[Mpi-forum] Reading request for FT and ErrH WG: remove_error_class and related functions

Hello all, The Fault Tolerance and Error Handling WG would like to bring for a reading text adding the procedures to remove user-defined error classes, codes, and strings. Issue: https://github.com/mpi-forum/mpi-issues/issues/283 PR: https://github.com/mpi-forum/mpi-standard/pull/166 This is a

Re: [Mpi-forum] Vote Request for Fault Tolerance and Error Handling WG (ulfm part1)

Correct, MPI 5 is the target Aurelien > On Nov 21, 2022, at 15:36, Wes Bland wrote: > > Just to be clear, this is being voted on for MPI 5.0, not MPI 4.1, right? > > Thanks, > Wes > >> On Nov 21, 2022, at 2:33 PM, Aurelien Bouteiller via mpi-forum >> wrote: >> >> Hello All, >> >> The Fa

[Mpi-forum] Announcement of Readings for December Meeting

Hi all, I would like to announce readings for the following issues:  title: "Rework Intro of External Interfaces Chapter / Possibly Rename" issue_number: 379 title: "Merge or Cross-Reference that Hints must be obeyed by Application in RMA and Info Chapters" is

[Mpi-forum] More Sessions related readings for upcoming MPI Fourm

Hi All, More Sessions (well actually the process management and creation chapter in general) related items for a first reading: Issue #514 Process management chapter changes for 4.1 - https://github.com/mpi-forum/mpi-issues/issues/514 PR #617 Topic/dynamic items deferred to 41 - https://github

[Mpi-forum] Vote Request for Fault Tolerance and Error Handling WG (ulfm part1)

Hello All, The Fault Tolerance and Error Handling WG would like to bring to a vote the first part of fine-grain fault tolerance: process failure error semantics and revoke (aka ulfm part 1). Issue: https://github.com/mpi-forum/mpi-issues/issues/581 PR: https://github.com/mpi-forum/mpi-standard

[Mpi-forum] Reading request for Session WG issue related to clarifying err handling fallback

Hello All, I’d like to put in a request to read the following pull request at the December ’22 MPI Forum: ## Clarification of errhandler fallback with Sessions Issue: https://github.com/mpi-forum/mpi-issues/issues/588 PR: https://github.com/mpi-forum/mpi-standard/pull/644 PR 644 was already r

[Mpi-forum] Reading requests: language interoperability concerns

On behalf of JeffH I'd like to request the first reading of the following issues/PRs addressing language interoperability issues at the December 2022 meeting: *add MPI_Status_{set,get} for 3 status fields* Issue: https://github.com/mpi-forum/mpi-issues/issues/645 PR: https://github.com/mpi-foru

Re: [Mpi-forum] RMA WG reading/vote announcements for December 2022 meeting

I'd like to push three more items to the heap of first reading requests for the RMA chapter: *RMA communication procedures should have local semantics* Issue: https://github.com/mpi-forum/mpi-issues/issues/653 PR: https://github.com/mpi-forum/mpi-standard/pull/769 This change depends on the larg

[Mpi-forum] Announcment reading/vote for issues improving the topology chapter

Hello all, For the upcoming December ‘22 MPI forum, I’d like to reserve a view minutes for presenting updates to the topology chapter. One suggested change is updating the chapter title - which the forum likely wants to have a (short) discussion and - reading/vote on #644 "Update "Process Topol

[Mpi-forum] Readings announcements for the December meeting of the MPI Forum

Dear all, I'd like to make the following readings on behalf of the Topologies working Group: 1- Allow pset names to guide splitting in MPI_Comm_split_type Issue: https://github.com/mpi-forum/mpi-issues/issues/538 PR: https://github.com/mpi-forum/mpi-standard/pull/761 2- New functions to query

Re: [Mpi-forum] RMA WG reading/vote announcements for December 2022 meeting

Yes, if the Forum agrees that it's an errata then we can vote on it right away. Thanks Joseph On 11/21/22 09:21, Wes Bland wrote: #634 is marked as errata. Should I schedule this for a vote as well? Thanks, Wes On Nov 18, 2022, at 5:14 PM, Joseph Schuchart via mpi-forum wrote: Dear all,

Re: [Mpi-forum] why is MPI_Status not opaque?

Yes, but every time the MPI Forum breaks backwards compatibility, an angel loses its wings, so we can’t fix design flaws like this. Everyone must suffer forever. More seriously, Lisandro pointer out that we’d need allocate and deallocate functions for status if they were handles to hidden stat

[Mpi-forum] Announcment reading/vote on #589

Hello all, For the upcoming December ‘22 MPI forum, I’d like to announce a * reading/vote on errata/issue #589 "Fixes for partitioned communication example 4.4" issue: https://github.com/mpi-forum/mpi-issues/issues/589 PR: https://github.com/mpi-forum/mpi-standard/pull/726 Best, Christoph N

[Mpi-forum] Announcements for Dec'22 MPI Forum meeting

Hi all, I'd like to request time at the Dec'22 meeting for the following issues/PRs: Reading: Enabled is a semantic term Issue 421: https://github.com/mpi-forum/mpi-issues/issues/421 PR 760: https://github.com/mpi-forum/mpi-standard/pull/760 Reading: Unsafe example relies on MPI providing buffer

Re: [Mpi-forum] why is MPI_Status not opaque?

It should be an opaque object :-) Anthony Skjellum, PhD 205-807-4968 On Nov 21, 2022, at 7:29 AM, Jeff Hammond via mpi-forum wrote:  I assume that MPI_Status is not opaque because somebody asserted that function call overhead was too much for some use cases. Was there more to it than this?

[Mpi-forum] why is MPI_Status not opaque?

I assume that MPI_Status is not opaque because somebody asserted that function call overhead was too much for some use cases. Was there more to it than this? Why does the standard say there is an opaque part for elements and cancelled, but not make those visible? The lack of consistency here doe