[CSC 435] MPI Issues

[Andrew J. Pounds]

Guys -- MPI is running inconsistently across the cluster right now (it 
works on some systems, but then fails on others).   That is a nightmare 
scenario for you and I doubt I will have this all sorted out by 
classtime tomorrow.  I'm also toying with the idea of just building the 
newest version of MPI from scratch so it will work with our updated 
compilers.

Anyway -- there will not be a new assignment tomorrow and fixing the 
problem will require me to take the systems up and down periodically 
throughout the day.  For that reason we will not have class tomorrow.   
However, I will be building a presentation for you that describes how 
the matrix multiplication MPI programs run and another presentation on 
how my big MPI application works.   You can take tomorrow off and just 
watch the videos and answer the questions I pose later.

It looks like several of you need to still knock out the OpenBLAS 
assignment -- so focus on that first.


-- 
*/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/20220331/abd8b44d/attachment.html>