On Nov 11, 2009, at 1:29 PM, Samuel Thibault wrote:
> How about HWLOC_UNSUPPORTED_SYS?
I don't think it's a good idea to make it a compile-time thing rather
than a runtime-time thing: if we expose to the application the fact
that the OS on which the application is building is not supported, it
may disable some parts of its internals, even if later a newer version
hwloc that does support the system gets installed, and then the user
would have to recompile its application in order to get the
application
support compiled.
I have no strong feelings about that one; dynamically updating .so's
behind the scenes is both a curse and a blessing.
My only objection was to having a name that was not prefixed by HWLOC_*.
--
Jeff Squyres
jsquy...@cisco.com
