Zhen Xie, Siddhisanket Raskar, Murali Emani, Venkatram Vishwanath. TrainBF: High-Performance DNN Training Engine Using BFloat16 on AI Accelerators. In José Cano 0001, Marios D. Dikaiakos, George A. Papadopoulos, Miquel Pericàs, Rizos Sakellariou, editors, Euro-Par 2023: Parallel Processing - 29th International Conference on Parallel and Distributed Computing, Limassol, Cyprus, August 28 - September 1, 2023, Proceedings. Volume 14100 of Lecture Notes in Computer Science, pages 458-473, Springer, 2023. [doi]
@inproceedings{XieREV23,
title = {TrainBF: High-Performance DNN Training Engine Using BFloat16 on AI Accelerators},
author = {Zhen Xie and Siddhisanket Raskar and Murali Emani and Venkatram Vishwanath},
year = {2023},
doi = {10.1007/978-3-031-39698-4_31},
url = {https://doi.org/10.1007/978-3-031-39698-4_31},
researchr = {https://researchr.org/publication/XieREV23},
cites = {0},
citedby = {0},
pages = {458-473},
booktitle = {Euro-Par 2023: Parallel Processing - 29th International Conference on Parallel and Distributed Computing, Limassol, Cyprus, August 28 - September 1, 2023, Proceedings},
editor = {José Cano 0001 and Marios D. Dikaiakos and George A. Papadopoulos and Miquel Pericàs and Rizos Sakellariou},
volume = {14100},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-031-39698-4},
}