A Multi-Mode 8K-MAC HW-Utilization-Aware Neural Processing Unit with a Unified Multi-Precision Datapath in 4nm Flagship Mobile SoC-Reference-Cited by-同舟云学术

A Multi-Mode 8K-MAC HW-Utilization-Aware Neural Processing Unit with a Unified Multi-Precision Datapath in 4nm Flagship Mobile SoC

Published:2022-02-20 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE International Solid- State Circuits Conference (ISSCC)
language:
Short-container-title:

Author:

Park Jun-Seok¹,Park Changsoo¹,Kwon Suknam¹,Kim Hyeong-Seok¹,Jeon Taeho¹,Kang Yesung¹,Lee Heonsoo¹,Lee Dongwoo¹,Kim James¹,Lee YoungJong¹,Park Sangkyu¹,Jang Jun-Woo²,Ha SangHyuck¹,Kim MinSeong¹,Bang Jihoon¹,Lim Suk Hwan¹,Kang Inyup¹

Affiliation:

1. Samsung Electronics,Hwaseong,Korea

2. Samsung Advanced Institute of Technology,Suwon,Korea

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9731529/9731102/09731639.pdf?arnumber=9731639

Reference8 articles.

1. 7.1 A 3.4-to-13.3TOPS/W 3.6TOPS Dual-Core Deep-Learning Accelerator for Versatile AI Applications in 7nm 5G Smartphone SoC

2. Ten Lessons from Three Generations Shaped Google's TPUv4i;jouppi;ISGA,2021

3. A 6K-MAC Feature-Map-Sparsity-Aware Neural Processing Unit in 5nm Flagshig Mobile SoC;park;ISSCC,2021

4. 7.2 A 12nm Programmable Convolution-Efficient Neural-Processing-Unit Chip Achieving 825TOPS

5. MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

Cited by 19 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. Survey of Deep Learning Accelerators for Edge and Emerging Computing;Electronics;2024-07-29

2. A Precision-Aware Neuron Engine for DNN Accelerators;SN Computer Science;2024-04-26

3. 20.1 NVE: A 3nm 23.2TOPS/W 12b-Digital-CIM-Based Neural Engine for High-Resolution Visual-Quality Enhancement on Smart Devices;2024 IEEE International Solid-State Circuits Conference (ISSCC);2024-02-18

4. Zero and Narrow-Width Value-Aware Compression for Quantized Convolutional Neural Networks;IEEE Transactions on Computers;2024-01

5. A183.4-nJ/Inference 152.8-μW 35-Voice Commands Recognition Wired-Logic Processor Using Algorithm-Circuit Co-Optimization Technique;IEEE Solid-State Circuits Letters;2024