Re: [O-MPI users] Open MPI @SC2005
> The Open MPI Team will be at SC this year. > I am co-hosting a BOF entitled "Why MPI Makes You Scream! And how can > we simplify parallel debugging?" By the way (though it may be offtopic here)... Does anybody know some statistics on MPI usage. e.i. : - percentage of C, C++, Fortran MPI programs - percentage of SPMD and MPMD programs - MPI function an function groups usage (how many people use topologies, asynchronous IO, communicator attributes etc.) - average number of nodes for running and for debugging I suppose this can be interesting for all MPI community as a valuable feedback from those who use MPI for real applications. There was a survey on SC'93 on the usage of debugging tools ( http://citeseer.ist.psu.edu/pancake94what.html ) and It might be possible (if its not too late now) to do something alike. -- Best regards, Konstantin.
Re: [O-MPI users] Open MPI @SC2005
Konstantin Karganov wrote: The Open MPI Team will be at SC this year. I am co-hosting a BOF entitled "Why MPI Makes You Scream! And how can we simplify parallel debugging?" By the way (though it may be offtopic here)... Does anybody know some statistics on MPI usage. e.i. : - percentage of C, C++, Fortran MPI programs - percentage of SPMD and MPMD programs - MPI function an function groups usage (how many people use topologies, asynchronous IO, communicator attributes etc.) - average number of nodes for running and for debugging I suppose this can be interesting for all MPI community as a valuable feedback from those who use MPI for real applications. There was a survey on SC'93 on the usage of debugging tools ( http://citeseer.ist.psu.edu/pancake94what.html ) and It might be possible (if its not too late now) to do something alike. There has been at least one project analysing these kind of things, look e.g. at http://www.hlrs.de/people/rabenseifner/publ/publications.html for papers about automatic MPI counter profiling. These were studies about the usage of MPI at two different HPC centers. Best regards Edgar -- Best regards, Konstantin. ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- Edgar Gabriel Assistant Professor Department of Computer Science email:gabr...@cs.uh.edu University of Houston http://www.cs.uh.edu/~gabriel Philip G. Hoffman Hall, Room 524Tel: +1 (713) 743-3857 Houston, TX-77204, USA Fax: +1 (713) 743-3335
[O-MPI users] Anyone installed openmpi in Redhat 4?
Hi, Did anyone installed openmpi in Redhat Core 4? I got a major problem to run mpi program with openmpi in RH 4. I would like to share your experience. Regards, Clement -- Clement Kam Man Chu Research Assistant School of Computer Science & Software Engineering Monash University, Caulfield Campus Ph: 61 3 9903 1964
Re: [O-MPI users] Error on mpirun in Redhat Fedora Core 4
Clement -- Sorry for the delay in replying. We're running around crazy here at SC, which pretty much keeps us away from e-mail except early in the morning and late at night. We fixed a bunch of things in the sm btl as of r8136 (someone reported similar issues as you, and we took the exchange off-list to fix). The problems could definitely affect correctness and cause segv's similar to what you were seeing (see http://www.open-mpi.org/community/lists/users/2005/11/0326.php for a little more info). I notice that you're running 8113 here -- could you try the latest nightly snapshot or rc and see if the same problems occur? Thanks for your patience! On Nov 14, 2005, at 4:51 AM, Clement Chu wrote: Hi Jeff, I tried the rc6 and trunk nightly 8150. I got the same problem. I copied the message from terminal as below. [clement@localhost testmpi]$ ompi_info Open MPI: 1.1a1r8113 Open MPI SVN revision: r8113 Open RTE: 1.1a1r8113 Open RTE SVN revision: r8113 OPAL: 1.1a1r8113 OPAL SVN revision: r8113 Prefix: /home/clement/openmpi/ Configured architecture: i686-pc-linux-gnu Configured by: clement Configured on: Mon Nov 14 10:12:12 EST 2005 Configure host: localhost Built by: clement Built on: Mon Nov 14 10:28:21 EST 2005 Built host: localhost C bindings: yes C++ bindings: yes Fortran77 bindings: yes (all) Fortran90 bindings: yes C compiler: gcc C compiler absolute: /usr/bin/gcc C++ compiler: g++ C++ compiler absolute: /usr/bin/g++ Fortran77 compiler: gfortran Fortran77 compiler abs: /usr/bin/gfortran