arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.09552cs.AR
收藏

回顾:EIE:面向稀疏与压缩神经网络的高效推理引擎

Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network

Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A. Horowitz, William J. Dally

AI总结:

本文回顾了2016年发表的EIE稀疏压缩神经网络加速引擎,梳理其研究背景与优缺点,指出该工作开辟了稀疏神经网络加速的新设计空间,并探讨了剪枝、稀疏与低精度技术加速新兴深度学习负载的新方向。

摘要:

EIE(高效推理引擎)提出通过利用神经网络加速器中的权重稀疏性、激活稀疏性以及4位权重量化共享,来加速经过剪枝与压缩的神经网络。自2016年发表于ISCA以来,它开辟了剪枝与稀疏神经网络加速的全新设计空间,在学术界与商用AI芯片领域催生了大量面向模型压缩与加速的算法-硬件协同设计研究。本次回顾中,我们梳理了该项目的研究背景,总结了其优缺点,并探讨了剪枝、稀疏性与低精度技术可用于加速新兴深度学习工作负载的新机遇。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