August 2019 - mpi-forum - mailman3.cels.anl.gov

Re: [Mpi-forum] Persistent WG to Read "MPI Partitioned Communication" Ticket #136 --- for Zurich Meeting
by Anthony Skjellum 22 Aug '19

22 Aug '19

Martin, I will ask Ryan Grant to prepare that. Tony On Thu, Aug 22, 2019 at 5:09 AM Martin Schulz via mpi-forum < mpi-forum(a)lists.mpi-forum.org> wrote: > Hi Tony, > > Do you have a pull request or document that shows the no/no changes you > are proposing? PR 117 shows only the entire ticket. > > Thanks, > > Martin > > > — > Prof. Dr. Martin Schulz, Chair of Computer Architecture and Parallel > Systems > Department of Informatics, TU-Munich, Boltzmannstraße 3, D-85748 Garching > Member of the Board of Directors at the Leibniz Supercomputing Centre (LRZ) > Email: schulzm(a)in.tum.de <schulzm(a)in.tum.de> > > > > > > > > > On 22. Aug 2019, at 02:03, Tony Skjellum via mpi-forum < > mpi-forum(a)lists.mpi-forum.org> wrote: > > Hi, I need to make a correction: actually we will do a no no vote on the > prior reading from Chicago . If successful, we will take a vote . If it > shouldn’t be for some reason, then a reading will be done immediately in > Zurich at same session. > > Thank you > Tony > > Anthony Skjellum, PhD > 205-807-4968 > > > On Aug 21, 2019, at 2:26 PM, Skjellum, Anthony via mpi-forum < > mpi-forum(a)lists.mpi-forum.org> wrote: > > Dear colleagues: This is the two-week announcement for the Zurich meeting > on Partition Communication, Ticket #136. > > Ticket #136: https://github.com/mpi-forum/mpi-issues/issues/136 > > > Pull request: mpi-forum/mpi-standard#117 > <https://github.com/mpi-forum/mpi-standard/pull/117> > > We will also have correlated PPT to share as backup and reading material > for those wishing to catch up before the meeting > or at the meeting before the reading. > > Thank you in advance for reviewing this Ticket for the Zurich meeting. > > This work is done in consultation with this PT2PT WG. > > Regards, > Tony Skjellum (on behalf of the Persistent WG) > > > Anthony Skjellum, PhD > Professor of Computer Science and Chair of Excellence > Director, SimCenter > University of Tennessee at Chattanooga (UTC) > tony-skjellum(a)utc.edu [or skjellum(a)gmail.com] > cell: 205-807-4968 > > > _______________________________________________ > mpi-forum mailing list > mpi-forum(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpi-forum > > _______________________________________________ > mpi-forum mailing list > mpi-forum(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpi-forum > > > _______________________________________________ > mpi-forum mailing list > mpi-forum(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpi-forum > -- Anthony Skjellum, PhD skjellum(a)gmail.com Cell: +1-205-807-4968

1 0

Re: [Mpi-forum] Sessions WG 2-week deadline announcement
by HOLMES Daniel 22 Aug '19

22 Aug '19

Hi all, The differences in the Sessions proposal since the last virtual meeting (which was 12th Jun 2019) are contained in the attached diff file. Cheers, Dan. — Dr Daniel Holmes PhD Architect (HPC Research) d.holmes(a)epcc.ed.ac.uk<mailto:[email protected]> Phone: +44 (0) 131 651 3465 Mobile: +44 (0) 7940 524 088 Address: Room 2.09, Bayes Centre, 47 Potterrow, Central Area, Edinburgh, EH8 9BT — The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. — On 22 Aug 2019, at 10:41, Martin Schulz <schulzm(a)in.tum.de<mailto:[email protected]>> wrote: Hi Dan, Do you have a pull request or document that shows the no/no changes you are proposing? PR 103 shows only the entire ticket. Thanks, Martin — Prof. Dr. Martin Schulz, Chair of Computer Architecture and Parallel Systems Department of Informatics, TU-Munich, Boltzmannstraße 3, D-85748 Garching Member of the Board of Directors at the Leibniz Supercomputing Centre (LRZ) Email: schulzm(a)in.tum.de<mailto:[email protected]> On 21. Aug 2019, at 21:27, HOLMES Daniel via mpi-forum <mpi-forum(a)lists.mpi-forum.org<mailto:[email protected]>> wrote: Hi all, The intention is to avoid reading the whole of the Sessions proposal again at the Zurich meeting. The Sessions WG is planning to hold a no-no-vote at the Zurich meeting regarding the changes made since the last face-to-face meeting. If that succeeds then we are hoping to move on to a 1st vote, also at the Zurich meeting. On the off chance that the no-no-vote is unsuccessful, please consider this email to be the formal announcement of a reading for the Sessions proposal. The issue is #103 and can be found here: https://github.com/mpi-forum/mpi-issues/issues/103 The PR is #55 and can be found here: https://github.com/mpi-forum/mpi-standard/pull/55 The PDF can be found here: https://github.com/mpi-forum/mpi-issues/files/3526944/mpi-report-ticket103-… Cheers, Dan. — Dr Daniel Holmes PhD Architect (HPC Research) d.holmes(a)epcc.ed.ac.uk<mailto:[email protected]> Phone: +44 (0) 131 651 3465 Mobile: +44 (0) 7940 524 088 Address: Room 2.09, Bayes Centre, 47 Potterrow, Central Area, Edinburgh, EH8 9BT — The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. — _______________________________________________ mpi-forum mailing list mpi-forum(a)lists.mpi-forum.org<mailto:[email protected]> https://lists.mpi-forum.org/mailman/listinfo/mpi-forum

