I'd suggest looking into TotalView (http://www.totalviewtech.com) and/or DDT
(http://www.allinea.com/). I've used TotalView pretty extensively and found
it to be pretty easy to use. They are both commercial, however, and not
cheap.
As far as I know, there isn't a whole lot of open source support
I'm trying to parallelize a Fortran code with rather complicated derived
types full of pointer arrays. When I build the MPI type for sending, all
the static components are sent, but the pointer arrays are not (and retain
initial values). I imagine this has to do with memory addresses when
creatin