{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:13:05Z","timestamp":1761559985850,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,6,10]],"date-time":"2010-06-10T00:00:00Z","timestamp":1276128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,6,10]]},"DOI":"10.1145\/1807128.1807140","type":"proceedings-article","created":{"date-parts":[[2010,6,11]],"date-time":"2010-06-11T18:52:58Z","timestamp":1276282378000},"page":"75-86","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":101,"title":["Skew-resistant parallel processing of feature-extracting scientific user-defined functions"],"prefix":"10.1145","author":[{"given":"YongChul","family":"Kwon","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Magdalena","family":"Balazinska","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bill","family":"Howe","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jerome","family":"Rolia","sequence":"additional","affiliation":[{"name":"HP Labs, Bristol, UNK, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2010,6,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Amazon Elastic Compute Cloud (Amazon EC2). http:\/\/www.amazon.com\/gp\/browse.html?node=201590011.  Amazon Elastic Compute Cloud (Amazon EC2). http:\/\/www.amazon.com\/gp\/browse.html?node=201590011."},{"key":"e_1_3_2_1_2_1","unstructured":"Oceanic remote chemical analyzer (ORCA). http:\/\/armbrustlab.ocean.washington.edu\/.  Oceanic remote chemical analyzer (ORCA). http:\/\/armbrustlab.ocean.washington.edu\/."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1987.1676942"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/333607.333610"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1086\/163168"},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. of the 6th OSDI Symp.","author":"Dean J.","year":"2004","unstructured":"J. Dean and S. Ghemawat . MapReduce: simplified data processing on large clusters . In Proc. of the 6th OSDI Symp. , 2004 . J. Dean and S. Ghemawat. MapReduce: simplified data processing on large clusters. In Proc. of the 6th OSDI Symp., 2004."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000001"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/5992.988653"},{"key":"e_1_3_2_1_9_1","volume-title":"Partitioning and load balancing for emerging parallel applications and architectures","author":"Devine K.","year":"2006","unstructured":"K. Devine , E. Boman , and G. Karypis . Partitioning and load balancing for emerging parallel applications and architectures , chapter 6. 2006 . K. Devine, E. Boman, and G. Karypis. Partitioning and load balancing for emerging parallel applications and architectures, chapter 6. 2006."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/129888.129894"},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. of the 18th VLDB Conf.","author":"DeWitt D. J.","year":"1992","unstructured":"D. J. DeWitt , J. F. Naughton , D. A. Schneider , and S. Seshadri . Practical Skew Handling in Parallel Joins . In Proc. of the 18th VLDB Conf. , 1992 . D. J. DeWitt, J. F. Naughton, D. A. Schneider, and S. Seshadri. Practical Skew Handling in Parallel Joins. In Proc. of the 18th VLDB Conf., 1992."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of the 34th VLDB Conf.","author":"Clustera DeWitt","year":"2008","unstructured":"DeWitt et. al. Clustera : an integrated computation and data management system . In Proc. of the 34th VLDB Conf. , 2008 . DeWitt et. al. Clustera: an integrated computation and data management system. In Proc. of the 34th VLDB Conf., 2008."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1086\/174922"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/0117039"},{"key":"e_1_3_2_1_15_1","unstructured":"Hadoop. http:\/\/hadoop.apache.org\/.  Hadoop. http:\/\/hadoop.apache.org\/."},{"key":"e_1_3_2_1_16_1","unstructured":"Hive. http:\/\/hadoop.apache.org\/hive\/.  Hive. http:\/\/hadoop.apache.org\/hive\/."},{"key":"e_1_3_2_1_17_1","volume-title":"Proc. of the Third CIDR Conf.","author":"Howe B.","year":"2007","unstructured":"B. Howe , D. Maier , and L. Bright . Smoothing the roi curve for scientific data management applications . In Proc. of the Third CIDR Conf. , 2007 . B. Howe, D. Maier, and L. Bright. Smoothing the roi curve for scientific data management applications. In Proc. of the Third CIDR Conf., 2007."},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. of the 17th VLDB Conf.","author":"Hua K. A.","year":"1991","unstructured":"K. A. Hua and C. Lee . Handling data skew in multiprocessor database computers using partition tuning . In Proc. of the 17th VLDB Conf. , 1991 . K. A. Hua and C. Lee. Handling data skew in multiprocessor database computers using partition tuning. In Proc. of the 17th VLDB Conf., 1991."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1272996.1273005"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1088\/0067-0049\/182\/2\/608"},{"key":"e_1_3_2_1_22_1","volume-title":"7th Workshop on Large-Scale Distributed Systems for Information Retrieval","volume":"2009","author":"Lin J.","unstructured":"J. Lin . The Curse of Zipf and Limits to Parallelization : A Look at the Stragglers Problem in MapReduce . In 7th Workshop on Large-Scale Distributed Systems for Information Retrieval , volume i, 2009 . J. Lin. The Curse of Zipf and Limits to Parallelization: A Look at the Stragglers Problem in MapReduce. In 7th Workshop on Large-Scale Distributed Systems for Information Retrieval, volume i, 2009."},{"key":"e_1_3_2_1_23_1","volume-title":"Department of Energy","author":"Mount R. P.","year":"2004","unstructured":"R. P. Mount . The office of science data-management challenge. Technical report , Department of Energy , 2004 . R. P. Mount. The office of science data-management challenge. Technical report, Department of Energy, 2004."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1998.1469"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"e_1_3_2_1_26_1","unstructured":"Oracle. http:\/\/www.oracle.com\/database\/.  Oracle. http:\/\/www.oracle.com\/database\/."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-006-7561-5"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559865"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646468.1646474"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223801"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature03597"},{"key":"e_1_3_2_1_32_1","unstructured":"Sql server. http:\/\/www.microsoft.com\/sqlserver\/.  Sql server. http:\/\/www.microsoft.com\/sqlserver\/."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/440413a"},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. of the 17th VLDB Conf.","author":"Walton C. B.","year":"1991","unstructured":"C. B. Walton , A. G. Dale , and R. M. Jenevein . A Taxonomy and Performance Model of Data Skew Effects in Parallel Joins . In Proc. of the 17th VLDB Conf. , 1991 . C. B. Walton, A. G. Dale, and R. M. Jenevein. A Taxonomy and Performance Model of Data Skew Effects in Parallel Joins. In Proc. of the 17th VLDB Conf., 1991."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/564691.564711"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1086\/303683"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687565"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376720"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629600"},{"key":"e_1_3_2_1_41_1","volume-title":"Proc. of the 8th OSDI Symp.","author":"Yu","year":"2008","unstructured":"Yu et. al. DryadLINQ : A system for general-purpose distributed data-parallel computing using a high-level language . In Proc. of the 8th OSDI Symp. , 2008 . Yu et. al. DryadLINQ: A system for general-purpose distributed data-parallel computing using a high-level language. In Proc. of the 8th OSDI Symp., 2008."}],"event":{"name":"SOCC '10: ACM SIGMOD-SIGOPS Workshop on Cloud Computing in conjunction with SIGMOD 2010","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"],"location":"Indianapolis Indiana USA","acronym":"SOCC '10"},"container-title":["Proceedings of the 1st ACM symposium on Cloud computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1807128.1807140","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1807128.1807140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T12:17:34Z","timestamp":1750249054000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1807128.1807140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,10]]},"references-count":39,"alternative-id":["10.1145\/1807128.1807140","10.1145\/1807128"],"URL":"https:\/\/doi.org\/10.1145\/1807128.1807140","relation":{},"subject":[],"published":{"date-parts":[[2010,6,10]]},"assertion":[{"value":"2010-06-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}