PL-NPU: An Energy-Efficient Edge-Device DNN Training Processor With Posit-Based Logarithm-Domain Computing-Reference-Cited by-同舟云学术

PL-NPU: An Energy-Efficient Edge-Device DNN Training Processor With Posit-Based Logarithm-Domain Computing

Published:2022-10 Issue:10 Volume:69 Page:4042-4055
ISSN:1549-8328
Container-title:IEEE Transactions on Circuits and Systems I: Regular Papers
language:
Short-container-title:IEEE Trans. Circuits Syst. I

Author:

Wang Yang¹^ORCID,Deng Dazheng¹,Liu Leibo¹^ORCID,Wei Shaojun¹^ORCID,Yin Shouyi¹^ORCID

Affiliation:

1. Beijing Innovation Center for Future Chip and the Beijing National Research Center for Information Science and Technology, School of Integrated Circuits, Tsinghua University, Beijing, China

Funder

NSFC

National Key Research and Development Program of China

Beijing Science and Technology Project

Beijing Advanced Innovation Center

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Hardware and Architecture

Link

http://xplorestaging.ieee.org/ielx7/8919/9904939/09803862.pdf?arnumber=9803862

Reference47 articles.

1. Evaluating the Hardware Cost of the Posit Number System

2. An extended precision logarithmic number system

3. The Accuracy of Floating Point Summation

4. A 22nm, 10.8 μ W/15.1 μ W Dual Computing Modes High Power-Performance-Area Efficiency Domained Background Noise Aware Keyword- Spotting Processor

5. Evaluations on Deep Neural Networks Training Using Posit Number System

Cited by 7 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. Energy-efficiency optimization for heterogeneous computing-assisted NOMA-MEC edge AI tasks;Future Generation Computer Systems;2025-01

2. Design of a novel low-latency parameterizable posit adder/subtractor using leading one predictor in FPGA;Digital Signal Processing;2024-12

3. A 28nm Energy-Area-Efficient Row-based pipelined Training Accelerator with Mixed FXP4/FP16 for On-Device Transfer Learning;2024 IEEE International Symposium on Circuits and Systems (ISCAS);2024-05-19

4. An Energy-Efficient Gain-Cell Embedded DRAM Design with Weight Encoding for CNN Applications;2023 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA);2023-10-27

5. Generating Posit-Based Accelerators With High-Level Synthesis;IEEE Transactions on Circuits and Systems I: Regular Papers;2023-10