@article{cattell2011scalable, title={Scalable SQL and NoSQL data stores}, author={Cattell, Rick}, journal={ACM SIGMOD Record}, volume={39}, number={4}, pages={12--27}, year={2011}, publisher={ACM} } @article{chang2008bigtable, title={Bigtable: A distributed storage system for structured data}, author={Chang, Fay and Dean, Jeffrey and Ghemawat, Sanjay and Hsieh, Wilson C and Wallach, Deborah A and Burrows, Mike and Chandra, Tushar and Fikes, Andrew and Gruber, Robert E}, journal={ACM Transactions on Computer Systems (TOCS)}, volume={26}, number={2}, pages={4}, year={2008}, publisher={ACM} } @inproceedings{decandia2007dynamo, title={Dynamo: amazon's highly available key-value store}, author={DeCandia, Giuseppe and Hastorun, Deniz and Jampani, Madan and Kakulapati, Gunavardhan and Lakshman, Avinash and Pilchin, Alex and Sivasubramanian, Swaminathan and Vosshall, Peter and Vogels, Werner}, booktitle={ACM SIGOPS Operating Systems Review}, volume={41}, number={6}, pages={205--220}, year={2007}, organization={ACM} } @inproceedings{bear2012vertica, title={The vertica database: SQL RDBMS for managing big data}, author={Bear, Chuck and Lamb, Andrew and Tran, Nga}, booktitle={Proceedings of the 2012 workshop on Management of big data systems}, pages={37--38}, year={2012}, organization={ACM} } @article{lakshman2010cassandra, title={Cassandra—A decentralized structured storage system}, author={Lakshman, Avinash and Malik, Prashant}, journal={Operating systems review}, volume={44}, number={2}, pages={35}, year={2010} } @article{melnik2010dremel, title={Dremel: interactive analysis of web-scale datasets}, author={Melnik, Sergey and Gubarev, Andrey and Long, Jing Jing and Romer, Geoffrey and Shivakumar, Shiva and Tolton, Matt and Vassilakis, Theo}, journal={Proceedings of the VLDB Endowment}, volume={3}, number={1-2}, pages={330--339}, year={2010}, publisher={VLDB Endowment} } @article{hall2012processing, title={Processing a trillion cells per mouse click}, author={Hall, Alexander and Bachmann, Olaf and B{\"u}ssow, Robert and G{\u{a}}nceanu, Silviu and Nunkesser, Marc}, journal={Proceedings of the VLDB Endowment}, volume={5}, number={11}, pages={1436--1446}, year={2012}, publisher={VLDB Endowment} } @inproceedings{shvachko2010hadoop, title={The hadoop distributed file system}, author={Shvachko, Konstantin and Kuang, Hairong and Radia, Sanjay and Chansler, Robert}, booktitle={Mass Storage Systems and Technologies (MSST), 2010 IEEE 26th Symposium on}, pages={1--10}, year={2010}, organization={IEEE} } @article{colantonio2010concise, title={Concise: Compressed ‘n’Composable Integer Set}, author={Colantonio, Alessandro and Di Pietro, Roberto}, journal={Information Processing Letters}, volume={110}, number={16}, pages={644--650}, year={2010}, publisher={Elsevier} } @article{lerner2010redis, title={At the Forge: Redis}, author={Lerner, Richard}, journal={Linux Journal}, volume={2010}, number={197}, pages={3}, year={2010} } @inproceedings{stonebraker2005c, title={C-store: a column-oriented DBMS}, author={Stonebraker, Mike and Abadi, Daniel J and Batkin, Adam and Chen, Xuedong and Cherniack, Mitch and Ferreira, Miguel and Lau, Edmond and Lin, Amerson and Madden, Sam and O'Neil, Elizabeth and others}, booktitle={Proceedings of the 31st international conference on Very large data bases}, pages={553--564}, year={2005}, organization={VLDB Endowment} } @inproceedings{engle2012shark, title={Shark: fast data analysis using coarse-grained distributed memory}, author={Engle, Cliff and Lupher, Antonio and Xin, Reynold and Zaharia, Matei and Franklin, Michael J and Shenker, Scott and Stoica, Ion}, booktitle={Proceedings of the 2012 international conference on Management of Data}, pages={689--692}, year={2012}, organization={ACM} } @inproceedings{zaharia2012discretized, title={Discretized streams: an efficient and fault-tolerant model for stream processing on large clusters}, author={Zaharia, Matei and Das, Tathagata and Li, Haoyuan and Shenker, Scott and Stoica, Ion}, booktitle={Proceedings of the 4th USENIX conference on Hot Topics in Cloud Computing}, pages={10--10}, year={2012}, organization={USENIX Association} } @misc{marz2013storm, author = {Marz, Nathan}, title = {Storm: Distributed and Fault-Tolerant Realtime Computation}, month = {February}, year = {2013}, howpublished = "\url{http://storm-project.net/}" } @article{farber2012sap, title={SAP HANA database: data management for modern business applications}, author={F{\"a}rber, Franz and Cha, Sang Kyun and Primsch, J{\"u}rgen and Bornh{\"o}vd, Christof and Sigg, Stefan and Lehner, Wolfgang}, journal={ACM Sigmod Record}, volume={40}, number={4}, pages={45--51}, year={2012}, publisher={ACM} } @misc{voltdb2010voltdb, title={VoltDB Technical Overview}, author={VoltDB, LLC}, year={2010}, howpublished = "\url{https://voltdb.com/}" } @inproceedings{macnicol2004sybase, title={Sybase IQ multiplex-designed for analytics}, author={MacNicol, Roger and French, Blaine}, booktitle={Proceedings of the Thirtieth international conference on Very large data bases-Volume 30}, pages={1227--1230}, year={2004}, organization={VLDB Endowment} } @inproceedings{singh2011introduction, title={Introduction to the IBM Netezza warehouse appliance}, author={Singh, Malcolm and Leonhardi, Ben}, booktitle={Proceedings of the 2011 Conference of the Center for Advanced Studies on Collaborative Research}, pages={385--386}, year={2011}, organization={IBM Corp.