{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:13:09Z","timestamp":1784178789859,"version":"3.55.0"},"reference-count":27,"publisher":"Association for Computing Machinery (ACM)","issue":"11","license":[{"start":{"date-parts":[[2017,10,28]],"date-time":"2017-10-28T00:00:00Z","timestamp":1509148800000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1139158"],"award-info":[{"award-number":["CCF-1139158"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2016,10,28]]},"abstract":"<jats:p>This open source computing framework unifies streaming, batch, and interactive big data workloads to unlock new applications.<\/jats:p>","DOI":"10.1145\/2934664","type":"journal-article","created":{"date-parts":[[2016,10,31]],"date-time":"2016-10-31T08:29:14Z","timestamp":1477902554000},"page":"56-65","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2129,"title":["Apache Spark"],"prefix":"10.1145","volume":"59","author":[{"given":"Matei","family":"Zaharia","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA and Databricks, San Francisco, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reynold S.","family":"Xin","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Wendell","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tathagata","family":"Das","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Armbrust","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Dave","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangrui","family":"Meng","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josh","family":"Rosen","sequence":"additional","affiliation":[{"name":"Databricks, San Francisco, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shivaram","family":"Venkataraman","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael J.","family":"Franklin","sequence":"additional","affiliation":[{"name":"University of Chicago and University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Ghodsi","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Gonzalez","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Shenker","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ion","family":"Stoica","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2016,10,28]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Apache Storm project; http:\/\/storm.apache.org"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"e_1_2_1_3_1","unstructured":"Dave A. Indexedrdd project; http:\/\/github.com\/amplab\/spark-indexedrdd"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/1251254.1251264"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3041"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685096"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1272996.1273005"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1873601.1873677"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the Seventh Biennial CIDR Conference on Innovative Data Systems Research","author":"Kornacker M.","year":"2015","unstructured":"Kornacker, M. et al. Impala: A modern, open-source SQL engine for Hadoop. In Proceedings of the Seventh Biennial CIDR Conference on Innovative Data Systems Research (Asilomar, CA, Jan. 4--7, 2015)."},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the 38th International VLDB Conference on Very Large Databases","author":"Low Y.","year":"2012","unstructured":"Low, Y. et al. Distributed GraphLab: A framework for machine learning and data mining in the cloud. In Proceedings of the 38th International VLDB Conference on Very Large Databases (Istanbul, Turkey, Aug. 27--31, 2012)."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807184"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/2831090.2831104"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920886"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946679"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742787"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.158"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2005.1"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2011.25"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"e_1_2_1_21_1","unstructured":"Venkataraman S. et al. SparkR; http:\/\/dl.acm.org\/citation.cfm?id=2903740&CFID=687410325&CFTOKEN=83630888"},{"key":"e_1_2_1_22_1","unstructured":"Xin R. and Zaharia M. Lessons from running large-scale Spark workloads; http:\/\/tinyurl.com\/large-scale-spark"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465288"},{"key":"e_1_2_1_24_1","unstructured":"Zaharia M. An Architecture for Fast and General Data Processing on Large Clusters. Ph.D. thesis Electrical Engineering and Computer Sciences Department University of California Berkeley 2014; https:\/\/www.eecs.berkeley.edu\/Pubs\/TechRpts\/2014\/EECS-2014-12.pdf"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2228298.2228301"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522737"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7363840"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2934664","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2934664","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2934664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:43:55Z","timestamp":1763459035000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2934664"}},"subtitle":["a unified engine for big data processing"],"short-title":[],"issued":{"date-parts":[[2016,10,28]]},"references-count":27,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2016,10,28]]}},"alternative-id":["10.1145\/2934664"],"URL":"https:\/\/doi.org\/10.1145\/2934664","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10,28]]},"assertion":[{"value":"2016-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}