SoBS-X: Squeeze-Out Bit Sparsity for ReRAM-Crossbar-Based Neural Network Accelerator-Reference-Cited by-同舟云学术

SoBS-X: Squeeze-Out Bit Sparsity for ReRAM-Crossbar-Based Neural Network Accelerator

Published:2023-01 Issue:1 Volume:42 Page:204-217
ISSN:0278-0070
Container-title:IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
language:
Short-container-title:IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

Author:

Liu Fangxin¹^ORCID,Wang Zongwu¹,Chen Yongbiao¹,He Zhezhi¹^ORCID,Yang Tao¹^ORCID,Liang Xiaoyao¹,Jiang Li²^ORCID

Affiliation:

1. Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

2. Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China

Funder

National Natural Science Foundation of China

National Key Research and Development Program of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Computer Graphics and Computer-Aided Design,Software

Link

http://xplorestaging.ieee.org/ielx7/43/9996095/09769275.pdf?arnumber=9769275

Reference45 articles.

1. Very deep convolutional networks for large-scale image recognition;simonyan;arXiv 1409 1556,2014

2. NVSim: A Circuit-Level Performance, Energy, and Area Model for Emerging Nonvolatile Memory

3. Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks;li;Proc 8th Int Conf Learn Represent (ICLR),2020

4. A 65nm 1Mb nonvolatile computing-in-memory ReRAM macro with sub-16ns multiply-and-accumulate for binary DNN AI edge processors

5. A high-throughput and energy-efficient RRAM-based convolutional neural network using data encoding and dynamic quantization

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. CRPIM: An efficient compute-reuse scheme for ReRAM-based Processing-in-Memory DNN accelerators;Journal of Systems Architecture;2024-08

2. ReShare: A Resource-Efficient Weight Pattern Sharing Scheme for Memristive DNN Accelerators;2024 IEEE International Symposium on Circuits and Systems (ISCAS);2024-05-19

3. DE-C3: Dynamic Energy-Aware Compression for Computing-In-Memory-Based Convolutional Neural Network Acceleration;2023 IEEE 36th International System-on-Chip Conference (SOCC);2023-09-05

4. E-UPQ: Energy-Aware Unified Pruning-Quantization Framework for CIM Architecture;IEEE Journal on Emerging and Selected Topics in Circuits and Systems;2023-03

5. ERA-BS: Boosting the Efficiency of ReRAM-based PIM Accelerator with Fine-Grained Bit-Level Sparsity;IEEE Transactions on Computers;2023