1 0

Re: [Mpi-forum] Sessions WG 2-week deadline announcement
by Martin Schulz 22 Aug '19

22 Aug '19

Hi Dan, Do you have a pull request or document that shows the no/no changes you are proposing? PR 103 shows only the entire ticket. Thanks, Martin — Prof. Dr. Martin Schulz, Chair of Computer Architecture and Parallel Systems Department of Informatics, TU-Munich, Boltzmannstraße 3, D-85748 Garching Member of the Board of Directors at the Leibniz Supercomputing Centre (LRZ) Email: schulzm(a)in.tum.de > On 21. Aug 2019, at 21:27, HOLMES Daniel via mpi-forum <mpi-forum(a)lists.mpi-forum.org> wrote: > > Hi all, > > The intention is to avoid reading the whole of the Sessions proposal again at the Zurich meeting. The Sessions WG is planning to hold a no-no-vote at the Zurich meeting regarding the changes made since the last face-to-face meeting. If that succeeds then we are hoping to move on to a 1st vote, also at the Zurich meeting. > > On the off chance that the no-no-vote is unsuccessful, please consider this email to be the formal announcement of a reading for the Sessions proposal. > > The issue is #103 and can be found here: https://github.com/mpi-forum/mpi-issues/issues/103 <https://github.com/mpi-forum/mpi-issues/issues/103> > The PR is #55 and can be found here: https://github.com/mpi-forum/mpi-standard/pull/55 <https://github.com/mpi-forum/mpi-standard/pull/55> > The PDF can be found here: https://github.com/mpi-forum/mpi-issues/files/3526944/mpi-report-ticket103-… <https://github.com/mpi-forum/mpi-issues/files/3526944/mpi-report-ticket103-…> > > Cheers, > Dan. > — > Dr Daniel Holmes PhD > Architect (HPC Research) > d.holmes(a)epcc.ed.ac.uk <mailto:[email protected]> > Phone: +44 (0) 131 651 3465 > Mobile: +44 (0) 7940 524 088 > Address: Room 2.09, Bayes Centre, 47 Potterrow, Central Area, Edinburgh, EH8 9BT > — > The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. > — > > _______________________________________________ > mpi-forum mailing list > mpi-forum(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpi-forum

1 0

Re: [Mpi-forum] Persistent WG to Read "MPI Partitioned Communication" Ticket #136 --- for Zurich Meeting
by schulzm＠in.tum.de 22 Aug '19

