The Data Mining Forum 
IMPORTANT: This is the old Data Mining forum.
I keep it online so that you can read the old messages.
Please post your new messages in the new forum: https://forum2.philippe-fournier-viger.com/index.php
How to write multicore / multi-threads data mining algorithms in Java: K-means
Posted by:
Clark
Date: September 05, 2011 04:38AM
Hi,
I found a good article about how to write algorithms in Java to take advantage of the power of multicore processors.
http://www.javaworld.com/javaworld/jw-11-2006/jw-1121-thread.html
The article is easy to read and an example is provided with the KMeans clustering algorithm.
A sequential version of K-Means is first presented and then the authors explain how to write a parallel version by using Java concurrency API.
Also a good book that I recommend for any Java programmers interested in concurrency is:
Java Concurrency in Practice
Some PDF versions ot the book can be found easily by searching on Google.
Clark
I found a good article about how to write algorithms in Java to take advantage of the power of multicore processors.
http://www.javaworld.com/javaworld/jw-11-2006/jw-1121-thread.html
The article is easy to read and an example is provided with the KMeans clustering algorithm.
A sequential version of K-Means is first presented and then the authors explain how to write a parallel version by using Java concurrency API.
Also a good book that I recommend for any Java programmers interested in concurrency is:
Java Concurrency in Practice
Some PDF versions ot the book can be found easily by searching on Google.
Clark