Review of Data-parallel Programming Model

被引：0
作者：
Hou, Ke [1 ,2 ]
Zhang, Jing [1 ]
Li, Jun-huai [1 ]
机构：
[1] Xian Univ Technol, Inst Comp Sci & Engn, Xian, Peoples R China
[2] Xian Shiyou Univ, Sch Econ Management, Xian, Peoples R China
来源：
PROCEEDINGS OF 2012 7TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE & EDUCATION, VOLS I-VI | 2012年
关键词：
DPPM; deployment of storage and computation; task partition; fault tolerance;
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
Data-parallel programming model (DPPM for short) specialized for data-intensive computing becomes considerable popular because it simplifies the development of distributed parallel programs. DPPMs are classified into two categories: 1) MapReduce, Dryad; and 2) Piccolo, Function Flow, etc. based on their maturity. We analyze and compare these typical models by deployment, application, data partition, communication, fault tolerance and so on. Finally, we pay more attention to discussing development of key technologies which are deployment of storage and computation, task partition and fault tolerance in DPPM.
引用
收藏
页码：629 / 633
页数：5
相关论文
共 29 条
  • [1] [Anonymous], 2009, CLOUDS BERKELEY VIEW
  • [2] [Anonymous], 2010, P 19 ACM INT S HIGH, DOI DOI 10.1145/1851476.1851593
  • [3] [Anonymous], P 2010 ACM SIGMOD IN, DOI [DOI 10.1145/1807167.1807184, 10.1145/1807167.1807184]
  • [4] Apache Software Foundation, 2011, HAD SOFTW
  • [5] Avery C., 2011, P 2011 HAD SUMM SANT
  • [6] Bent John, 2004, P 1 USENIX S NETW SY
  • [7] BLUMOFE RD, 1995, SIGPLAN NOTICES, V30, P207
  • [8] BRYANT RE, 2007, CMUCS07128
  • [9] Bu YY, 2010, PROC VLDB ENDOW, V3, P285
  • [10] OpenMP: An industry standard API for shared-memory programming
    Dagum, L
    Menon, R
    [J]. IEEE COMPUTATIONAL SCIENCE & ENGINEERING, 1998, 5 (01): : 46 - 55
123