> - changed MPI_COMM_GET_PARENT to return MPI_COMM_NULL if parent
> has been freed or disconnected. Changed advice to users to reflect
> this.
>
It seems to me that MPI_COMM_FREE on the communicator returned by
MPI_COMM_GET_PARENT is about as reasonable as MPI_REQUEST_FREE on a
receive request. MPI-1 does not call it erroneous but does point out
that no reasonable program will do this.
Is there a circumstance where an MPI spawn group could SAFELY follow a
return from MPI_Comm_free on this communicator with a call to
MPI_Abort(MPI_COMM_WORLD) or a segfault? I am refering to SAFE for the
parent.
If not, I would suggest either pointing this out in the new advice or
even declaring MPI_COMM_FREE on this communicator an error.
Dick
-- Dick Treumann IBM RS/6000 Division (Internet) treumann@pok.ibm.com Poughkeepsie, NY (VNET) TREUMANN at KGNVMC Tel: (914) 433-7846 (internal) treumann@windsurf.pok.ibm.com Fax: (914) 433-8363