STICKER: An Energy-Efficient Multi-Sparsity Compatible Accelerator for Convolutional Neural Networks in 65-nm CMOS
- 4 November 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 55 (2) , 465-477
Abstract
STICKER is an energy-efficient convolutional neural network (NN) processor. It mainly improves energy efficiency by making full use of sparsity. The network sparsity can potentially lower storage and computation requirements. However, the sparsity distribution of both activations and weights ranges from 2% to 99% in different layers or models. Therefore, good support for the sparsity distribution is the key to improve the energy efficiency. Three new features are proposed in this article to support wide sparsity distribution efficiently. First, multi-sparsity control and data flow are implemented for finer sparsity granularity support. It can automatically switch the processor among nine sparsity modes for higher energy efficiency. Second, a multi-mode hierarchical data memory which can be reconfigured for networks with different sparsity modes is designed for higher storage efficiency. Third, a multi-sparsity-compatible set-associative convolution processing element (PE) array is designed to efficiently carry out convolution operations under different sparsity modes, especially when both activations and weights are sparse. STICKER was implemented in a 65-nm CMOS technology. With its wide-range sparsity-supported capacity, the peak energy efficiency reaches 62.1 TOPS/W when sparsity ratios of both activations and weights are 5%. In a completely pruned Alexnet model, STICKER achieves 2.82 TOPS/W energy efficiency 1.8x higher than that of the state-of-the-art processors.Keywords
Funding Information
- National Key R&D Program (2018YFA0701500)
- National Natural Science Foundation of China (61934005, 61674094)
- Beijing Innovation Center for Future Chip
This publication has 25 references indexed in Scilit:
- DropSample : A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten Chinese character recognitionPattern Recognition, 2016
- EyerissACM SIGARCH Computer Architecture News, 2016
- EIEACM SIGARCH Computer Architecture News, 2016
- Going Deeper with Embedded FPGA Platform for Convolutional Neural Network2016
- 14.6 A 1.42TOPS/W deep convolutional neural network recognition processor for intelligent IoE systems2016
- CNNTracker: Online discriminative object tracking via deep convolutional neural networkApplied Soft Computing, 2016
- Going deeper with convolutions2015
- Fully convolutional networks for semantic segmentation2015
- Deep learningNature, 2015
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998