Hi, 

I want to design an application program (C++) that can distribute computing 
tasks on a cluster with MPI installed. 

I would like to use boost.MPI to do the data communication and Rhapsodia.Scheduler
to do the task scheduling. 

For example, I need to solve a big problem, which can be divided into 
multiple small tasks. 

These small tasks can be done independently on different nodes. So, 
when they are done, they return their results to one node, which combine 
their results into a solution for the big problem. 

Right now, the big problem has been programmed with C++. It is a 
sequential algorithm. 

I need to design a task/job scheduler that can do the above scheduling 
on cluster system so that the small tasks can be run in parallel. 

In this way, we can improve the performance of the sequential 
algorithm. 

Does my idea make sense ? 

Any help is appreciated. 


thanks 


Jack 

May 29  2010 


Hotmail is redefining busy with tools for the New Busy. Get more from your inbox. See how.