Dustin: A 16-Cores Parallel Ultra-Low-Power Cluster With 2b-to-32b Fully Flexible Bit-Precision and Vector Lockstep Execution Mode-Reference-Cited by-同舟云学术

Dustin: A 16-Cores Parallel Ultra-Low-Power Cluster With 2b-to-32b Fully Flexible Bit-Precision and Vector Lockstep Execution Mode

Published:2023-06 Issue:6 Volume:70 Page:2450-2463
ISSN:1549-8328
Container-title:IEEE Transactions on Circuits and Systems I: Regular Papers
language:
Short-container-title:IEEE Trans. Circuits Syst. I

Author:

Ottavi Gianmarco¹^ORCID,Garofalo Angelo¹^ORCID,Tagliavini Giuseppe²^ORCID,Conti Francesco¹^ORCID,Mauro Alfio Di³^ORCID,Benini Luca¹^ORCID,Rossi Davide¹^ORCID

Affiliation:

1. Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna, Bologna, Italy

2. Department of Computer Science and Engineering (DISI), University of Bologna, Bologna, Italy

3. IIS Integrated Systems Laboratory, ETH Züric, Züric, Switzerland

Funder

European Commission Horizon 2020 Framework through The European Pilot project

WiPLASH project

CSEL Joint Undertaking Horizon 2020 through the AI4DI

GreenWaves Technologies

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Hardware and Architecture

Link

http://xplorestaging.ieee.org/ielx7/8919/10137339/10071725.pdf?arnumber=10071725

Reference34 articles.

1. Mixed precision quantization of ConvNets via differentiable neural architecture search;wu;arXiv 1812 00090,2018

2. HAQ: Hardware-Aware Automated Quantization With Mixed Precision

3. Mr.Wolf: An Energy-Precision Scalable Parallel Ultra Low Power SoC for IoT Edge Processing

4. HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision

5. On periodic functions as regularizers for quantization of neural networks;naumov;arXiv 1811 09862,2018

Cited by 9 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. Integrating error correction and detection techniques in RISC-V processor microarchitecture for enhanced reliability;Integration;2024-09

2. Exploring RISC-V Based DNN Accelerators;2024 IEEE International Conference on Omni-layer Intelligent Systems (COINS);2024-07-29

3. A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference;2024 IEEE International Symposium on Circuits and Systems (ISCAS);2024-05-19

4. A Precision-Scalable RISC-V DNN Processor with On-Device Learning Capability at the Extreme Edge;2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC);2024-01-22

5. The Impact of Profiling Versus Static Analysis in Precision Tuning;IEEE Access;2024