DOE OSTI · code-121881
DDStore
Abstract
DDStore is designed to addresses random, read-oriented, global shuffle operations for data-intensive deep learning applications. By preserving global shuffling, DDStore ensures that deep learning model maintains high accuracy and generalizability when it is trained with large volume of data using HPC facilities.
Keep this discovery
Explore connections, maps & timelines
Choi, Jong Youl [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000264596152), Lupo Pasini, Massimiliano [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000249806924), Mehta, Kshitij [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000297149981), Zhang, Pei [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000283510529), Ibrahim, Khaled [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (0009000453623612), Bae, Jonghyun [Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)] (0000000280019451). 2024-02-09. DDStore. https://doi.org/10.11578/dc.20240209.1
Cite the original work for its findings. Save a collection to share your selection of sources.