Abstract
We propose joint allocation of computation resource and optical transmission time slices to realize ultralow-latency optical interconnection in time-synchronized HPC systems. Results show that over 80% reduction in buffering time is achieved at high load.
© 2019 The Author(s)
PDF ArticleMore Like This
Roe Hemenway
CTuV2 Conference on Lasers and Electro-Optics (CLEO:S&I) 2004
Yufang Yu, Nan Hua, Zhizhen Zhong, Jialong Li, Ruijie Luo, Zelin Zheng, and Xiaoping Zheng
S4C.6 Asia Communications and Photonics Conference (ACP) 2017
Jialong Li, Nan Hua, Chen Zhao, Yanhe Li, Xiaoping Zheng, and Bingkun Zhou
M4A.210 Asia Communications and Photonics Conference (ACP) 2020