View Document Preview and Link Document Date: 2014-02-02 20:47:34 Open Document File Size: 205,21 KB Share Result on Facebook
City Washington / DC / Berlin / San Diego / / Company Fujitsu / Amazon / eBay / Sun Microsystems / MIT Press / Netflix / Google / Facebook / Cisco / NetApp / HP / VMware / Intel / Microsoft / Yahoo! / / Country United States / Canada / / Facility D. Hall / University of California / Ion Stoica University of California / / IndustryTerm machine learning algorithms / statistical computing / relational data processing / dot product / iterative machine learning algorithms / large-scale data-intensive applications / e-science / interactive scientific computing / multicore systems / scientific data processing / cluster computing / parallel applications / consistency protocol / interactive data analysis tools / data processing / cluster computing framework / distributed data-parallel computing / cluster computing frameworks / iterative classification algorithm / scientific computing / learning algorithms / / Organization MIT / Berkeley RAD Lab / Ion Stoica University / University of California / Berkeley / Natural Sciences and Engineering Research Council of Canada / IEEE Computer Society / EECS Department / / Person Michael J. Franklin / Scott Shenker / Ali Ghodsi / J. Cheney / / Position driver / model of cluster computing / Python interpreter / Spark interpreter / Interpreter / Scala interpreter / programmer / / Product Spark / / ProgrammingLanguage Java / SQL / Scala / / ProvinceOrState California / / Technology functional programming / machine learning algorithms / iterative machine learning algorithms / API / ten learning algorithms / machine learning / operating system / html / shared memory / consistency protocol / load balancing / Java / caching / iterative classification algorithm / virtual memory / / URL http / SocialTag 
Spark: Cluster Computing with Working Sets Matei Zaharia, Mosharaf Chowdhury, Michael J. Franklin, Scott Shenker, Ion Stoica University of California, Berkeley Abstract MapReduce/Dryad job, each job must reload the data