
11/22/2019

SparseTrain:Leveraging Dynamic Sparsity in Training DNNs on General-Purpose SIMD Processors

Our community has greatly improved the efficiency of deep learning appli...
research
11/09/2021

Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networks

Sparse convolutional neural networks (CNNs) have gained significant trac...

Please sign up or login with your details

Forgot password? Click here to reset