DistSim: A performance model of large-scale hybrid distributed DNN training

Guandong Lu, Runzhe Chen, Yakai Wang, Yangjie Zhou 0001, Rui Zhang, Zheng Hu, Yanming Miao, Zhifang Cai, Li Li 0012, Jingwen Leng, Minyi Guo. DistSim: A performance model of large-scale hybrid distributed DNN training. In Andrea Bartolini, Kristian F. D. Rietveld, Catherine D. Schuman, Jose Moreira, editors, Proceedings of the 20th ACM International Conference on Computing Frontiers, CF 2023, Bologna, Italy, May 9-11, 2023. pages 112-122, ACM, 2023. [doi]

@inproceedings{LuCW0ZHMC0LG23,
  title = {DistSim: A performance model of large-scale hybrid distributed DNN training},
  author = {Guandong Lu and Runzhe Chen and Yakai Wang and Yangjie Zhou 0001 and Rui Zhang and Zheng Hu and Yanming Miao and Zhifang Cai and Li Li 0012 and Jingwen Leng and Minyi Guo},
  year = {2023},
  doi = {10.1145/3587135.3592200},
  url = {https://doi.org/10.1145/3587135.3592200},
  researchr = {https://researchr.org/publication/LuCW0ZHMC0LG23},
  cites = {0},
  citedby = {0},
  pages = {112-122},
  booktitle = {Proceedings of the 20th ACM International Conference on Computing Frontiers, CF 2023, Bologna, Italy, May 9-11, 2023},
  editor = {Andrea Bartolini and Kristian F. D. Rietveld and Catherine D. Schuman and Jose Moreira},
  publisher = {ACM},
}