{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:43:09Z","timestamp":1780764189706,"version":"3.54.1"},"reference-count":43,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1109\/iiswc.2014.6983058","type":"proceedings-article","created":{"date-parts":[[2014,12,30]],"date-time":"2014-12-30T23:51:51Z","timestamp":1419983511000},"page":"191-201","source":"Crossref","is-referenced-by-count":49,"title":["Characterizing and subsetting big data workloads"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sally A.","family":"McKee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunjie","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.103"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2011.144"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2200\/S00193ED1V01Y200905CAC006"},{"key":"ref32","first-page":"727","article-title":"X-means: Extending K-means with efficient estimation of the number of clusters","author":"pelleg","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/605397.605403"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2006.302732"},{"key":"ref37","year":"2014","journal-title":"BigDataBench multi-tenancy version"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/s11704-012-2118-7","article-title":"Cloudrank-d: benchmarking and ranking cloud computing systems for data processing applications","volume":"6","author":"luo","year":"2012","journal-title":"Frontiers of Computer Science"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/978-3-642-53974-9_5","article-title":"The implications of diverse applications and scalable data sets in benchmarking big data systems","author":"jia","year":"2014","journal-title":"Specifying Big Data Benchmarks Springer"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2011.6114193"},{"key":"ref10","author":"white","year":"2009","journal-title":"Hadoop The Definitive Guide"},{"key":"ref40","year":"2014","journal-title":"TPC-C"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835958"},{"key":"ref12","author":"gray","year":"1992","journal-title":"Benchmark Handbook for Database and Transaction Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/978-3-642-53974-9_4","article-title":"From tpc-c to big data benchmarks: A functional workload model","author":"chen","year":"2014","journal-title":"Specifying Big Data Benchmarks"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.75"},{"key":"ref16","article-title":"BDGS: A scalable big data generator suite in big data benchmarking","author":"ming","year":"2014","journal-title":"Lecture Note in Computer Sciences Extended Version for the Fourth Workshop on Big Data Benchmarking"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687609"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213934"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2004.1310786"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704671"},{"key":"ref4","year":"2014","journal-title":"Big Data Benchmark"},{"key":"ref27","article-title":"Programming Guide","year":"2011","journal-title":"IA-32 Intel&#x00AF Architecture Software Developer s Manual"},{"key":"ref3","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"0","journal-title":"USENIX Conference on Networked Systems Design and Implementation"},{"key":"ref6","first-page":"1","article-title":"Quantifying the impact of input data sets on program behavior and its applications","volume":"5","author":"eeckhout","year":"2003","journal-title":"Journal of Instruction-Level Parallelism"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2007.4362196"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2150982"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2002.1106006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2006.302733"},{"key":"ref2","article-title":"The Digital Universe In 2020: Big Data, Bigger Digital Shadows, and Biggest Growth in the Far East","author":"john","year":"2012","journal-title":"IDC Report"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250713"},{"key":"ref1","author":"schmidt","year":"2014","journal-title":"Techonomy Conference"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1998.694759"},{"key":"ref22","author":"levinthal","year":"2014","journal-title":"Cycle Accounting Analysis on Intel Core 2 Processors"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168880"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559865"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2010.5649519"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807152"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/0470013192.bsa501"},{"key":"ref26","year":"2014","journal-title":"Performance Counters for Linux"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1145\/1241601.1241616","article-title":"Subsetting the SPEC CPU2006 benchmark suite","volume":"35","author":"phansalkar","year":"2007","journal-title":"ACM SIGARCH Computer Architecture News"},{"key":"ref25","article-title":"Performance Analysis Guide for Intel Core i7 Processor and Intel Xeon 5500 Processors","author":"levinthal","year":"2009","journal-title":"Intel Performance Analysis Guide"}],"event":{"name":"2014 IEEE International Symposium on Workload Characterization (IISWC)","location":"Raleigh, NC, USA","start":{"date-parts":[[2014,10,26]]},"end":{"date-parts":[[2014,10,28]]}},"container-title":["2014 IEEE International Symposium on Workload Characterization (IISWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6966889\/6983029\/06983058.pdf?arnumber=6983058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T13:39:34Z","timestamp":1598621974000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6983058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iiswc.2014.6983058","relation":{},"subject":[],"published":{"date-parts":[[2014,10]]}}}