Fortran90 compiler: gfortran Fortran90 compiler abs: /usr/bin/gfortran C profiling: yes C++ profiling: yes Fortran77 profiling: yes Fortran90 profiling: yes C++ exceptions: no Thread support: posix (mpi: no, progress: no) Internal debug support: no MPI parameter check: runtime Memory profiling support: no Memory debugging support: no libltdl support: 1 MCA memory: malloc_hooks (MCA v1.0, API v1.0, Component v1.1) MCA paffinity: linux (MCA v1.0, API v1.0, Component v1.1) MCA maffinity: first_use (MCA v1.0, API v1.0, Component v1.1) MCA timer: linux (MCA v1.0, API v1.0, Component v1.1) MCA allocator: basic (MCA v1.0, API v1.0, Component v1.0) MCA allocator: bucket (MCA v1.0, API v1.0, Component v1.0) MCA coll: basic (MCA v1.0, API v1.0, Component v1.1) MCA coll: hierarch (MCA v1.0, API v1.0, Component v1.1) MCA coll: self (MCA v1.0, API v1.0, Component v1.1) MCA coll: sm (MCA v1.0, API v1.0, Component v1.1) MCA io: romio (MCA v1.0, API v1.0, Component v1.1) MCA mpool: sm (MCA v1.0, API v1.0, Component v1.1) MCA pml: ob1 (MCA v1.0, API v1.0, Component v1.1) MCA pml: teg (MCA v1.0, API v1.0, Component v1.1) MCA pml: uniq (MCA v1.0, API v1.0, Component v1.1) MCA ptl: self (MCA v1.0, API v1.0, Component v1.1) MCA ptl: sm (MCA v1.0, API v1.0, Component v1.1) MCA ptl: tcp (MCA v1.0, API v1.0, Component v1.1) MCA btl: self (MCA v1.0, API v1.0, Component v1.1) MCA btl: sm (MCA v1.0, API v1.0, Component v1.1) MCA btl: tcp (MCA v1.0, API v1.0, Component v1.0) MCA topo: unity (MCA v1.0, API v1.0, Component v1.1) MCA gpr: null (MCA v1.0, API v1.0, Component v1.1) MCA gpr: proxy (MCA v1.0, API v1.0, Component v1.1) MCA gpr: replica (MCA v1.0, API v1.0, Component v1.1) MCA iof: proxy (MCA v1.0, API v1.0, Component v1.1) MCA iof: svc (MCA v1.0, API v1.0, Component v1.1) MCA ns: proxy (MCA v1.0, API v1.0, Component v1.1) MCA ns: replica (MCA v1.0, API v1.0, Component v1.1) MCA oob: tcp (MCA v1.0, API v1.0, Component v1.0) MCA ras: dash_host (MCA v1.0, API v1.0, Component v1.1) MCA ras: hostfile (MCA v1.0, API v1.0, Component v1.1) MCA ras: localhost (MCA v1.0, API v1.0, Component v1.1) MCA ras: slurm (MCA v1.0, API v1.0, Component v1.1) MCA rds: hostfile (MCA v1.0, API v1.0, Component v1.1) MCA rds: resfile (MCA v1.0, API v1.0, Component v1.1) MCA rmaps: round_robin (MCA v1.0, API v1.0, Component v1.1) MCA rmgr: proxy (MCA v1.0, API v1.0, Component v1.1) MCA rmgr: urm (MCA v1.0, API v1.0, Component v1.1) MCA rml: oob (MCA v1.0, API v1.0, Component v1.1) MCA pls: fork (MCA v1.0, API v1.0, Component v1.1) MCA
Re: [O-MPI users] Error on mpirun in Redhat Fedora Core 4
I get this on rh9 ONLY if I leave out a -hostfile option on mpirun, otherwise it works fine. This is an old Red Hat. Regards, Mostyn On Wed, 16 Nov 2005, Jeff Squyres wrote: Clement -- Sorry for the delay in replying. We're running around crazy here at SC, which pretty much keeps us away from e-mail except early in the morning and late at night. We fixed a bunch of things in the sm btl as of r8136 (someone reported similar issues as you, and we took the exchange off-list to fix). The problems could definitely affect correctness and cause segv's similar to what you were seeing (see http://www.open-mpi.org/community/lists/users/2005/11/0326.php for a little more info). I notice that you're running 8113 here -- could you try the latest nightly snapshot or rc and see if the same problems occur? Thanks for your patience! On Nov 14, 2005, at 4:51 AM, Clement Chu wrote: Hi Jeff, I tried the rc6 and trunk nightly 8150. I got the same problem. I copied the message from terminal as below. [clement@localhost testmpi]$ ompi_info Open MPI: 1.1a1r8113 Open MPI SVN revision: r8113 Open RTE: 1.1a1r8113 Open RTE SVN revision: r8113 OPAL: 1.1a1r8113 OPAL SVN revision: r8113 Prefix: /home/clement/openmpi/ Configured architecture: i686-pc-linux-gnu Configured by: clement Configured on: Mon Nov 14 10:12:12 EST 2005 Configure host: localhost Built by: clement Built on: Mon Nov 14 10:28:21 EST 2005 Built host: localhost C bindings: yes C++ bindings: yes Fortran77 bindings: yes (all) Fortran90 bindings: yes C compiler: gcc C compiler absolute: /usr/bin/gcc C++ compiler: g++ C++ compiler absolute: /usr/bin/g++ Fortran77 compiler: gfortran Fortran77 compiler abs: /usr/bin/gfortran Fortran90 compiler: gfortran Fortran90 