From: Yukiya Aoyama <aoyama@XXXXXXXX>
Date: January 29, 2008 7:49:39 PM CST
To: mpi-comments@XXXXXXXXXXXXX
Subject: Re: Fwd: [mpi-21] Ballot 4 - Re: Re: SEND COUNT and RECEIVE COUNT

Thanks for the information.

In page 112, lines 37-40, it is true that it clearly states.
But compared with the following three, MPI_ALLTOALLV is only different from others, and (I think) a little ambiguous. 

(page 97) MPI_GATHERV   recvcounts
integer array (of length group size) containing the number of elements that are received from each process(significant only at root)

(page 110) MPI_ALLGATHERV   recvcounts
integer array (of length group size) containing the number of elements that are received from each process

(page 112) MPI_ALLTOALLV   recvcounts
integer array equal to the group size specifying the number of elments that can be received from each processor
                                                                                                   

At 09:22 08/01/29 -0600, you wrote:
Here's a response to a note that you sent to the MPI Forum at the end of 2006.  If you have any comments, please send them to mpi-comments@mpi-forum.org .

Bill

Begin forwarded message:

From: "Rolf Rabenseifner" <rabenseifner@XXXXXXX>
Date: January 28, 2008 8:44:19 AM CST
To: mpi-21@XXXXXXXXXXX
Subject: [mpi-21] Ballot 4 - Re: Re: SEND COUNT and RECEIVE COUNT
Reply-To: "Mailing list for discussion of MPI 2.1" <mpi-21@XXXXXXXXXXX>
Bill, 
please can you forward this to Yukiya Aoyama <aoyama@XXX>,the originator of this track.
Thanks, Rolf
___________________________________
This is a proposal for MPI 2.1, Ballot 4.

This is a follow up to:
  Description of the send and receive count arguments to MPI_Alltoallv 
  in http://www.cs.uiuc.edu/homes/wgropp/projects/parallel/MPI/mpi-errata/index.html
with mail discussion in
  http://www.cs.uiuc.edu/homes/wgropp/projects/parallel/MPI/mpi-errata/discuss/alltoallv/

Based on the questions for clarification, I propose not to include
any further clarification into the standard.

Reason:
MPI-1, Sect. 4.8, MPI_ALLTOALLV, page 112, lines 37-40 clearly states:

  "The type signature associated with sendcount[j], sendtype at 
  process i must be equal to the type signature associated with 
  recvcount[i], recvtype at process j. This implies that the amount 
  of data sent must be equal to the amount of data received, pairwise 
  between every pair of processes. Distinct type maps between sender 
  and receiver are still allowed."

The same text is also used for 
MPI-2.0, Sect. 7.3.5 MPI_ALLTOALLW, page 165, lines 42-45.

Okay?

Best regards
Rolf


Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner@XXXXXXX
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: Allmandring 30)
_______________________________________________
mpi-21 mailing list
mpi-21@XXXXXXXXXXX
http://lists.cs.uiuc.edu/mailman/listinfo/mpi-21

William Gropp
Paul and Cynthia Saylor Professor of Computer Science
University of Illinois Urbana-Champaign

**********************************(  R—q\0x^_N (Yukiya Aoyama) (  tSf[xvz@b0Å`1XúWäv»0ó0¿0ü0(  û–P[á0ü0ë0ÿaoyama@XXXXXXXXX  OO@bÿ0351-0198 üW‰swŒTIQ^ƒ^¢l2-1(  û–qŠÿ(YÚ})048-467-4982  (…QÚ})3822(  FAX ÿ048-462-4634( **********************************