June 2009 - mpiwg-ft - mailman3.cels.anl.gov

Re: [Mpi3-ft] Topics for next telecon
by Greg Bronevetsky 17 Jun '09

17 Jun '09

We're planning on one. Greg Bronevetsky Post-Doctoral Researcher Lawrence Livermore National Lab (925) 424-5756 bronevetsky(a)llnl.gov http://greg.bronevetsky.com At 06:30 AM 6/17/2009, Josh Hursey wrote: >Is there a teleconf today or did you all decide to push until next >week due to the Forum meeting last week? > >-- Josh > >On Jun 14, 2009, at 8:19 PM, Graham, Richard L. wrote: > >>All the information is on the web, under the mpi-3 ft working group. >>If you need a URL, I can send it to you later - don't have access now. >> >>Rich >> >> >>From: mpi3-ft-bounces(a)lists.mpi-forum.org >>To: MPI 3.0 Fault Tolerance and Dynamic Process Control working Group >>Sent: Sun Jun 14 20:11:04 2009 >>Subject: Re: [Mpi3-ft] Topics for next telecon >> >>Hi, What is the telecon schedule and how does one get invited? >>Thanks, >>Tony >> >> >>On Wed, Jun 10, 2009 at 11:54 PM, Martin Schulz <schulzm(a)llnl.gov> >>wrote: >>Hi all, >> >> >>At 06:00 PM 6/10/2009, Greg Bronevetsky wrote: >>For the next telecon I propose that we address the following topics. >>- The piggybacking proposal was considered by the FT group several >>months ago but then got lost in a limbo between the FT group and the >>tools group. We need to discuss this proposal and the issues behind >>it so that we can figure out how to make progress on it. >> >>I agree with Greg - it would be great if we could pick this up >>again and try to come up with a single, common proposal. There is >>interest in this from multiple WGs (which is probably part of >>the problem of why nobody has pushed this forward) and if the FT >>group could continue to "host" this, that would be great. It >>would also be good to cross-post the TelCon announcement to the >>tools and AM WGs (for the latter, Torsten has voiced interest). >> >>Thanks, >> >>Martin >> >> >> >>- During the face-to-face discussion we began talking about the >>desired error notification semantics for collectives. The question >>is: are MPI implementations allowed to provide no error notification >>as part of their collectives, relying on calls to MPI_Validate for >>this functionality or do we expect them to report all relevant >>errors. In particular, is MPI_Barrier responsible for reporting >>failures of any members of the communicator or is it allowed to >>mis- behave in the event of failures and for example, return successfully >>even if one process failed before calling MPI_Barrier? If so, how do >>we bound the limit of such mis-behaviors? >> >>Greg Bronevetsky >>Post-Doctoral Researcher >>Lawrence Livermore National Lab >>(925) 424-5756 >>bronevetsky(a)llnl.gov >>http:// greg.bronevetsky.com >>_______________________________________________ >>mpi3-ft mailing list >>mpi3-ft(a)lists.mpi-forum.org >>http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft >> >>_______________________________________________________________________ >>Martin Schulz, schulzm(a)llnl.gov, http:// people.llnl.gov/schulz6 >>CASC @ Lawrence Livermore National Laboratory, Livermore, USA >> >>_______________________________________________ >>mpi3-ft mailing list >>mpi3-ft(a)lists.mpi-forum.org >>http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft >> >> >> >>-- >>Tony Skjellum, PhD >>RunTime Computing Solutions, LLC >>tony(a)runtimecomputing.com >>direct: +1-205-314-3595 >>cell: +1-205-807-4968 >> >>_______________________________________________ >>mpi3-ft mailing list >>mpi3-ft(a)lists.mpi-forum.org >>http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft > >_______________________________________________ >mpi3-ft mailing list >mpi3-ft(a)lists.mpi-forum.org >http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft

