Yi He, Yanjing Li. Understanding Permanent Hardware Failures in Deep Learning Training Accelerator Systems. In IEEE European Test Symposium, ETS 2023, Venezia, Italy, May 22-26, 2023. pages 1-6, IEEE, 2023. [doi]
@inproceedings{HeL23-10,
title = {Understanding Permanent Hardware Failures in Deep Learning Training Accelerator Systems},
author = {Yi He and Yanjing Li},
year = {2023},
doi = {10.1109/ETS56758.2023.10173972},
url = {https://doi.org/10.1109/ETS56758.2023.10173972},
researchr = {https://researchr.org/publication/HeL23-10},
cites = {0},
citedby = {0},
pages = {1-6},
booktitle = {IEEE European Test Symposium, ETS 2023, Venezia, Italy, May 22-26, 2023},
publisher = {IEEE},
isbn = {979-8-3503-3634-4},
}