September 2018 - mpiwg-sessions - mailman3.cels.anl.gov

Re: [mpiwg-sessions] Next meeting - today - 1pm Eastern US time
by HOLMES Daniel 24 Sep '18

24 Sep '18

Hi Howard, In that case (unless there are strenuous objections from others on this email list), I will cancel the Sessions meeting today. I’d like to do the “what didn’t happen this meeting” conversation just once, and I have nothing new to add today. Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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 24 Sep 2018, at 16:08, Pritchard Jr., Howard <howardp(a)lanl.gov<mailto:[email protected]>> wrote: Hi Dan, Unfortunately I have a conflict this morning – OpenSHMEM specification committee ;) - so I will not be able to call in. I plan to spend some time this week experimenting with PMIx group test case and make sure it works on some of our testbed systems. Howard -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org<mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Date: Monday, September 24, 2018 at 3:53 AM To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Cc: HOLMES Daniel <d.holmes(a)epcc.ed.ac.uk<mailto:[email protected]>> Subject: [mpiwg-sessions] Next meeting - today - 1pm Eastern US time Hi all, The next meeting for the Sessions WG is today at 1pm Eastern US time. The connection details for the call can be found here: http://mpi-forum.epcc.ed.ac.uk/mpiwg-sessions.php The wiki for the working group, including documentation about Sessions and minutes of previous meetings is here: https://github.com/mpiwg-sessions/sessions-issues/wiki We have two current topics. 1) Changes for the main part of the core sessions proposal https://github.com/mpi-forum/mpi-issues/issues/103 https://github.com/mpi-forum/mpi-standard/pull/55 2) Implementation of Sessions a) As a library on top of MPI-3.1 using connect/accept https://github.com/hpc/mpi_sessions_code_sandbox<https://bitbucket.org/howard_pritchard/mpi_sessions_code_sandbox/commits/all> b) Directly on top of PMIx, using PMIx groups https://github.com/pmix/RFCs/pull/33/files https://pmix.org/pmix-standard/pmix-groups/ Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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. — The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.

1 0

Re: [mpiwg-sessions] Next meeting - today - 1pm Eastern US time
by Pritchard Jr., Howard 24 Sep '18

24 Sep '18

Hi Dan, Unfortunately I have a conflict this morning – OpenSHMEM specification committee ;) - so I will not be able to call in. I plan to spend some time this week experimenting with PMIx group test case and make sure it works on some of our testbed systems. Howard -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org<mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Date: Monday, September 24, 2018 at 3:53 AM To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Cc: HOLMES Daniel <d.holmes(a)epcc.ed.ac.uk<mailto:[email protected]>> Subject: [mpiwg-sessions] Next meeting - today - 1pm Eastern US time Hi all, The next meeting for the Sessions WG is today at 1pm Eastern US time. The connection details for the call can be found here: http://mpi-forum.epcc.ed.ac.uk/mpiwg-sessions.php The wiki for the working group, including documentation about Sessions and minutes of previous meetings is here: https://github.com/mpiwg-sessions/sessions-issues/wiki We have two current topics. 1) Changes for the main part of the core sessions proposal https://github.com/mpi-forum/mpi-issues/issues/103 https://github.com/mpi-forum/mpi-standard/pull/55 2) Implementation of Sessions a) As a library on top of MPI-3.1 using connect/accept https://github.com/hpc/mpi_sessions_code_sandbox<https://bitbucket.org/howard_pritchard/mpi_sessions_code_sandbox/commits/all> b) Directly on top of PMIx, using PMIx groups https://github.com/pmix/RFCs/pull/33/files https://pmix.org/pmix-standard/pmix-groups/ Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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. —

1 0

Next meeting - today - 1pm Eastern US time
by HOLMES Daniel 24 Sep '18

24 Sep '18

Hi all, The next meeting for the Sessions WG is today at 1pm Eastern US time. The connection details for the call can be found here: http://mpi-forum.epcc.ed.ac.uk/mpiwg-sessions.php The wiki for the working group, including documentation about Sessions and minutes of previous meetings is here: https://github.com/mpiwg-sessions/sessions-issues/wiki We have two current topics. 1) Changes for the main part of the core sessions proposal https://github.com/mpi-forum/mpi-issues/issues/103 https://github.com/mpi-forum/mpi-standard/pull/55 2) Implementation of Sessions a) As a library on top of MPI-3.1 using connect/accept https://github.com/hpc/mpi_sessions_code_sandbox<https://bitbucket.org/howard_pritchard/mpi_sessions_code_sandbox/commits/all> b) Directly on top of PMIx, using PMIx groups https://github.com/pmix/RFCs/pull/33/files https://pmix.org/pmix-standard/pmix-groups/ Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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. — The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.

