I just talked to Jeff about this. The problem was that on Sif we use
--enable-visibility, and apparently the new c++ bindings access
ompi_errhandler_create, which was not OMPI_DECLSPEC'd. Jeff will fix
Jeff Squyres wrote:
> I'm a little concerned about the C++ test build failures from last
> They are likely due to the C++ changes that came in over the weekend,
> but they *only* showed up at IU, which is somewhat odd. I'm trying to
> replicate now (doing a fresh build of the trunk and will build the
> tests that failed for you), but I'm kinda guessing it's going to work
> fine on my platforms.
> IU: do you have any idea what caused these failures? Does sif have a
> newer compiler that is somehow picking up on a latent bug that we
> missed in the C++ stuff?