{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:11:08Z","timestamp":1730200268048,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,10]]},"DOI":"10.1109\/bigdata50022.2020.9377841","type":"proceedings-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T21:10:21Z","timestamp":1616188221000},"page":"2649-2653","source":"Crossref","is-referenced-by-count":0,"title":["A middle-ware approach to leverage the distributed data de-duplication capability on HPC and Cloud storage systems"],"prefix":"10.1109","author":[{"given":"Hsing-bung","family":"Chen","sequence":"first","affiliation":[]},{"given":"Sihai","family":"tang","sequence":"additional","affiliation":[]},{"given":"Song","family":"Fu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"SS-CDC: a two-stage parallel content-defined chunking for deduplicating backup storage","author":"fan","year":"2019","journal-title":"SYSTOR '19 Proceedings of the 12th ACM International Conference on Systems and StorageMay"},{"key":"ref11","article-title":"Design of Global Data De-duplication for a Scale-Out Distributed Storage System","author":"oh","year":"0","journal-title":"2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)"},{"key":"ref12","article-title":"Estimation of de-duplication ratios in large data sets","author":"harnik","year":"0","journal-title":"Mass Storage Systems and Technologies (MSST) 2012 IEEE 28th Symposium on"},{"key":"ref13","article-title":"De-duplication Potential of HPC Applications’ Checkpoints","author":"kaiser","year":"0","journal-title":"2016 IEEE International Conference on Cluster Computing (CLUSTER)"},{"key":"ref14","article-title":"Optimizing Checkpoint Restart with Data De-duplication","author":"chen","year":"2016","journal-title":"Scientific Computing"},{"key":"ref15","article-title":"Study of Chunking Algorithm in Data De-duplication","author":"venish","year":"0","journal-title":"Proceedings of the 2015 International Conference on Soft Computing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-48800-3_25"},{"journal-title":"2018 International Journal of Cyber-Security and Digital Forensics","article-title":"Analysis of Secure Hash Algorithm (SHA) 512 for Encryption Process on Web Based Application","year":"0","key":"ref17"},{"journal-title":"Redhat Release 8 Deduplicating and compressing storage","year":"0","key":"ref18"},{"key":"ref19","article-title":"A middle-ware approach to leverage the distributed data de-duplication capability on HPC and Cloud storage systems","author":"chen","year":"0","journal-title":"LAUR-XX-YYYY Los Alamos National Laboratory Technical report"},{"key":"ref4","article-title":"A survey: On data de-duplication for efficiently utilizing cloud storage for big data backups","author":"bhallerao","year":"0","journal-title":"2017 ICEI International Conference on Trends in Electronics and Informatics"},{"journal-title":"Arista networks","year":"0","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2611778"},{"key":"ref6","article-title":"A study on data de-duplication in HPC storage systems","author":"meister","year":"0","journal-title":"IEEE 2012 Proceedings of the International Conference on High Performance Computing Networking Storage and Analysis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-120418"},{"key":"ref8","article-title":"99 De-duplication Problems","author":"shilane","year":"0","journal-title":"USENIX 2016 HotStorages Conference"},{"key":"ref7","article-title":"Improving Storage Efficiencies with Data De-duplication","author":"scully","year":"2010","journal-title":"IDC White Paper"},{"key":"ref2","article-title":"Survey on De-duplication Techniques in Flash-Based Storage","author":"chernov","year":"0","journal-title":"Proceeding Of The 22nd Conference Of Fruct Association"},{"key":"ref9","article-title":"FastCDC: A Fast and Efficient Content-Defined Chunking Approach for Data De-duplication","author":"xia","year":"2016","journal-title":"2016 USENIX Annual Technical Conference"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/JPROC.2016.2571298","article-title":"A Comprehensive Study of the Past, Present, and Future of Data De-duplication","volume":"104","author":"xia","year":"2016","journal-title":"Proceedings of the IEEE"},{"journal-title":"Redis","year":"0","key":"ref20"},{"journal-title":"Los Alamos National Laboratory Ultrascale Systems Research Center (USRC) Data Sources","year":"0","key":"ref22"},{"key":"ref21","article-title":"Optimizing Checkpoint Restart with Data De-duplication","volume":"2016","author":"chen","year":"0","journal-title":"Journal of Scientific Programming special Issue on Resource Management in Virtualized Clouds"},{"key":"ref24","article-title":"0.374 Pflop\/s Trillion-Particle Kinetic Modeling of Laser Plasma Interaction on Road-runner","author":"bowers","year":"0","journal-title":"Proc 2008 ACM\/IEEE Conf Supercomputing"},{"journal-title":"Backblaze open source disk smart data sets","year":"0","key":"ref23"},{"journal-title":"RockPort Networka","year":"0","key":"ref26"},{"journal-title":"Disk Smart data","year":"0","key":"ref25"}],"event":{"name":"2020 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2020,12,10]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2020,12,13]]}},"container-title":["2020 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9377717\/9377728\/09377841.pdf?arnumber=9377841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:53:31Z","timestamp":1656345211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9377841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,10]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/bigdata50022.2020.9377841","relation":{},"subject":[],"published":{"date-parts":[[2020,12,10]]}}}