1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
|
@article{bu2010haloop,
title={HaLoop: efficient iterative data processing on large clusters},
author={Bu, Yingyi and Howe, Bill and Balazinska, Magdalena and Ernst, Michael D},
journal={Proceedings of the VLDB Endowment},
volume={3},
number={1-2},
pages={285--296},
year={2010},
publisher={VLDB Endowment}
}
@inproceedings{chambers2010flumejava,
title={FlumeJava: easy, efficient data-parallel pipelines},
author={Chambers, Craig and Raniwala, Ashish and Perry, Frances and Adams, Stephen and Henry, Robert R and Bradshaw, Robert and Weizenbaum, Nathan},
booktitle={ACM Sigplan Notices},
volume={45},
number={6},
pages={363--375},
year={2010},
organization={ACM}
}
@article{ching2015one,
title={One trillion edges: graph processing at Facebook-scale},
author={Ching, Avery and Edunov, Sergey and Kabiljo, Maja and Logothetis, Dionysios and Muthukrishnan, Sambavi},
journal={Proceedings of the VLDB Endowment},
volume={8},
number={12},
pages={1804--1815},
year={2015},
publisher={VLDB Endowment}
}
@article{dean2008mapreduce,
title={MapReduce: simplified data processing on large clusters},
author={Dean, Jeffrey and Ghemawat, Sanjay},
journal={Communications of the ACM},
volume={51},
number={1},
pages={107--113},
year={2008},
publisher={ACM}
}
@inproceedings{ekanayake2010twister,
title={Twister: a runtime for iterative mapreduce},
author={Ekanayake, Jaliya and Li, Hui and Zhang, Bingjing and Gunarathne, Thilina and Bae, Seung-Hee and Qiu, Judy and Fox, Geoffrey},
booktitle={Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing},
pages={810--818},
year={2010},
organization={ACM}
}
@inproceedings{isard2007dryad,
title={Dryad: distributed data-parallel programs from sequential building blocks},
author={Isard, Michael and Budiu, Mihai and Yu, Yuan and Birrell, Andrew and Fetterly, Dennis},
booktitle={ACM SIGOPS Operating Systems Review},
volume={41},
number={3},
pages={59--72},
year={2007},
organization={ACM}
}
@inproceedings{malewicz2010pregel,
title={Pregel: a system for large-scale graph processing},
author={Malewicz, Grzegorz and Austern, Matthew H and Bik, Aart JC and Dehnert, James C and Horn, Ilan and Leiser, Naty and Czajkowski, Grzegorz},
booktitle={Proceedings of the 2010 ACM SIGMOD International Conference on Management of data},
pages={135--146},
year={2010},
organization={ACM}
}
@inproceedings{olston2008pig,
title={Pig latin: a not-so-foreign language for data processing},
author={Olston, Christopher and Reed, Benjamin and Srivastava, Utkarsh and Kumar, Ravi and Tomkins, Andrew},
booktitle={Proceedings of the 2008 ACM SIGMOD international conference on Management of data},
pages={1099--1110},
year={2008},
organization={ACM}
}
@article{pike2005interpreting,
title={Interpreting the data: Parallel analysis with Sawzall},
author={Pike, Rob and Dorward, Sean and Griesemer, Robert and Quinlan, Sean},
journal={Scientific Programming},
volume={13},
number={4},
pages={277--298},
year={2005},
publisher={Hindawi Publishing Corporation}
}
@online{WinNT,
author = {Tarau, Paul},
title = {Bulk synchronous model},
year = 2014,
url = {http://www.cse.unt.edu/~tarau/teaching/parpro/papers/Bulk%20synchronous%20parallel.pdf},
urldate = {2016-11-24}
}
@article{thusoo2009hive,
title={Hive: a warehousing solution over a map-reduce framework},
author={Thusoo, Ashish and Sarma, Joydeep Sen and Jain, Namit and Shao, Zheng and Chakka, Prasad and Anthony, Suresh and Liu, Hao and Wyckoff, Pete and Murthy, Raghotham},
journal={Proceedings of the VLDB Endowment},
volume={2},
number={2},
pages={1626--1629},
year={2009},
publisher={VLDB Endowment}
}
@inproceedings{thusoo2010hive,
title={Hive-a petabyte scale data warehouse using hadoop},
author={Thusoo, Ashish and Sarma, Joydeep Sen and Jain, Namit and Shao, Zheng and Chakka, Prasad and Zhang, Ning and Antony, Suresh and Liu, Hao and Murthy, Raghotham},
booktitle={2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)},
pages={996--1005},
year={2010},
organization={IEEE}
}
@inproceedings{yu2008dryadlinq,
title={DryadLINQ: A System for General-Purpose Distributed Data-Parallel Computing Using a High-Level Language.},
author={Yu, Yuan and Isard, Michael and Fetterly, Dennis and Budiu, Mihai and Erlingsson, {\'U}lfar and Gunda, Pradeep Kumar and Currey, Jon},
booktitle={OSDI},
volume={8},
pages={1--14},
year={2008}
}
@article{zaharia2010spark,
title={Spark: cluster computing with working sets.},
author={Zaharia, Matei and Chowdhury, Mosharaf and Franklin, Michael J and Shenker, Scott and Stoica, Ion},
journal={HotCloud},
volume={10},
pages={10--10},
year={2010}
}
@article{zhang2012imapreduce,
title={imapreduce: A distributed computing framework for iterative computation},
author={Zhang, Yanfeng and Gao, Qixin and Gao, Lixin and Wang, Cuirong},
journal={Journal of Grid Computing},
volume={10},
number={1},
pages={47--68},
year={2012},
publisher={Springer}
}
|
