@inproceedings{1d31b7ec5f58417da1a50ac2a3dcf770,
title = "Co-sites: The autonomous distributed dataflows in collaborative scientific discovery",
abstract = "Online {"}big data{"} processing applications have seen increas- ing importance in the high performance computing domain, including online analytics of large volumes of data output by various scientific applications. This work contributes to answering the question of how to promote efficient collaborative science in face of unpre- dictable analytics workloads and dynamics in available re- sources? It proposes the Co-Sites solution employing online resource management at the sites participating online collab- oration, including geographically distributed sites that may spread across large distances. Co-Sites operates by each site observing its local progress and making its own decisions to better utilize local resources and to maintain acceptable rates of global progress. Co-Sites further enriches such dis- tributed data ows to permit just-in-time data sharing to better leverage collaborators' diverse domain expertise. Experiments with a combustion workow demonstrate the Co-Sites solution with (i) improved end-to-end completion times, (ii) good scalability, and (iii) with good data sharing latencies.",
author = "Yanwei Zhang and Matthew Wolf and Karsten Schwan and Qing Liu and Greg Eisenhauer and Scott Klasky",
note = "Publisher Copyright: {\textcopyright} 2015 ACM.; 10th Workshop on Workflows in Support of Large-Scale Science, WORKS 2015 ; Conference date: 15-11-2015",
year = "2015",
month = nov,
day = "15",
doi = "10.1145/2822332.2822337",
language = "English (US)",
series = "Proceedings of WORKS 2015: 10th Workshop on Workflows in Support of Large-Scale Science - Held in conjunction with SC 2015: The International Conference for High Performance Computing, Networking, Storage and Analysis",
publisher = "Association for Computing Machinery, Inc",
booktitle = "Proceedings of WORKS 2015",
}