@inproceedings{a8ba5f02fa7647989c668337832f8a19,
title = "HadoopDB in action: Building real world applications",
abstract = "HadoopDB is a hybrid of MapReduce and DBMS technologies, designed to meet the growing demand of analyzing massive datasets on very large clusters of machines. Our previous work has shown that HadoopDB approaches parallel databases in performance and still yields the scalability and fault tolerance of MapReduce-based systems. In this demonstration, we focus on HadoopDB's flexible architecture and versatility with two real world application scenarios: a semantic web data application for protein sequence analysis and a business data warehousing application based on TPC-H. The demonstration offers a thorough walk-through of how to easily build applications on top of HadoopDB.",
keywords = "hadoop, hadoopdb, hive, mapreduce, parallel database, semantic web, tpc-h, uniprot",
author = "Azza Abouzied and Kamil Bajda-Pawlikowski and Jiewen Huang and Abadi, {Daniel J.} and Avi Silberschatz",
year = "2010",
doi = "10.1145/1807167.1807294",
language = "English (US)",
isbn = "9781450300322",
series = "Proceedings of the ACM SIGMOD International Conference on Management of Data",
pages = "1111--1113",
booktitle = "Proceedings of the 2010 International Conference on Management of Data, SIGMOD '10",
note = "2010 International Conference on Management of Data, SIGMOD '10 ; Conference date: 06-06-2010 Through 11-06-2010",
}