1 0

Re: [Mpi3-ft] Topics for next telecon
by Josh Hursey 17 Jun '09

17 Jun '09

Is there a teleconf today or did you all decide to push until next week due to the Forum meeting last week? -- Josh On Jun 14, 2009, at 8:19 PM, Graham, Richard L. wrote: > All the information is on the web, under the mpi-3 ft working group. > If you need a URL, I can send it to you later - don't have access now. > > Rich > > > From: mpi3-ft-bounces(a)lists.mpi-forum.org > To: MPI 3.0 Fault Tolerance and Dynamic Process Control working Group > Sent: Sun Jun 14 20:11:04 2009 > Subject: Re: [Mpi3-ft] Topics for next telecon > > Hi, What is the telecon schedule and how does one get invited? > Thanks, > Tony > > > On Wed, Jun 10, 2009 at 11:54 PM, Martin Schulz <schulzm(a)llnl.gov> > wrote: > Hi all, > > > At 06:00 PM 6/10/2009, Greg Bronevetsky wrote: > For the next telecon I propose that we address the following topics. > - The piggybacking proposal was considered by the FT group several > months ago but then got lost in a limbo between the FT group and the > tools group. We need to discuss this proposal and the issues behind > it so that we can figure out how to make progress on it. > > I agree with Greg - it would be great if we could pick this up > again and try to come up with a single, common proposal. There is > interest in this from multiple WGs (which is probably part of > the problem of why nobody has pushed this forward) and if the FT > group could continue to "host" this, that would be great. It > would also be good to cross-post the TelCon announcement to the > tools and AM WGs (for the latter, Torsten has voiced interest). > > Thanks, > > Martin > > > > - During the face-to-face discussion we began talking about the > desired error notification semantics for collectives. The question > is: are MPI implementations allowed to provide no error notification > as part of their collectives, relying on calls to MPI_Validate for > this functionality or do we expect them to report all relevant > errors. In particular, is MPI_Barrier responsible for reporting > failures of any members of the communicator or is it allowed to mis- > behave in the event of failures and for example, return successfully > even if one process failed before calling MPI_Barrier? If so, how do > we bound the limit of such mis-behaviors? > > Greg Bronevetsky > Post-Doctoral Researcher > Lawrence Livermore National Lab > (925) 424-5756 > bronevetsky(a)llnl.gov > http:// greg.bronevetsky.com > _______________________________________________ > mpi3-ft mailing list > mpi3-ft(a)lists.mpi-forum.org > http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft > > _______________________________________________________________________ > Martin Schulz, schulzm(a)llnl.gov, http://people.llnl.gov/schulz6 > CASC @ Lawrence Livermore National Laboratory, Livermore, USA > > _______________________________________________ > mpi3-ft mailing list > mpi3-ft(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft > > > > -- > Tony Skjellum, PhD > RunTime Computing Solutions, LLC > tony(a)runtimecomputing.com > direct: +1-205-314-3595 > cell: +1-205-807-4968 > > _______________________________________________ > mpi3-ft mailing list > mpi3-ft(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft

