Hi again Jordan
I can't comment on this error at this stage but I know that all tests normally pass so it must be something about your version of MPICH perhaps.
However, if the problem only arises with reduce, I'd ignore it for now unless, of course, you plan to rely on reduce. In my (and many other's) opinion the most efficient MPI programs use a very small subset of MPI (as in send and receive).
So I'd just get cracking with the parallel Python program :-)
When you have a chance, I have a question about tests that seem to be failing in pypar_tests.py.
Most of the tests run fine. When it gets to the section for testing reduce, all the assert statements return False. the reduce function seems to be encountering the error "Input array and buffer must be of the same type". According to python the arrays being passed in here have the same type. So I'm not sure what would be causing mpiext to interpret these as different types. Any ideas?
Otherwise things seem to be working and I'm looking forward to using pypar!