1 0

Re: [mpiwg-sessions] Reading at Sept 2018 meeting of MPI Forum
by HOLMES Daniel 23 Sep '18

23 Sep '18

As long as no-one raises objections, which they won’t because … oh, wait :( I want to illicit those objections as soon as possible so that we can prepare counter-arguments or adjust our proposal and move this thing along as fast as possible. One hour is enough to get people usefully engaged but hopefully not long enough to get them unhelpfully enraged. Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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 23 Sep 2018, at 15:48, Wesley Bland via mpiwg-sessions <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> wrote: We’re going to get through sessions in an hour over WebEx? This should be fun. 😀 On Sep 21, 2018, at 4:33 PM, Pritchard Jr., Howard via mpiwg-sessions <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> wrote: Thanks Dan! -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org<mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Date: Friday, September 21, 2018 at 3:32 PM To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Cc: HOLMES Daniel <d.holmes(a)epcc.ed.ac.uk<mailto:[email protected]>> Subject: [mpiwg-sessions] Reading at Sept 2018 meeting of MPI Forum Hi all, Disappointingly, Sessions was not presented at this meeting of the MPI Forum because we ran out of time. A virtual meeting has been scheduled for 7th Nov 2018 to accommodate the presentation of the Sessions proposal. Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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. — _______________________________________________ mpiwg-sessions mailing list mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions _______________________________________________ mpiwg-sessions mailing list mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.

1 0

Re: [mpiwg-sessions] Reading at Sept 2018 meeting of MPI Forum
by Wesley Bland 23 Sep '18

23 Sep '18

We’re going to get through sessions in an hour over WebEx? This should be fun. 😀 > On Sep 21, 2018, at 4:33 PM, Pritchard Jr., Howard via mpiwg-sessions <mpiwg-sessions(a)lists.mpi-forum.org> wrote: > > Thanks Dan! > > -- > Howard Pritchard > B Schedule > HPC-ENV > Office 9, 2nd floor Research Park > TA-03, Building 4200, Room 203 > Los Alamos National Laboratory > > > From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org <mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]>> > Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]>> > Date: Friday, September 21, 2018 at 3:32 PM > To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]>> > Cc: HOLMES Daniel <d.holmes(a)epcc.ed.ac.uk <mailto:[email protected]>> > Subject: [mpiwg-sessions] Reading at Sept 2018 meeting of MPI Forum > >> Hi all, >> >> Disappointingly, Sessions was not presented at this meeting of the MPI Forum because we ran out of time. >> >> A virtual meeting has been scheduled for 7th Nov 2018 to accommodate the presentation of the Sessions proposal. >> >> Cheers, >> Dan. >> — >> Dr Daniel Holmes PhD >> Applications Consultant in 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. >> — >> > _______________________________________________ > mpiwg-sessions mailing list > mpiwg-sessions(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions

1 0

Re: [mpiwg-sessions] Reading at Sept 2018 meeting of MPI Forum
by Pritchard Jr., Howard 21 Sep '18

21 Sep '18

Thanks Dan! -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org<mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Date: Friday, September 21, 2018 at 3:32 PM To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Cc: HOLMES Daniel <d.holmes(a)epcc.ed.ac.uk<mailto:[email protected]>> Subject: [mpiwg-sessions] Reading at Sept 2018 meeting of MPI Forum Hi all, Disappointingly, Sessions was not presented at this meeting of the MPI Forum because we ran out of time. A virtual meeting has been scheduled for 7th Nov 2018 to accommodate the presentation of the Sessions proposal. Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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. —

1 0

Reading at Sept 2018 meeting of MPI Forum
by HOLMES Daniel 21 Sep '18

21 Sep '18

Hi all, Disappointingly, Sessions was not presented at this meeting of the MPI Forum because we ran out of time. A virtual meeting has been scheduled for 7th Nov 2018 to accommodate the presentation of the Sessions proposal. Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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. — The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.

