[Mpi-forum] Announcing second vote for issue #137 - The Embiggenment ("BigCount")

Bangalore, Purushotham puri at uab.edu
Mon Sep 14 12:03:38 CDT 2020

Hi All,

Here are the details related to this announcement:

Issue: https://github.com/mpi-forum/mpi-issues/issues/137
PR: https://github.com/mpi-forum/mpi-standard/pull/268
PDF: mpi40-report-ticket137-cfed9a5-14Sep2020.pdf<https://github.com/mpi-forum/mpi-issues/files/5219835/mpi40-report-ticket137-cfed9a5-14Sep2020.pdf>
Highlighted PDF that shows the changes since first vote: mpi40-report-ticket137-cfed9a5-14Sep2020-highlighted.pdf<https://github.com/mpi-forum/mpi-issues/files/5219837/mpi40-report-ticket137-cfed9a5-14Sep2020-highlighted.pdf>

We would like to propose a no-no-vote on the changes made since the first vote. There was some concern that there are a lot of changes based on the number of files changes in the PR. I wanted to emphasize that we had to create a new pull request to address the merge conflicts that were created after several new chapters and sections were merged. As a result, the new PR includes several changes that were already made in the original PR. The actual differences between the two versions are not that many and most of these changes are editorial. I have listed the explicit changes made since the first vote below (these changes are also highlighted in the PDF file above):

0. the change bar latex macros have been removed

1. change all new function extensions from _l to _c and the text " - an underscore followed by a lower-case L " has been removed, where used

2. addition of the following sentence in Section 2.5.8:
"Even though the \type{MPI\_Count} type is large enough to encode address locations, \type{MPI\_Count} type shall not be used to represent an \mpitermni{absolute address}\mpitermindex{addresses!absolute}."

3. delete the following sentence that was repeated:
"The support for large count and displacement in Fortran is available when using newer \MPI/ Fortran bindings \code{(USE mpi_f08)}."



6. addition of separate MPI_Op_create_c and MPI_Register_datarep_c functions for F08 bindings

7. following text changes in Section 18.2:

(a) replace "The following were used prior to MPI-4.0:" with
"The following types, which were used prior to MPI-4.0, have been deemed too small to hold values that applications wish to use:" and remove the sentence "These types have been deemed too small to hold values that applications wish to use." in the next paragraph

(b) addition of "(e.g., in constructors of MPI datatypes that can be used with files)" to the end of third bullet

(c) addition of the following new text:
For the large count versions of three datatype constructors, MPI_TYPE_CREATE_HINDEXED, MPI_TYPE_CREATE_HINDEXED_BLOCK, and MPI_TYPE_CREATE_STRUCT, absolute addresses shall not be used to specify byte displacements since the parameter is of type MPI_COUNT instead of type MPI_AINT (see Section 2.5.8).

(d) addition of "MPI_Offset for parameters that represent byte displacement in files, " in the C bindings description

(e) addition of "INTEGER(KIND=MPI_OFFSET_KIND) for parameters that represent byte displacement in files, " in the Fortran bindings description

Puri on behalf of the large counts WG

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpi-forum.org/pipermail/mpi-forum/attachments/20200914/8fdd015b/attachment.html>

More information about the mpi-forum mailing list