1 0

Re: [Mpi3-ft] Topics for next telecon
by Graham, Richard L. 14 Jun '09

14 Jun '09

All the information is on the web, under the mpi-3 ft working group. If you need a URL, I can send it to you later - don't have access now. Rich ________________________________ From: mpi3-ft-bounces(a)lists.mpi-forum.org To: MPI 3.0 Fault Tolerance and Dynamic Process Control working Group Sent: Sun Jun 14 20:11:04 2009 Subject: Re: [Mpi3-ft] Topics for next telecon Hi, What is the telecon schedule and how does one get invited? Thanks, Tony On Wed, Jun 10, 2009 at 11:54 PM, Martin Schulz <schulzm(a)llnl.gov> wrote: Hi all, At 06:00 PM 6/10/2009, Greg Bronevetsky wrote: For the next telecon I propose that we address the following topics. - The piggybacking proposal was considered by the FT group several months ago but then got lost in a limbo between the FT group and the tools group. We need to discuss this proposal and the issues behind it so that we can figure out how to make progress on it. I agree with Greg - it would be great if we could pick this up again and try to come up with a single, common proposal. There is interest in this from multiple WGs (which is probably part of the problem of why nobody has pushed this forward) and if the FT group could continue to "host" this, that would be great. It would also be good to cross-post the TelCon announcement to the tools and AM WGs (for the latter, Torsten has voiced interest). Thanks, Martin - During the face-to-face discussion we began talking about the desired error notification semantics for collectives. The question is: are MPI implementations allowed to provide no error notification as part of their collectives, relying on calls to MPI_Validate for this functionality or do we expect them to report all relevant errors. In particular, is MPI_Barrier responsible for reporting failures of any members of the communicator or is it allowed to mis-behave in the event of failures and for example, return successfully even if one process failed before calling MPI_Barrier? If so, how do we bound the limit of such mis-behaviors? Greg Bronevetsky Post-Doctoral Researcher Lawrence Livermore National Lab (925) 424-5756 bronevetsky(a)llnl.gov http:// greg.bronevetsky.com _______________________________________________ mpi3-ft mailing list mpi3-ft(a)lists.mpi-forum.org http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft _______________________________________________________________________ Martin Schulz, schulzm(a)llnl.gov, http://people.llnl.gov/schulz6 CASC @ Lawrence Livermore National Laboratory, Livermore, USA _______________________________________________ mpi3-ft mailing list mpi3-ft(a)lists.mpi-forum.org http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft -- Tony Skjellum, PhD RunTime Computing Solutions, LLC tony(a)runtimecomputing.com direct: +1-205-314-3595 cell: +1-205-807-4968

1 0

Re: [Mpi3-ft] Topics for next telecon
by Anthony Skjellum 14 Jun '09

14 Jun '09

Hi, What is the telecon schedule and how does one get invited? Thanks, Tony On Wed, Jun 10, 2009 at 11:54 PM, Martin Schulz <schulzm(a)llnl.gov> wrote: > Hi all, > > At 06:00 PM 6/10/2009, Greg Bronevetsky wrote: > >> For the next telecon I propose that we address the following topics. >> - The piggybacking proposal was considered by the FT group several months >> ago but then got lost in a limbo between the FT group and the tools group. >> We need to discuss this proposal and the issues behind it so that we can >> figure out how to make progress on it. >> > > I agree with Greg - it would be great if we could pick this up > again and try to come up with a single, common proposal. There is > interest in this from multiple WGs (which is probably part of > the problem of why nobody has pushed this forward) and if the FT > group could continue to "host" this, that would be great. It > would also be good to cross-post the TelCon announcement to the > tools and AM WGs (for the latter, Torsten has voiced interest). > > Thanks, > > Martin > > > - During the face-to-face discussion we began talking about the desired >> error notification semantics for collectives. The question is: are MPI >> implementations allowed to provide no error notification as part of their >> collectives, relying on calls to MPI_Validate for this functionality or do >> we expect them to report all relevant errors. In particular, is MPI_Barrier >> responsible for reporting failures of any members of the communicator or is >> it allowed to mis-behave in the event of failures and for example, return >> successfully even if one process failed before calling MPI_Barrier? If so, >> how do we bound the limit of such mis-behaviors? >> >> Greg Bronevetsky >> Post-Doctoral Researcher >> Lawrence Livermore National Lab >> (925) 424-5756 >> bronevetsky(a)llnl.gov >> http:// greg.bronevetsky.com >> _______________________________________________ >> mpi3-ft mailing list >> mpi3-ft(a)lists.mpi-forum.org >> http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft >> > > _______________________________________________________________________ > Martin Schulz, schulzm(a)llnl.gov, http://people.llnl.gov/schulz6 > CASC @ Lawrence Livermore National Laboratory, Livermore, USA > > _______________________________________________ > mpi3-ft mailing list > mpi3-ft(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft > -- Tony Skjellum, PhD RunTime Computing Solutions, LLC tony(a)runtimecomputing.com direct: +1-205-314-3595 cell: +1-205-807-4968