1 0

Re: [mpiwg-sessions] MPICH/hydra happier with Dan's test cases (kind of)
by Ralph H Castain 19 Sep '18

19 Sep '18

Dan/Howard: can you provide me with a simple reproducer of the problem for OMPI? I may have a little time to track it down - have an idea of the source of the trouble from Dan’s offlist note. Ralph > On Sep 17, 2018, at 8:42 AM, HOLMES Daniel via mpiwg-sessions <mpiwg-sessions(a)lists.mpi-forum.org> wrote: > > Hi Howard, et al, > > Howard: thanks for checking this on MPICH. Looks like we need a cross-mpirun example code - we could work on that this week. > > All: *reminder* no telecon today - we’ll meet up during the MPI Forum in a couple of days. > > Cheers, > Dan. > — > Dr Daniel Holmes PhD > Applications Consultant in 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 17 Sep 2018, at 05:39, Pritchard Jr., >> Howard via mpiwg-sessions <mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]>> wrote: >> >> Hi Folks, >> >> I made some minor corrections to the two problem test cases and they now work >> with mpich. I opened a PR and assigned Dan as the reviewer. >> >> Howard >> >> -- >> Howard Pritchard >> B Schedule >> HPC-ENV >> Office 9, 2nd floor Research Park >> TA-03, Building 4200, Room 203 >> Los Alamos National Laboratory >> >> >> From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org <mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]>> >> Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]>> >> Date: Sunday, September 16, 2018 at 10:10 PM >> To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]>> >> Cc: Howard Pritchard <howardp(a)lanl.gov <mailto:[email protected]>> >> Subject: [mpiwg-sessions] MPICH/hydra happier with Dan's test cases (kind of) >> >>> HI Folks, >>> >>> MPICH/hydra is happy with libCFG_noMCW, even with all the sleeps >>> removed. I ran up to 36 ranks with hydra/mpich and didn’t see a problem. >>> >>> Its not so happy with the other tests, I think they are buggy. >>> >>> Here’s what I get for libCFG_noMCW_multiport >>> >>> hpp@sn-fey1:/usr/projects/hpctools/hpp/mpi_sessions_code_sandbox>mpiexec -n 8 ./libCFG_noMCW_multiport >>> process 1 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD >>> process 3 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD >>> process 4 (MPI_COMM_WORLD) calling from group thingy >>> rank 4 non-trivial use-case: target group size 4, localGroup size 1 >>> rank 4 opening port >>> process 5 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD >>> process 6 (MPI_COMM_WORLD) calling from group thingy >>> rank 6 non-trivial use-case: target group size 4, localGroup size 1 >>> rank 6 opening port >>> process 7 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD >>> process 0 (MPI_COMM_WORLD) calling from group thingy >>> rank 0 non-trivial use-case: target group size 4, localGroup size 1 >>> process 2 (MPI_COMM_WORLD) calling from group thingy >>> rank 2 non-trivial use-case: target group size 4, localGroup size 1 >>> rank 2 opening port >>> rank 2 opened port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#55566$ifname#128.165.227.181$ >>> rank 2 publishing port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#55566$ifname#128.165.227.181$ using name foobar10 round 1 >>> rank 4 opened port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#45508$ifname#128.165.227.181$ >>> rank 4 publishing port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#45508$ifname#128.165.227.181$ using name foobar10 round 2 >>> rank 6 opened port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#52388$ifname#128.165.227.181$ >>> rank 6 publishing port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#52388$ifname#128.165.227.181$ using name foobar10 round 3 >>> rank 2 published port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#55566$ifname#128.165.227.181$ using name foobar10 round 1 >>> rank 2 accepting on port tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#55566$ifname#128.165.227.181$ (localSize 1) >>> Fatal error in PMPI_Publish_name: Invalid service name (see MPI_Publish_name), error stack: >>> PMPI_Publish_name(134): MPI_Publish_name(service="foobar10 round 2", MPI_INFO_NULL, port="tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#45508$ifname#128.165.227.181$") failed >>> MPID_NS_Publish(67)...: Lookup failed for service name foobar10 round 2 >>> Fatal error in PMPI_Publish_name: Invalid service name (see MPI_Publish_name), error stack: >>> PMPI_Publish_name(134): MPI_Publish_name(service="foobar10 round 3", MPI_INFO_NULL, port="tag#0$description#sn-fey1.lanl.gov <http://sn-fey1.lanl.gov/>$port#52388$ifname#128.165.227.181$") failed >>> MPID_NS_Publish(67)...: Lookup failed for service name foobar10 round 3 >>> >>> >>> If I have a chance I”ll play with this test and see if I can get it to work. hmm.. maybe hydra doesn’t like the whitespace publish names. >>> >>> Howard >>> >>> >>> -- >>> Howard Pritchard >>> B Schedule >>> HPC-ENV >>> Office 9, 2nd floor Research Park >>> TA-03, Building 4200, Room 203 >>> Los Alamos National Laboratory >>> >> _______________________________________________ >> mpiwg-sessions mailing list >> mpiwg-sessions(a)lists.mpi-forum.org <mailto:[email protected]> >> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions > > The University of Edinburgh is a charitable body, registered in > Scotland, with registration number SC005336. > _______________________________________________ > mpiwg-sessions mailing list > mpiwg-sessions(a)lists.mpi-forum.org > https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions

1 0

Re: [mpiwg-sessions] MPICH/hydra happier with Dan's test cases (kind of)
by HOLMES Daniel 17 Sep '18

17 Sep '18

Hi Howard, et al, Howard: thanks for checking this on MPICH. Looks like we need a cross-mpirun example code - we could work on that this week. All: *reminder* no telecon today - we’ll meet up during the MPI Forum in a couple of days. Cheers, Dan. — Dr Daniel Holmes PhD Applications Consultant in 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 17 Sep 2018, at 05:39, Pritchard Jr., Howard via mpiwg-sessions <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> wrote: Hi Folks, I made some minor corrections to the two problem test cases and they now work with mpich. I opened a PR and assigned Dan as the reviewer. Howard -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org<mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Date: Sunday, September 16, 2018 at 10:10 PM To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Cc: Howard Pritchard <howardp(a)lanl.gov<mailto:[email protected]>> Subject: [mpiwg-sessions] MPICH/hydra happier with Dan's test cases (kind of) HI Folks, MPICH/hydra is happy with libCFG_noMCW, even with all the sleeps removed. I ran up to 36 ranks with hydra/mpich and didn’t see a problem. Its not so happy with the other tests, I think they are buggy. Here’s what I get for libCFG_noMCW_multiport hpp@sn-fey1:/usr/projects/hpctools/hpp/mpi_sessions_code_sandbox>mpiexec -n 8 ./libCFG_noMCW_multiport process 1 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 3 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 4 (MPI_COMM_WORLD) calling from group thingy rank 4 non-trivial use-case: target group size 4, localGroup size 1 rank 4 opening port process 5 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 6 (MPI_COMM_WORLD) calling from group thingy rank 6 non-trivial use-case: target group size 4, localGroup size 1 rank 6 opening port process 7 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 0 (MPI_COMM_WORLD) calling from group thingy rank 0 non-trivial use-case: target group size 4, localGroup size 1 process 2 (MPI_COMM_WORLD) calling from group thingy rank 2 non-trivial use-case: target group size 4, localGroup size 1 rank 2 opening port rank 2 opened port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#55566$ifname#128.165.227.181$ rank 2 publishing port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#55566$ifname#128.165.227.181$ using name foobar10 round 1 rank 4 opened port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#45508$ifname#128.165.227.181$ rank 4 publishing port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#45508$ifname#128.165.227.181$ using name foobar10 round 2 rank 6 opened port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#52388$ifname#128.165.227.181$ rank 6 publishing port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#52388$ifname#128.165.227.181$ using name foobar10 round 3 rank 2 published port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#55566$ifname#128.165.227.181$ using name foobar10 round 1 rank 2 accepting on port tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#55566$ifname#128.165.227.181$ (localSize 1) Fatal error in PMPI_Publish_name: Invalid service name (see MPI_Publish_name), error stack: PMPI_Publish_name(134): MPI_Publish_name(service="foobar10 round 2", MPI_INFO_NULL, port="tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#45508$ifname#128.165.227.181$") failed MPID_NS_Publish(67)...: Lookup failed for service name foobar10 round 2 Fatal error in PMPI_Publish_name: Invalid service name (see MPI_Publish_name), error stack: PMPI_Publish_name(134): MPI_Publish_name(service="foobar10 round 3", MPI_INFO_NULL, port="tag#0$description#sn-fey1.lanl.gov<http://sn-fey1.lanl.gov>$port#52388$ifname#128.165.227.181$") failed MPID_NS_Publish(67)...: Lookup failed for service name foobar10 round 3 If I have a chance I”ll play with this test and see if I can get it to work. hmm.. maybe hydra doesn’t like the whitespace publish names. Howard -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory _______________________________________________ mpiwg-sessions mailing list mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336.

