[CSC 435] MPI Issues and Class on Monday

[Andrew J. Pounds]

So I have several versions of the MPI (Message Passing Interface) 
running on hammer and the systems in Godsey.  The problem is that I have 
got to compile a newer version on these systems but not destroy the 
backward capatibility that is needed by my research codes.  I discovered 
the incompatibilities when I was prepping your assignments for Monday.  
I was hoping to start MPI on Monday, but that is not going to happen.

I have another assignment for you to complete on Monday that you can do 
from anywhere.  It includes a video for you to watch and then you have 
to run a bunch of code on hammer.   It should also provide you with some 
examples of how to start building parallel speedup plots for your BabyBLAS.

So, there is no class scheduled for Monday -- work on the code at your 
own leasure from the comfort of your own home/office.  The assignment is 
due on Wednesday night.

With any luck, I will have a "development version" of MPI ready for us 
to use on Wednesday.  I will send out an e-mail once it is ready.

-- 
*Andrew J. Pounds, Ph.D.*
/Professor of Chemistry and Computer Science/
/Director of the Computational Science Program/
/Mercer University, Macon, GA, 31207 (478) 301-5627 /
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://theochem.mercer.edu/pipermail/csc435/attachments/20240322/6219afd2/attachment.html>