MOZART+: Masking Outputs With Zeros for Improved Architectural Robustness and Testing of DNN Accelerators-Reference-Cited by-同舟云学术

MOZART+: Masking Outputs With Zeros for Improved Architectural Robustness and Testing of DNN Accelerators

Published:2022-06 Issue:2 Volume:22 Page:120-128
ISSN:1530-4388
Container-title:IEEE Transactions on Device and Materials Reliability
language:
Short-container-title:IEEE Trans. Device Mater. Relib.

Author:

Burel Stephane¹,Evans Adrian¹^ORCID,Anghel Lorena²^ORCID

Affiliation:

1. CEA, LIST, Univ. Grenoble Alpes, Grenoble, France

2. IRIG-Spintec Laboratory, Univ. Grenoble Alpes, CEA, CNRS, Grenoble INP (Institute of Engineering Univ. Grenoble Alpes), Grenoble, France

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Safety, Risk, Reliability and Quality,Electronic, Optical and Magnetic Materials

Link

http://xplorestaging.ieee.org/ielx7/7298/9789687/09733388.pdf?arnumber=9733388

Reference34 articles.

1. Soft Error Mitigation for Deep Convolution Neural Network on FPGA Accelerators

2. On the Resilience of RTL NN Accelerators: Fault Characterization and Mitigation

3. On the design of fault-tolerant two-dimensional systolic arrays for yield enhancement

4. Terminal brain damage: Exposing the graceless degradation in deep neural networks under hardware fault attacks;hong;Proc 28th USENIX Conf Secur Symp,2019

5. Reliable classification with ensemble convolutional neural networks;gao;Proc IEEE Int Symp Defect Fault Tolerance VLSI Syst (DFT),2020

Cited by 13 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. Understanding and Mitigating the Soft Error of Contrastive Language-Image Pre-training Models;2024 IEEE International Test Conference in Asia (ITC-Asia);2024-08-18

2. VitBit: Enhancing Embedded GPU Performance for AI Workloads through Register Operand Packing;Proceedings of the 53rd International Conference on Parallel Processing;2024-08-12

3. VANDOR: Mitigating SEUs into Quantized Neural Networks;2024 IEEE 30th International Symposium on On-Line Testing and Robust System Design (IOLTS);2024-07-03

4. Sensitivity analysis of similarity learning models for well-intervals based on logging data;Geoenergy Science and Engineering;2024-07

5. PerFT-N: Low-overhead Permanent Fault-Tolerance Mechanism for Neural Processing Units;Proceedings of the Great Lakes Symposium on VLSI 2024;2024-06-12