1 0

Re: [mpiwg-sessions] MPICH/hydra happier with Dan's test cases (kind of)
by Pritchard Jr., Howard 16 Sep '18

16 Sep '18

Hi Folks, I made some minor corrections to the two problem test cases and they now work with mpich. I opened a PR and assigned Dan as the reviewer. Howard -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory From: mpiwg-sessions <mpiwg-sessions-bounces(a)lists.mpi-forum.org<mailto:[email protected]>> on behalf of MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Reply-To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Date: Sunday, September 16, 2018 at 10:10 PM To: MPI Sessions working group <mpiwg-sessions(a)lists.mpi-forum.org<mailto:[email protected]>> Cc: Howard Pritchard <howardp(a)lanl.gov<mailto:[email protected]>> Subject: [mpiwg-sessions] MPICH/hydra happier with Dan's test cases (kind of) HI Folks, MPICH/hydra is happy with libCFG_noMCW, even with all the sleeps removed. I ran up to 36 ranks with hydra/mpich and didn’t see a problem. Its not so happy with the other tests, I think they are buggy. Here’s what I get for libCFG_noMCW_multiport hpp@sn-fey1:/usr/projects/hpctools/hpp/mpi_sessions_code_sandbox>mpiexec -n 8 ./libCFG_noMCW_multiport process 1 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 3 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 4 (MPI_COMM_WORLD) calling from group thingy rank 4 non-trivial use-case: target group size 4, localGroup size 1 rank 4 opening port process 5 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 6 (MPI_COMM_WORLD) calling from group thingy rank 6 non-trivial use-case: target group size 4, localGroup size 1 rank 6 opening port process 7 (MPI_COMM_WORLD) now calling barrier on MPI_COMM_WORLD process 0 (MPI_COMM_WORLD) calling from group thingy rank 0 non-trivial use-case: target group size 4, localGroup size 1 process 2 (MPI_COMM_WORLD) calling from group thingy rank 2 non-trivial use-case: target group size 4, localGroup size 1 rank 2 opening port rank 2 opened port tag#0$description#sn-fey1.lanl.gov$port#55566$ifname#128.165.227.181$ rank 2 publishing port tag#0$description#sn-fey1.lanl.gov$port#55566$ifname#128.165.227.181$ using name foobar10 round 1 rank 4 opened port tag#0$description#sn-fey1.lanl.gov$port#45508$ifname#128.165.227.181$ rank 4 publishing port tag#0$description#sn-fey1.lanl.gov$port#45508$ifname#128.165.227.181$ using name foobar10 round 2 rank 6 opened port tag#0$description#sn-fey1.lanl.gov$port#52388$ifname#128.165.227.181$ rank 6 publishing port tag#0$description#sn-fey1.lanl.gov$port#52388$ifname#128.165.227.181$ using name foobar10 round 3 rank 2 published port tag#0$description#sn-fey1.lanl.gov$port#55566$ifname#128.165.227.181$ using name foobar10 round 1 rank 2 accepting on port tag#0$description#sn-fey1.lanl.gov$port#55566$ifname#128.165.227.181$ (localSize 1) Fatal error in PMPI_Publish_name: Invalid service name (see MPI_Publish_name), error stack: PMPI_Publish_name(134): MPI_Publish_name(service="foobar10 round 2", MPI_INFO_NULL, port="tag#0$description#sn-fey1.lanl.gov$port#45508$ifname#128.165.227.181$") failed MPID_NS_Publish(67)...: Lookup failed for service name foobar10 round 2 Fatal error in PMPI_Publish_name: Invalid service name (see MPI_Publish_name), error stack: PMPI_Publish_name(134): MPI_Publish_name(service="foobar10 round 3", MPI_INFO_NULL, port="tag#0$description#sn-fey1.lanl.gov$port#52388$ifname#128.165.227.181$") failed MPID_NS_Publish(67)...: Lookup failed for service name foobar10 round 3 If I have a chance I”ll play with this test and see if I can get it to work. hmm.. maybe hydra doesn’t like the whitespace publish names. Howard -- Howard Pritchard B Schedule HPC-ENV Office 9, 2nd floor Research Park TA-03, Building 4200, Room 203 Los Alamos National Laboratory

1 0