An 8.9–71.3 TOPS/W Deep Learning Accelerator for Arbitrarily Quantized Neural Networks-Reference-Cited by-同舟云学术

An 8.9–71.3 TOPS/W Deep Learning Accelerator for Arbitrarily Quantized Neural Networks

Published:2022-10 Issue:10 Volume:69 Page:4148-4152
ISSN:1549-7747
Container-title:IEEE Transactions on Circuits and Systems II: Express Briefs
language:
Short-container-title:IEEE Trans. Circuits Syst. II

Author:

Moon Seunghyun¹^ORCID,Lee Kyeong-Jun¹^ORCID,Mun Han-Gyeol¹^ORCID,Kim Byungjun²^ORCID,Sim Jae-Yoon²^ORCID

Affiliation:

1. Department of Convergence IT Engineering, Pohang University of Science and Technology, Pohang, South Korea

2. Department of Electronic and Electrical Engineering, Pohang University of Science and Technology, Pohang, South Korea

Funder

National Research Foundation

Korea Ministry of Science and ICT

IC Design Education Center

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering

Link

http://xplorestaging.ieee.org/ielx7/8920/9900496/09803289.pdf?arnumber=9803289

Reference18 articles.

1. Deep residual learning for image recognition;he;arxiv abs/1512 03385,2015

2. Attention is all you need;vaswani;ArXiv abs/1706 03762,2017

3. A 3.4-to-13.3TOPS/W 3.6TOPS dual-core deep-learning accelearator for versatile AI applications in 7nm 5G Smartphone SoC;lin;Proc Int l Solid-States Circuits Conf (ISSCC),2020

4. 9.2 A 28nm 12.1TOPS/W Dual-Mode CNN Processor Using Effective-Weight-Based Convolution and Error-Compensation-Based Prediction

Cited by 3 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. Memory-Efficient Batch Normalization by One-Pass Computation for On-Device Training;IEEE Transactions on Circuits and Systems II: Express Briefs;2024-06

2. Multipurpose Deep-Learning Accelerator for Arbitrary Quantization With Reduction of Storage, Logic, and Latency Waste;IEEE Journal of Solid-State Circuits;2024-01

3. A 127.8TOPS/W Arbitrarily Quantized 1-to-8b Scalable-Precision Accelerator for General-Purpose Deep Learning with Reduction of Storage, Logic and Latency Waste;2023 IEEE International Solid- State Circuits Conference (ISSCC);2023-02-19