Intel® Processors, Tools, and Utilities
13850 Discussions

MPI, divide the work and void deadlocks


Hello everyone,
I've bin struggeling for a while with MPI and i am not able to Parallelize GameOfLife in c++ using MPI . i dont really understand how should i divide the work for each Process , and how will every Process do its own work i think i've reached a close End here .

foe example if i have 2D-Array and i want to do some operations on it , so i send from the root block for each process a part of that work
then i recieve  from each process in a block of the other processes the work for each of them
for me its clear untill now ,
but when i recieve those parts and start the iterating should i iterate through the subarrays or through the whole original 2D-Array and every process will just know its  limits and do only its own part ?
and when its done , should i create a new block for the root to recieve the finished work or should i send it to the first Block of root process ?
i attached screenshot from the Code , if that could help
thank you very much

0 Kudos
1 Reply

Hello Mo9324,  


Thank you for posting on the Intel® communities.   


I would like to let you know that we have a specific forum for this kind of issue and product, it is called the Intel Developer Zone. There you will receive the appropriate support on this and other concerns you may have related to this product. 


Here you will find the links to access the website and the community forums: 




 Please keep in mind that this thread will no longer be monitored by Intel.  



Deivid A.  

Intel Customer Support Technician  

0 Kudos