Search Mailing List Archives

Limit search to: Subject & Body Subject Author
Sort by: Reverse Sort
Limit to: All This Week Last Week This Month Last Month
Select Date Range     through    

[farmshare-discuss] MapReduce Workshop on campus 4/29 - 5/1

Alex Chekholko chekh at
Mon Apr 22 12:06:06 PDT 2013

The morning sessions, to be held in G19 Redwood, are standard 
seminar-type talks, open to everyone.  The afternoon sessions will be 
held at ICME and are intended for using MapReduce on your own data sets. 
  See the web site referenced below for the specifics of how to sign up 
for this opportunity.

Research Computing is happy to have a small hand in this upcoming workshop.


2nd ICME Workshop on MapReduce in Science and Engineering
Stanford University
April 29 - May 1

We would like to invite you to participate in the 2nd ICME MapReduce 
Workshop to be held April 29 - May 1 on Stanford's campus.

The goals of the workshop are as follows:
- Learn the basics of Hadoop/MapReduce.
- Use Hadoop/MapReduce to process large-scale data from science and 
engineering applications.
- Explore your own data in a collaborate, group setting on a Hadoop cluster.

Each day of the workshop will include a morning session and an afternoon 
session. The morning sessions will take place in Redwood Hall, room G19, 
and are open to the public. The schedule of speakers is as follows:

Monday, April 29:
9:30am -- Prof. David Gleich (Purdue computer science), Sparse matrix 
computations in MapReduce
10:30am -- Austin Benson (Stanford ICME), Tall and skinny matrix 
computations in MapReduce

Tuesday, April 30:
9:30am -- Joe Buck (UC Santa Cruz computer science), Extending MapReduce 
for scientific computing
10:30am -- Dr. Chunsheng (Victor) Fang (Pivotal Data Science Team), 
Large Scale Video Analytics Platform on Pivotal Hadoop

Wednesday, May 1:
9:30am -- Dr. Joe Nichols (Stanford mechanical engineering), 
Computational fluid dynamics applications in MapReduce
10:30am -- Dr. Lavanya Ramakrishnan (Lawrence Berkeley National Labs), 
Evaluating MapReduce and Hadoop for Science

In the afternoon, the project groups will work side-by-side writing 
MapReduce scripts to perform their specific analysis tasks on their own 
data set. Last year, the afternoon sessions also included a great deal 
of informal discussion on the advantages and limitations of MapReduce 
for scientific data sets.

To learn more and find out how you can participate, please visit our 

More information about the farmshare-discuss mailing list