1 0

Re: [Mpi3-ft] Topics for next telecon
by Martin Schulz 10 Jun '09

10 Jun '09

Hi all, At 06:00 PM 6/10/2009, Greg Bronevetsky wrote: >For the next telecon I propose that we address the following topics. >- The piggybacking proposal was considered by the FT group several >months ago but then got lost in a limbo between the FT group and the >tools group. We need to discuss this proposal and the issues behind >it so that we can figure out how to make progress on it. I agree with Greg - it would be great if we could pick this up again and try to come up with a single, common proposal. There is interest in this from multiple WGs (which is probably part of the problem of why nobody has pushed this forward) and if the FT group could continue to "host" this, that would be great. It would also be good to cross-post the TelCon announcement to the tools and AM WGs (for the latter, Torsten has voiced interest). Thanks, Martin >- During the face-to-face discussion we began talking about the >desired error notification semantics for collectives. The question >is: are MPI implementations allowed to provide no error notification >as part of their collectives, relying on calls to MPI_Validate for >this functionality or do we expect them to report all relevant >errors. In particular, is MPI_Barrier responsible for reporting >failures of any members of the communicator or is it allowed to >mis-behave in the event of failures and for example, return >successfully even if one process failed before calling MPI_Barrier? >If so, how do we bound the limit of such mis-behaviors? > >Greg Bronevetsky >Post-Doctoral Researcher >Lawrence Livermore National Lab >(925) 424-5756 >bronevetsky(a)llnl.gov >http:// greg.bronevetsky.com >_______________________________________________ >mpi3-ft mailing list >mpi3-ft(a)lists.mpi-forum.org >http:// lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft _______________________________________________________________________ Martin Schulz, schulzm(a)llnl.gov, http://people.llnl.gov/schulz6 CASC @ Lawrence Livermore National Laboratory, Livermore, USA

1 0

[Mpi3-ft] Topics for next telecon
by Greg Bronevetsky 10 Jun '09

10 Jun '09

For the next telecon I propose that we address the following topics. - The piggybacking proposal was considered by the FT group several months ago but then got lost in a limbo between the FT group and the tools group. We need to discuss this proposal and the issues behind it so that we can figure out how to make progress on it. - During the face-to-face discussion we began talking about the desired error notification semantics for collectives. The question is: are MPI implementations allowed to provide no error notification as part of their collectives, relying on calls to MPI_Validate for this functionality or do we expect them to report all relevant errors. In particular, is MPI_Barrier responsible for reporting failures of any members of the communicator or is it allowed to mis-behave in the event of failures and for example, return successfully even if one process failed before calling MPI_Barrier? If so, how do we bound the limit of such mis-behaviors? Greg Bronevetsky Post-Doctoral Researcher Lawrence Livermore National Lab (925) 424-5756 bronevetsky(a)llnl.gov http://greg.bronevetsky.com

1 0

[Mpi3-ft] Svn
by Richard Barrett 10 Jun '09

10 Jun '09

Folks, We have set up an svn repository for managing documents, etc. To activate your account, two steps are required: (1) Request an XCAMS by selecting a NEW XCAMS username/password: https://xcams.ornl.gov/xcams/regStep1.shtml (2) Go to the SCICOMP Forge Account Request Page and at the following link request the desired applications/services: https://forge-ldap.ornl.gov/accounts/request.html For these purposes, https://forge-cluster.ornl.gov/mpiFT/svn Please let me know when you have done this, and please let me know if you have any problems. Thanks, Richard -- Richard Barrett Application Performance Tools group Computer Science and Mathematics Division Oak Ridge National Laboratory http://users.nccs.gov/~rbarrett

1 0

Re: [Mpi3-ft] Next wg on 6/3/2009
by Richard Graham 01 Jun '09

01 Jun '09

No responses to this, so this week¹s telecon is canceled, and we will talk at the face-to-face meeting next week. Rich On 5/27/09 10:05 AM, "Richard Graham" <rlgraham(a)ornl.gov> wrote: > Does anyone have items for discussion at next weeks planned wg call ? If so, > please let me know by this Friday, 5/27/2009. If not, we will meet next at > our face-to-face meeting in 2 weeks. > > Thanks, > Rich > > _______________________________________________ > mpi3-ft mailing list > mpi3-ft(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft

1 0