[Mpi-forum] Discussion points from the MPI-<next> discussion today
jedbrown at mcs.anl.gov
Sun Sep 23 10:06:32 CDT 2012
On Sun, Sep 23, 2012 at 9:45 AM, N.M. Maclaren <nmm1 at cam.ac.uk> wrote:
> That can be done only if you impose some OTHER constraints on the use
> of the buffers, which MPI currently does not do. I know how to do it,
> in both Fortran and C99, but I doubt that you do. The issues for
> MPI_Ireduce and MPI_Irecv_reduce are far subtler, and I am not even
> going to try explaining them until you understand the simpler one.
MPI imposes that the user is forbidden from accessing the buffer until the
request has completed. The MPI implementation provides the memory barrier
before returning to the user. Please explain why this is not sufficient?
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the mpi-forum