April 2012 - mpiwg-tools - mailman3.cels.anl.gov

Re: [Mpi3-tools] Standardized MPI_COMM_WORLD rank environment variable?
by William Gropp 24 Apr '12

24 Apr '12

Yes, an MPI process need not be an OS process, and there is in fact a long history of such implementations, starting (as far as I know) with TMPI. An easy out is to make this optional and only apply when there is such a one-to-one mapping of MPI and OS processes. Bill William Gropp Director, Parallel Computing Institute Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign On Apr 24, 2012, at 12:46 PM, John DelSignore wrote: > > I'm not familiar with any implementations where there are multiple MPI processes per OS process. I did read Snir's proposal, but I can't say that I'm less confused about what it implies relative to an MPI process's rank in MPI_COMM_WORLD. Are you saying that a single OS process may have contain multiple MPI processes where each MPI process has a unique rank in MPI_COMM_WORLD? And therefore, if we try to use the environment to identify an OS process's rank in MPI_COMM_WORLD, it would have to be more like a list of ranks rather than a single value?

1 0

Re: [Mpi3-tools] Standardized MPI_COMM_WORLD rank environment variable?
by John DelSignore 24 Apr '12

24 Apr '12

Hi Jeff, Jeffrey Squyres wrote: > Rayson Ho has been working with a few tools recently (e.g., Google's > gperftools) that do things like profile (MPI) processes and then > output files with meta data about the run. Valgrind does analogous > things. > > The problem is that if all the MPI processes are running in the same > networked filesystem directory, they need a way to write unique > output filenames. > > A common way to solve this has been to include the process' > MPI_COMM_WORLD rank somewhere in the filename. Open MPI's run time > sets the OMPI_COMM_WORLD_RANK environment variable with that proc's > MPI_COMM_WORLD rank. Likewise, MPICH2 sets the PMI_RANK environment > variable. > > These env variables can then be used to form the tool's output > filename, and all is well. > > My question is: is it worth it to standardize an environment variable > name (or some other mechanism) for a tool to get an MPI process' rank > in MPI_COMM_WORLD? I think so. > I admit that this gets murkier when there are multiple MPI processes > per OS process, but that problem, too, will need to be solved by the > tools... I'm not familiar with any implementations where there are multiple MPI processes per OS process. I did read Snir's proposal, but I can't say that I'm less confused about what it implies relative to an MPI process's rank in MPI_COMM_WORLD. Are you saying that a single OS process may have contain multiple MPI processes where each MPI process has a unique rank in MPI_COMM_WORLD? And therefore, if we try to use the environment to identify an OS process's rank in MPI_COMM_WORLD, it would have to be more like a list of ranks rather than a single value? Cheers, John D.

1 0

[Mpi3-tools] Standardized MPI_COMM_WORLD rank environment variable?
by Jeffrey Squyres 24 Apr '12

24 Apr '12

Rayson Ho has been working with a few tools recently (e.g., Google's gperftools) that do things like profile (MPI) processes and then output files with meta data about the run. Valgrind does analogous things. The problem is that if all the MPI processes are running in the same networked filesystem directory, they need a way to write unique output filenames. A common way to solve this has been to include the process' MPI_COMM_WORLD rank somewhere in the filename. Open MPI's run time sets the OMPI_COMM_WORLD_RANK environment variable with that proc's MPI_COMM_WORLD rank. Likewise, MPICH2 sets the PMI_RANK environment variable. These env variables can then be used to form the tool's output filename, and all is well. My question is: is it worth it to standardize an environment variable name (or some other mechanism) for a tool to get an MPI process' rank in MPI_COMM_WORLD? I admit that this gets murkier when there are multiple MPI processes per OS process, but that problem, too, will need to be solved by the tools... -- Jeff Squyres jsquyres(a)cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/

1 0

Re: [Mpi3-tools] Next TelCon, Monday April 2nd, 8am PDT
by Schulz, Martin 10 Apr '12

10 Apr '12

Hi John, We are trying to get back to the biweekly schedule, starting on 4/2 and then every 14 days. However, Jeff and David had a few things coming up and hence said they wouldn't have a chance to make progress until 4/16 and we canceled that one. This makes the next meeting 4/30 at the usual time. Martin On Apr 9, 2012, at 5:06 AM, John DelSignore wrote: > Hi Martin, > > Sorry I missed the meeting. My calendar is out of sync with the meeting schedule. I noticed that on the website the next meeting is 4/30/12. Have you decided on a regular recurring meeting schedule? I'll be more likely to make it if it's on my calendar properly. > > Cheers, John D. > > > Martin Schulz wrote: >> Hi all, >> >> Just as a reminder - our next MPI-3.x tools TelCon is next Monday, April 2nd, at 8am PDT, 11am EDT, 5pm MSZ. As the main point on the agenda, Jeff will lead the continuation of the discussion on the MPI handles interface. >> >> Login information for WebEx is on the Wiki. >> >> Martin >> >> >> ________________________________________________________________________ >> Martin Schulz, schulzm(a)llnl.gov, http://people.llnl.gov/schulzm >> CASC @ Lawrence Livermore National Laboratory, Livermore, USA >> >> >> >> >> _______________________________________________ >> Mpi3-tools mailing list >> Mpi3-tools(a)lists.mpi-forum.org >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-tools >> ________________________________________________________________________ Martin Schulz, schulzm(a)llnl.gov, http://people.llnl.gov/schulzm CASC @ Lawrence Livermore National Laboratory, Livermore, USA

1 0

Re: [Mpi3-tools] Next TelCon, Monday April 2nd, 8am PDT
by John DelSignore 09 Apr '12

09 Apr '12

Hi Martin, Sorry I missed the meeting. My calendar is out of sync with the meeting schedule. I noticed that on the website the next meeting is 4/30/12. Have you decided on a regular recurring meeting schedule? I'll be more likely to make it if it's on my calendar properly. Cheers, John D. Martin Schulz wrote: > Hi all, > > Just as a reminder - our next MPI-3.x tools TelCon is next Monday, April 2nd, at 8am PDT, 11am EDT, 5pm MSZ. As the main point on the agenda, Jeff will lead the continuation of the discussion on the MPI handles interface. > > Login information for WebEx is on the Wiki. > > Martin > > > ________________________________________________________________________ > Martin Schulz, schulzm(a)llnl.gov, http://people.llnl.gov/schulzm > CASC @ Lawrence Livermore National Laboratory, Livermore, USA > > > > > _______________________________________________ > Mpi3-tools mailing list > Mpi3-tools(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-tools >

1 0