22 Aug '19

Hi Tony, Do you have a pull request or document that shows the no/no changes you are proposing? PR 117 shows only the entire ticket. Thanks, Martin — Prof. Dr. Martin Schulz, Chair of Computer Architecture and Parallel Systems Department of Informatics, TU-Munich, Boltzmannstraße 3, D-85748 Garching Member of the Board of Directors at the Leibniz Supercomputing Centre (LRZ) Email: schulzm(a)in.tum.de > On 22. Aug 2019, at 02:03, Tony Skjellum via mpi-forum <mpi-forum(a)lists.mpi-forum.org> wrote: > > Hi, I need to make a correction: actually we will do a no no vote on the prior reading from Chicago . If successful, we will take a vote . If it shouldn’t be for some reason, then a reading will be done immediately in Zurich at same session. > > Thank you > Tony > > Anthony Skjellum, PhD > 205-807-4968 > > > On Aug 21, 2019, at 2:26 PM, Skjellum, Anthony via mpi-forum <mpi-forum(a)lists.mpi-forum.org <mailto:[email protected]>> wrote: > >> Dear colleagues: This is the two-week announcement for the Zurich meeting on Partition Communication, Ticket #136. >> >> Ticket #136: https://github.com/mpi-forum/mpi-issues/issues/136 <https://github.com/mpi-forum/mpi-issues/issues/136> >> >> >> Pull request: mpi-forum/mpi-standard#117 <https://github.com/mpi-forum/mpi-standard/pull/117> >> We will also have correlated PPT to share as backup and reading material for those wishing to catch up before the meeting >> or at the meeting before the reading. >> >> Thank you in advance for reviewing this Ticket for the Zurich meeting. >> >> This work is done in consultation with this PT2PT WG. >> >> Regards, >> Tony Skjellum (on behalf of the Persistent WG) >> >> >> Anthony Skjellum, PhD >> Professor of Computer Science and Chair of Excellence >> Director, SimCenter >> University of Tennessee at Chattanooga (UTC) >> tony-skjellum(a)utc.edu <mailto:[email protected]> [or skjellum(a)gmail.com <mailto:[email protected]>] >> cell: 205-807-4968 >> >> >> _______________________________________________ >> mpi-forum mailing list >> mpi-forum(a)lists.mpi-forum.org <mailto:[email protected]> >> https://lists.mpi-forum.org/mailman/listinfo/mpi-forum <https://lists.mpi-forum.org/mailman/listinfo/mpi-forum> > _______________________________________________ > mpi-forum mailing list > mpi-forum(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpi-forum

1 0

Zurich Reading Request: Memory Alignment and RMA ordering errata
by Joseph Schuchart 22 Aug '19

22 Aug '19

Dear all, I would like to request the reading of the following two proposals at the Zurich meeting: *Memory Alignment* Ticket #121: https://github.com/mpi-forum/mpi-issues/issues/121 PR: https://github.com/mpi-forum/mpi-standard/pull/96 PDF: https://github.com/mpi-forum/mpi-issues/files/3528813/mpi-report_issue-121_… *RMA Ordering Errata* The purpose of this errata is to clarify an ambiguity concerning the ordering of RMA accumulate operations with the target being the same as the origin. Ticket #144: https://github.com/mpi-forum/mpi-issues/issues/144 PR: https://github.com/mpi-forum/mpi-standard/pull/127 *Mandatory Info Keys* If time permits, I would also like to bring up a few slides on introducing info keys that are mandatory to recognize. There are a few ideas on how to introduce this third class of keys so I would like to get a discussion started. This topic came up in the context of the memory alignment ticket but the scope is likely not limited to that. Thanks, Joseph -- Dipl.-Inf. Joseph Schuchart High Performance Computing Center Stuttgart (HLRS) Nobelstr. 19 D-70569 Stuttgart Tel.: +49(0)711-68565890 Fax: +49(0)711-6856832 E-Mail: schuchart(a)hlrs.de

1 0

Tools WG Reading announcement
by Marc-André Hermanns 22 Aug '19

22 Aug '19

Dear all, as discussed during the last face-to-face and the virtual meeting, we would like to avoid reading the full proposal again at the Zurich meeting. The idea is to give a general overview of the API and then go through the changes since the last face-to-face. The ticket: https://github.com/mpi-forum/mpi-issues/issues/79 The pull request: https://github.com/mpi-forum/mpi-standard/pull/33 The PDF: https://github.com/mpi-forum/mpi-standard/files/3527343/mpi32-report.pdf Cheers, Marc-Andre -- Dr. rer. nat. Marc-André Hermanns IT Center Group: High Performance Computing Division: Computational Science and Engineering RWTH Aachen University Seffenter Weg 23 52074 Aachen Phone: +49 241 80-24381 hermanns(a)itc.rwth-aachen.de www.itc.rwth-aachen.de

1 0

Re: [Mpi-forum] Persistent WG to Read "MPI Partitioned Communication" Ticket #136 --- for Zurich Meeting
by Tony Skjellum 21 Aug '19

