This open source computing framework unifies streaming, batch, and interactive big data workloads to unlock new applications. A simple programming model can capture streaming, batch, and interactive workloads and enable new applications that combine them. Apache Spark applications range from finance to scientific data processing and combine libraries for SQL, machine learning, and graphs. In six years, Apache Spark has grown to 1,000 contributors and thousands of deployments.
%0 Journal Article
%1 ZahariaXinEtAl16cacm
%A Zaharia, Matei
%A Xin, Reynold S.
%A Wendell, Patrick
%A Das, Tathagata
%A Armbrust, Michael
%A Dave, Ankur
%A Meng, Xiangrui
%A Rosen, Josh
%A Venkataraman, Shivaram
%A Franklin, Michael J.
%A Ghodsi, Ali
%A Gonzalez, Joseph
%A Shenker, Scott
%A Stoica, Ion
%D 2016
%J Communications of the ACM
%K 01841 acm paper ai data pattern recognition analysis information retrieval tool zzz.big
%N 11
%P 56--65
%R 10.1145/2934664
%T Apache Spark: A Unified Engine for Big Data Processing
%V 59
%X This open source computing framework unifies streaming, batch, and interactive big data workloads to unlock new applications. A simple programming model can capture streaming, batch, and interactive workloads and enable new applications that combine them. Apache Spark applications range from finance to scientific data processing and combine libraries for SQL, machine learning, and graphs. In six years, Apache Spark has grown to 1,000 contributors and thousands of deployments.
@article{ZahariaXinEtAl16cacm,
abstract = {This open source computing framework unifies streaming, batch, and interactive big data workloads to unlock new applications. A simple programming model can capture streaming, batch, and interactive workloads and enable new applications that combine them. Apache Spark applications range from finance to scientific data processing and combine libraries for SQL, machine learning, and graphs. In six years, Apache Spark has grown to 1,000 contributors and thousands of deployments.},
added-at = {2016-11-02T10:36:14.000+0100},
author = {Zaharia, Matei and Xin, Reynold S. and Wendell, Patrick and Das, Tathagata and Armbrust, Michael and Dave, Ankur and Meng, Xiangrui and Rosen, Josh and Venkataraman, Shivaram and Franklin, Michael J. and Ghodsi, Ali and Gonzalez, Joseph and Shenker, Scott and Stoica, Ion},
biburl = {https://www.bibsonomy.org/bibtex/2c215622ad306325525be6cbca36e57e1/flint63},
doi = {10.1145/2934664},
file = {ACM Digital Library:2016/ZahariaXinEtAl16cacm.pdf:PDF},
groups = {public},
interhash = {b738cb49f24ffce7c52974ab49a09b7f},
intrahash = {c215622ad306325525be6cbca36e57e1},
issn = {0001-0782},
journal = {Communications of the ACM},
keywords = {01841 acm paper ai data pattern recognition analysis information retrieval tool zzz.big},
month = {#nov#},
number = 11,
pages = {56--65},
timestamp = {2018-04-16T12:35:05.000+0200},
title = {{Apache Spark}: A Unified Engine for Big Data Processing},
username = {flint63},
volume = 59,
year = 2016
}