Re: MPI-2.1 corrections, Batch 2 / AlltoallW

["Richard Treumann" <treumann@us.ibm.com>]

I like the name Rolf suggests.  MPI_Alltoallx could stand for MPI_Alltoall
(eXtended).

I assume MPI_Alltoall-> MPI_Alltoallv in MPI-1 was to suggest the addition
of vectors of displacements.

I never knew what the choice of "w" in going from Alltoallv -> Alltoallw
was about.  Did the "w" stand for something?  If we use Alltoallx and
someday decide that is deficient we can do Alltoally and Alltoallz  (;>).

MPI_Alltoallve (Alltoall vector enhanced) or MPI_Alltoallvx (Alltoall
vector extended) are a couple more options that would even be mnemonic.

         Dick

Dick Treumann                RS/6000 SP Development
IBM Poughkeepsie Unix Development Lab
Dept 0lva / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601
Tele (845) 433-7846         Fax (845) 433-8363

----- Forwarded by Richard Treumann/Poughkeepsie/IBM on 07/20/2001 09:26 AM
-----
                                                                                                                            
                    Rolf Rabenseifner                                                                                       
                    <Rabenseifner@RUS.Uni-Stu       To:     mpi-21@mpi-forum.org                                            
                    ttgart.DE>                      cc:                                                                     
                    Sent by:                        Subject:     Re: MPI-2.1 corrections, Batch 2 / AlltoallW               
                    owner-mpi-21@mpi-forum.or                                                                               
                    g                                                                                                       
                                                                                                                            
                                                                                                                            
                    07/20/2001 08:48 AM                                                                                     
                    Please respond to mpi-21                                                                                
                                                                                                                            
                                                                                                                            



I started the discussion in Nov. 2000 and now, after reading all the
arguments, I would also prefer to define a new function,
e.g., MPI_Alltoallx, with MPI_Aint for the displacement arguments.

And MPI_Alltoallw can go to the deprecated function list.

Rolf


Dr. Rolf Rabenseifner                      High Performance Computing
Parallel Computing                         Center Stuttgart    (HLRS)
Rechenzentrum Universitaet Stuttgart (RUS) Phone:    ++49 711 6855530
Allmandring 30                             FAX:      ++49 711 6787626
D-70550 Stuttgart                   rabenseifner@rus.uni-stuttgart.de
Germany                        http://www.hlrs.de/people/rabenseifner