240A Winter 2016 HW2

240A Winter 2016 HW2

Due on March 1, 2016 before class.

Setup: For Part II, you can start a local Spark implementation at CSIL using a fake Python RDD.

$ cp -r ~cs240a/hw2/pagerank-start your-directory 

For Comet, copy the startup files into your diretory:

$ cp -r /home/tyang/cs240sample/log your-directory 
$ cp -r /home/tyang/cs240sample/pagerank-start your-directory 

Part I: Parallel web traffic analysis with Mapreduce

Part II: Parallel PageRank with Spark

Part III: GPU and SPMD programming

How to submit

Write a report with your group members. Submit a hardcopy of your answers along with the changed code for Part I and Part II.

Turn in the source code/report directory without compiled binary files using turnin program from a CSIL account (turnin HW2@cs240a directory-name).