21 Aug '19

Hi, I need to make a correction: actually we will do a no no vote on the prior reading from Chicago . If successful, we will take a vote . If it shouldn’t be for some reason, then a reading will be done immediately in Zurich at same session. Thank you Tony Anthony Skjellum, PhD 205-807-4968 > On Aug 21, 2019, at 2:26 PM, Skjellum, Anthony via mpi-forum <mpi-forum(a)lists.mpi-forum.org> wrote: > > Dear colleagues: This is the two-week announcement for the Zurich meeting on Partition Communication, Ticket #136. > > Ticket #136: https://github.com/mpi-forum/mpi-issues/issues/136 > > > Pull request: mpi-forum/mpi-standard#117 > > > We will also have correlated PPT to share as backup and reading material for those wishing to catch up before the meeting > or at the meeting before the reading. > > Thank you in advance for reviewing this Ticket for the Zurich meeting. > > This work is done in consultation with this PT2PT WG. > > Regards, > Tony Skjellum (on behalf of the Persistent WG) > > > Anthony Skjellum, PhD > Professor of Computer Science and Chair of Excellence > Director, SimCenter > University of Tennessee at Chattanooga (UTC) > tony-skjellum(a)utc.edu [or skjellum(a)gmail.com] > cell: 205-807-4968 > > > _______________________________________________ > mpi-forum mailing list > mpi-forum(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpi-forum

1 0

FTWG Readings and Votes for September 2019 Meeting
by Wesley Bland 21 Aug '19

21 Aug '19

Hi all, The Fault Tolerance Working Group will be reading the following ticket at the September 2019 meeting: Create MPI_INFO_ENV before MPI_INIT Issue #143 <https://github.com/mpi-forum/mpi-issues/issues/143> Pull Request #126 <https://github.com/mpi-forum/mpi-standard/pull/126> Add a new API function for constructing an MPI_INFO_ENV object when one might not exist (or might be wrong). This is sort of in conjunction with the Tools and Sessions working groups. We will also hold a no-no and first vote on the following ticket: Add MPI_ERR_PROC_ABORTED Issue #134 <https://github.com/mpi-forum/mpi-issues/issues/134> Pull Request #112 <https://github.com/mpi-forum/mpi-standard/pull/112> Add the MPI_ERR_PROC_ABORTED error class. No-no text is here: https://github.com/mpi-forum/mpi-standard/pull/112/commits/4872280602dcac86… <https://github.com/mpi-forum/mpi-standard/pull/112/commits/4872280602dcac86…> Finally, we will have a second vote on these two issues: Clarify what MPI_SUCCESS guarantees, and what is left undefined when MPI_ERR_XXX happens Issue #119 <https://github.com/mpi-forum/mpi-issues/issues/119> Pull Request #95 <https://github.com/mpi-forum/mpi-standard/pull/95> The definition of MPI_SUCCESS is a terse "no error returned". When we operate under the assumption that some failure (process, resource, transport, otherwise) may happen, we need to clarify in which cases MPI_SUCCESS is possible, and what it guarantees. For example an implementation may mask errors that do not have a direct consequence on the call semantic. Conversely, we need to clarify what arguments and buffers are valid or undefined after a call has raised an error. Define error/failure behavior in MPI_INIT/FINALIZE Issue #102 <https://github.com/mpi-forum/mpi-issues/issues/102> Pull Request #50 <https://github.com/mpi-forum/mpi-standard/pull/50> Errors before or during MPI_INIT may kill the entire application, which makes initializing MPI a possibly risky proposition in a mixed-mode application. Thanks, Wesley

1 0

Re: [Mpi-forum] Semantic Terms WG Reading for Zurich MPI Forum Meeting
by Bo Fang 21 Aug '19

21 Aug '19

On Wed, Aug 21, 2019 at 1:44 PM Bangalore, Purushotham via mpi-forum < mpi-forum(a)lists.mpi-forum.org> wrote: > Hi All, > > The Semantic Terms WG would like to announce reading for update to > semantic terms section along with other appropriate changes elsewhere. > > Issue #96: https://github.com/mpi-forum/mpi-issues/issues/96 > PR #116: https://github.com/mpi-forum/mpi-standard/pull/116 > > > PDF: > https://github.com/mpi-forum/mpi-standard/files/3527193/mpi32-report.pdf > > > Thanks, > Puri > _______________________________________________ > mpi-forum mailing list > mpi-forum(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpi-forum >

1 0

Semantic Terms WG Reading for Zurich MPI Forum Meeting
by Bangalore, Purushotham 21 Aug '19

21 Aug '19

Hi All, The Semantic Terms WG would like to announce reading for update to semantic terms section along with other appropriate changes elsewhere. Issue #96: https://github.com/mpi-forum/mpi-issues/issues/96 PR #116: https://github.com/mpi-forum/mpi-standard/pull/116 PDF: https://github.com/mpi-forum/mpi-standard/files/3527193/mpi32-report.pdf Thanks, Puri

1 0