compiler abs: /usr/bin/gfortran C profiling: yes C++ profiling: yes Fortran77 profiling: yes Fortran90 profiling: yes C++ exceptions: no Thread support: posix (mpi: no, progress: no) Internal debug support: no MPI parameter check: runtime Memory profiling support: no Memory debugging support: no libltdl support: 1 MCA memory: malloc_hooks (MCA v1.0, API v1.0, Component v1.1) MCA paffinity: linux (MCA v1.0, API v1.0, Component v1.1) MCA maffinity: first_use (MCA v1.0, API v1.0, Component v1.1) MCA timer: linux (MCA v1.0, API v1.0, Component v1.1) MCA allocator: basic (MCA v1.0, API v1.0, Component v1.0) MCA allocator: bucket (MCA v1.0, API v1.0, Component v1.0) MCA coll: basic (MCA v1.0, API v1.0, Component v1.1) MCA coll: hierarch (MCA v1.0, API v1.0, Component v1.1) MCA coll: self (MCA v1.0, API v1.0, Component v1.1) MCA coll: sm (MCA v1.0, API v1.0, Component v1.1) MCA io: romio (MCA v1.0, API v1.0, Component v1.1) MCA mpool: sm (MCA v1.0, API v1.0, Component v1.1) MCA pml: ob1 (MCA v1.0, API v1.0, Component v1.1) MCA pml: teg (MCA v1.0, API v1.0, Component v1.1) MCA pml: uniq (MCA v1.0, API v1.0, Component v1.1) MCA ptl: self (MCA v1.0, API v1.0, Component v1.1) MCA ptl: sm (MCA v1.0, API v1.0, Component v1.1) MCA ptl: tcp (MCA v1.0, API v1.0, Component v1.1) MCA btl: self (MCA v1.0, API v1.0, Component v1.1) MCA btl: sm (MCA v1.0, API v1.0, Component v1.1) MCA btl: tcp (MCA v1.0, API v1.0, Component v1.0) MCA topo: unity (MCA v1.0, API v1.0, Component v1.1) MCA gpr: null (MCA v1.0, API v1.0, Component v1.1) MCA gpr: proxy (MCA v1.0, API v1.0, Component v1.1) MCA gpr: replica (MCA v1.0, API v1.0, Component v1.1) MCA iof: proxy (MCA v1.0, API v1.0, Component v1.1) MCA iof: svc (MCA v1.0, API v1.0, Component v1.1) MCA ns: proxy (MCA v1.0, API v1.0, Component v1.1) MCA ns: replica (MCA v1.0, API v1.0, Component v1.1) MCA oob: tcp (MCA v1.0, API v1.0, Component v1.0) MCA ras: dash_host (MCA v1.0, API v1.0, Component v1.1) MCA ras: hostfile (MCA v1.0, API v1.0, Component v1.1) MCA ras: localhost (MCA v1.0, API v1.0, Component v1.1) MCA ras: slurm (MCA v1.0, API v1.0, Component v1.1) MCA rds: hostfile (MCA v1.0, API v1.0, Component v1.1) MCA rds: resfile (MCA v1.0, API v1.0, Component v1.1) MCA rmaps: round_robin (MCA v1.0, API v1.0, Component v1.1) MCA rmgr: proxy (MCA v1.0, API v1.0, Component v1.1) MCA rmgr: urm (MCA v1.0, API v1.0, Compon
[O-MPI users] Configuring port
Hi, I put together a small cluster (4 computers) which has one head node that sees the world and 3 that are on a private network. If I want to use the head node (which has 2 NICs) as part of the ring, how do I tell it to go over the NIC that is part of the private network? In mpich, there is a modification to the hostfile, but I did not see any such thing with OpenMPI Thanks, Enrique _ Enrique Curchitser ec...@columbia.edu
Re: [O-MPI users] Configuring port
On Wed, 16 Nov 2005 14:16:20 -0700, Enrique Curchitser wrote: Hi, I put together a small cluster (4 computers) which has one head node that sees the world and 3 that are on a private network. If I want to use the head node (which has 2 NICs) as part of the ring, how do I tell it to go over the NIC that is part of the private network? In mpich, there is a modification to the hostfile, but I did not see any such thing with OpenMPI Here's an entry from an earlier post to this list (in the archives) that I believe applies: http://www.open-mpi.org/community/lists/users/2005/11/0337.php
Re: [O-MPI users] Configuring port
Thank you. It did the trick! Now on to optimizing the communications over gig-ethernet. _ Enrique Curchitser ec...@columbia.edu On Nov 16, 2005, at 4:29 PM, Troy Telford wrote: On Wed, 16 Nov 2005 14:16:20 -0700, Enrique Curchitser wrote: Hi, I put together a small cluster (4 computers) which has one head node that sees the world and 3 that are on a private network. If I want to use the head node (which has 2 NICs) as part of the ring, how do I tell it to go over the NIC that is part of the private network? In mpich, there is a modification to the hostfile, but I did not see any such thing with OpenMPI Here's an entry from an earlier post to this list (in the archives) that I believe applies: http://www.open-mpi.org/community/lists/users/2005/11/0337.php ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users
