On Jul 31, 2019, at 5:44 PM, Jan Bierbaum <jan.bierb...@os.inf.tu-dresden.de> 
> Thanks a lot. This completely fixed those build problems. I used 'git
> clean -df' (without x) before and could have sworn I also tried a fresh
> clone … well, obviously I hadn't.

Ah ha!  Ok, good.  Because I was seriously stumped there.  Not all components 
(i.e., repo dirs) are present in all branches.  So if you had built one branch, 
and then "git clean -df" and then built another branch, it is quite possible 
that chaos/hilarity ensued...

> Any suggestions for my question about a test suite for (Open)MPI that
> also covers correct communication? It would be great to have some way to
> check my setup “layer by layer”.

Ah, sorry missed that question at the bottom of your prior email.

We don't really have any test suites that just test, for example, the BTLs.  We 
usually rely on the usual MPI benchmarks and test suites (e.g., the Intel MPI 
benchmarks have a correctness-checking mode).  We have a pile of internal 
tests/suites that we use, but they're not publicly available because many of 
them are modified versions of public test suites, and we never bothered to 
check into redistribution rights.  :-(

Jeff Squyres

devel mailing list

Reply via email to