EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since published in ISCA’16, it opened a new design space to accelerate pruned and sparse neural networks and spawned many algorithm-hardware co-designs for model compression and acceleration, both in academia and commercial AI chips. In retrospect, we review the background of this project, summarize the pros and cons, and discuss new opportunities where pruning, sparsity, and low-precision can accelerate emerging deep learning workloads.
@article{han2023retrospective,
title={Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network},
author={Han, Song and Liu, Xingyu and Mao, Huizi and Pu, Jing and Pedram, Ardavan and Horowitz, Mark A and Dally, William J},
journal={arXiv preprint arXiv:2306.09552},
year={2023}
}