} } @inproceedings{miner2012unified, title={Unified analytics platform for big data}, author={Miner, Donald}, booktitle={Proceedings of the WICSA/ECSA 2012 Companion Volume}, pages={176--176}, year={2012}, organization={ACM} } @inproceedings{fink2012distributed, title={Distributed computation on dynamo-style distributed storage: riak pipe}, author={Fink, Bryan}, booktitle={Proceedings of the eleventh ACM SIGPLAN workshop on Erlang workshop}, pages={43--50}, year={2012}, organization={ACM} } @misc{paraccel2013, key = {ParAccel Analytic Database}, title = {ParAccel Analytic Database}, month = {March}, year = {2013}, howpublished = "\url{http://www.paraccel.com/resources/Datasheets/ParAccel-Core-Analytic-Database.pdf}" } @article{barroso2009datacenter, title={The datacenter as a computer: An introduction to the design of warehouse-scale machines}, author={Barroso, Luiz Andr{\'e} and H{\"o}lzle, Urs}, journal={Synthesis Lectures on Computer Architecture}, volume={4}, number={1}, pages={1--108}, year={2009}, publisher={Morgan \& Claypool Publishers} } @article{chaudhuri1997overview, title={An overview of data warehousing and OLAP technology}, author={Chaudhuri, Surajit and Dayal, Umeshwar}, journal={ACM Sigmod record}, volume={26}, number={1}, pages={65--74}, year={1997} } @article{dewitt1992parallel, title={Parallel database systems: the future of high performance database systems}, author={DeWitt, David and Gray, Jim}, journal={Communications of the ACM}, volume={35}, number={6}, pages={85--98}, year={1992}, publisher={ACM} } @misc{cloudera2013, key = {Cloudera Impala}, title = {Cloudera Impala}, month = {March}, year = {2013}, url = {}, howpublished = "\url{http://blog.cloudera.com/blog}" } @inproceedings{hunt2010zookeeper, title={ZooKeeper: Wait-free coordination for Internet-scale systems}, author={Hunt, Patrick and Konar, Mahadev and Junqueira, Flavio P and Reed, Benjamin}, booktitle={USENIX ATC}, volume={10}, year={2010} } @inproceedings{kreps2011kafka, title={Kafka: A distributed messaging system for log processing}, author={Kreps, Jay and Narkhede, Neha and Rao, Jun}, booktitle={Proceedings of 6th International Workshop on Networking Meets Databases (NetDB), Athens, Greece}, year={2011} } @misc{liblzf2013, title = {LibLZF}, key = {LibLZF}, month = {March}, year = {2013}, howpublished = "\url{http://freecode.com/projects/liblzf}" } @inproceedings{tomasic1993performance, title={Performance of inverted indices in shared-nothing distributed text document information retrieval systems}, author={Tomasic, Anthony and Garcia-Molina, Hector}, booktitle={Parallel and Distributed Information Systems, 1993., Proceedings of the Second International Conference on}, pages={8--17}, year={1993}, organization={IEEE} } @inproceedings{antoshenkov1995byte, title={Byte-aligned bitmap compression}, author={Antoshenkov, Gennady}, booktitle={Data Compression Conference, 1995. DCC'95. Proceedings}, pages={476}, year={1995}, organization={IEEE} } @inproceedings{van2011memory, title={A memory efficient reachability data structure through bit vector compression}, author={van Schaik, Sebastiaan J and de Moor, Oege}, booktitle={Proceedings of the 2011 international conference on Management of data}, pages={913--924}, year={2011}, organization={ACM} } @inproceedings{o1993lru, title={The LRU-K page replacement algorithm for database disk buffering}, author={O'neil, Elizabeth J and O'neil, Patrick E and Weikum, Gerhard}, booktitle={ACM SIGMOD Record}, volume={22}, number={2}, pages={297--306}, year={1993}, organization={ACM} } @article{kim2001lrfu, title={LRFU: A spectrum of policies that subsumes the least recently used and least frequently used policies}, author={Kim, Chong Sang}, journal={IEEE Transactions on Computers}, volume={50}, number={12}, year={2001} } @article{wu2006optimizing, title={Optimizing bitmap indices with efficient compression}, author={Wu, Kesheng and Otoo, Ekow J and Shoshani, Arie}, journal={ACM Transactions on Database Systems (TODS)}, volume={31}, number={1}, pages={1--38}, year={2006}, publisher={ACM} } @misc{twitter2013, key = {Twitter Public Streams}, title = {Twitter Public Streams}, month = {March}, year = {2013}, howpublished = "\url{https://dev.twitter.com/docs/streaming-apis/streams/public}" } @article{fitzpatrick2004distributed, title={Distributed caching with memcached}, author={Fitzpatrick, Brad}, journal={Linux journal}, number={124}, pages={72--74}, year={2004} } @inproceedings{amdahl1967validity, title={Validity of the single processor approach to achieving large scale computing capabilities}, author={Amdahl, Gene M}, booktitle={Proceedings of the April 18-20, 1967, spring joint computer conference}, pages={483--485}, year={1967}, organization={ACM} }