[mpich-discuss] mpi/errhan/defmsg.h
Jeff Hammond
jeff.science at gmail.com
Thu Sep 30 01:11:13 CDT 2010
Yes, Dries, that's exactly how I solved the problem. I was familiar
with MPI_IN_PLACE already but just didn't catch the double in=out
usage in my library because it goes through a few layers before
hitting MPI.
Jeff
On Thu, Sep 30, 2010 at 1:06 AM, Dries Kimpe <dkimpe at mcs.anl.gov> wrote:
>
> * Jeff Hammond <jhammond at mcs.anl.gov> [2010-09-29 23:47:35]:
>
>> You are correct. I switched from DCMF to MPI collectives and
>> apparently only the latter cares about in-place. See A1 commit 605
>> for details.
>
> There is always MPI_IN_PLACE ...
>
> http://www.mpi-forum.org/docs/mpi-20-html/node145.htm
>
> Dries
>
> _______________________________________________
> mpich-discuss mailing list
> mpich-discuss at mcs.anl.gov
> https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss
>
>
--
Jeff Hammond
Argonne Leadership Computing Facility
jhammond at alcf.anl.gov / (630) 252-5381
http://www.linkedin.com/in/jeffhammond
More information about the mpich-discuss
mailing list