[Mpi-forum] Discussion and reading of #120 at Albuquerque MPI forum meeting Dec. 2019

[Rolf Rabenseifner]

Dear all,

thanks to you all for your many feedback that we received for this proposal,
especially during the meeting in Zurich and from the hw-topology WG.

Especially, the definition of MPI_Cart/Dims_create_weighted 
is now completely independent from special use cases, like 
halo communication, see pages 314 and 318.
Such halo communication is now only an example, see Exa.7.4 on page 320.

Based on that, I updated the issue #120

   MPI_Cart_weighted_create / Topology aware Cartesian communicators 

   https://github.com/mpi-forum/mpi-issues/issues/120

for reading at December Meeting 2019 in Albquerque.

I expect that this text now fits to the wishes that were expressed
in the previous MPI Forum meetings, latest in Zurich.

For a full pdf of the proposal with changebars, see

   https://github.com/mpi-forum/mpi-issues/files/3876045/mpi32-report-topol-2019-11-07-annotated-corr-11-21.pdf

The pull request is at
   https://github.com/mpi-forum/mpi-standard/pull/98

A portable and complete implementation together with documentation
can be found on the issue and also on our EuroMPI 2018 directory: 

   https://fs.hlrs.de/projects/par/mpi/EuroMPI2018-Cartesian/

Because I'm on travel next two weeks with very limited email-access,
I send out this email very early and a bit uncoordinated - my apologies.

Best regards
Rolf


-- 
Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner at hlrs.de .
High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530 .
University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832 .
Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner .
Nobelstr. 19, D-70550 Stuttgart, Germany . . . . (Office: Room 1.307) .