Date of Award
11-21-2014
Document Type
Thesis
Degree Name
Computer Science, MS
First Advisor
Hai Jiang
Committee Members
Hung-Chi Su; Jeff Jenness; XiuZhen Huang
Call Number
LD 251 .A566t 2014 Q46
Abstract
The MapReduce programming model has been criticized for a long time for its lack of flexibility to apply on many difficult scientific computations. Currently, several approaches try to conduct a more flexible MapReduce framework, but some of them are required to run on a particular platform, others have a lack of support to GPU environments. In this thesis, we present MR-Tree, a customizable GPU MapReduce framework. In MR-Tree, users can configure each task's data I/O behavior, so computations that have strong data dependency will no longer hold back the MapReduce runtime. Moreover, MR-Tree also features configurable workflow. Users can arrange the task nodes in several different ways to handle complicated MapReduce jobs. We will discuss the customization for MR-Tree to handle intricate, iterative, long-running and regular MapReduce applications.
Rights Management
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Qiao, Zhi, "Mr-Tree: A Customizable GPU Mapreduce Framework" (2014). Student Theses and Dissertations. 747.
https://arch.astate.edu/all-etd/747