- mpi-comments - mailman3.cels.anl.gov

Re: [Mpi-comments] error message while I tried to do a parallel job on a cluster
by Terry Pang 30 Jul '14

30 Jul '14

Hi Chun, I had this problem same as you and this is how I solved it. I unsure my method will work for you. I found that my source code example, mympi.c and makefile must have the same location in slaves computers too else it keep showing this error. Then compile them (in slaves too), master and slaves will get the executable file. When run the executable file from master, slaves will detect the execution code you typed from master and run the executable file. Hope this works for you. Good luck!!Thank You. Regards,Terry Pang Date: Tue, 29 Jul 2014 17:35:16 -0700 From: miracle.chun.2010(a)gmail.com To: mpi-comments(a)lists.mpi-forum.org Subject: [Mpi-comments] error message while I tried to do a parallel job on a cluster Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here:[mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed[mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra?And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them?Is there anyone who can give me some hint? Thanks a lot! Best,Chun _______________________________________________ mpi-comments mailing list mpi-comments(a)lists.mpi-forum.org http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments

1 0

Re: [Mpi-comments] hydra problem ?
by Bland, Wesley B. 29 Jul '14

29 Jul '14

This mailing list is for commenting on the MPI Standard. Not for asking questions about using MPI. You should direct your question to the mailings list for your implementation (discuss(a)mpich.org<mailto:[email protected]>). On Jul 29, 2014, at 7:45 PM, "Chun Meng" <miracle.chun.2010(a)gmail.com<mailto:[email protected]>> wrote: Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here: [mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed [mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra? And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them? Is there anyone who can give me some hint? Thanks a lot! Best, Chun _______________________________________________ mpi-comments mailing list mpi-comments(a)lists.mpi-forum.org<mailto:[email protected]> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments

1 0

hydra problem ?
by Chun Meng 29 Jul '14

29 Jul '14

Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here: [mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed [mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra? And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them? Is there anyone who can give me some hint? Thanks a lot! Best, Chun

1 0

error message while I tried to do a parallel job on a cluster
by Chun Meng 29 Jul '14

29 Jul '14

Hi all, I have an error message while I tried to do a parallel job on a cluster. The error is listed here: [mpiexec@M001-********] HYDU_sock_read (./utils/sock/sock.c:222): read errno (Input/output error) [mpiexec@M001-********] control_cb (./pm/pmiserv/pmiserv_cb.c:249): assert (!closed) failed [mpiexec@M001-********] HYDT_dmxu_poll_wait_for_event (./tools/demux/demux_poll.c:77): callback returned error status [mpiexec@M001-********] HYD_pmci_wait_for_completion (./pm/pmiserv/pmiserv_pmci.c:206): error waiting for event [mpiexec@M001-********] main (./ui/mpich/mpiexec.c:404): process manager error waiting for completion I'm using mpich2-1.3.2 to do the job.It seems the error is pointing to hydra? And I'm not sure about if hydra is installed in this cluster.So Maybe I need to install a same version hydra with mpich2 first? Also I'm confused how hydra is linked to mpich2-1.3.2 while installing them? Is there anyone who can give me some hint? Thanks a lot! Best, Chun

1 0

Re: [Mpi-comments] MPICH installation - severe errors and catastrophic errors messages
by Bland, Wesley B. 11 Feb '14

11 Feb '14

Pedro, This is the mailing list for those writing the MPI Standard document to receive comments on it. If you have questions about a specific problem with the library you are using, you should use the support system for that library. In your case, with MPICH, you should email discuss(a)mpich.org<mailto:[email protected]>. Thanks, Wesley On Feb 11, 2014, at 3:02 AM, "Estudos e Projetos Ambientais" <epa(a)ecosoft.com.br<mailto:[email protected]>> wrote: Dear, I am trying to install the MPICH v3.0.4 with PGI Fortran/C/C++ compiler (version 14.1). But during installation process it appeared severe errors and catastrophic errors messages. There were many severe errors messages associated with conftest.c. The catastrophic error appears in conftest.cpp. Nevertheless, my tests indicated that MPICH is working. Please, I need help. Do these error messages harm the MPICH running? Best regards, -- Pedro Ivo Diógenis Belo Environmental Engineer -------------------------------------------------------------------------------- EcoSoft Consultoria e Softwares Ambientais Ltda Environmental Engineering Rua Anabyr Lopes França, 111 - Santa Lúcia - Vitória - ES CEP: 29.056-195 Tel. (27)3315-4493 <config.log> _______________________________________________ mpi-comments mailing list mpi-comments(a)lists.mpi-forum.org<mailto:[email protected]> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments

1 0

MPICH installation - severe errors and catastrophic errors messages
by Estudos e Projetos Ambientais 11 Feb '14

11 Feb '14

Dear, I am trying to install the MPICH v3.0.4 with PGI Fortran/C/C++ compiler (version 14.1). But during installation process it appeared severe errors and catastrophic errors messages. There were many severe errors messages associated with conftest.c. The catastrophic error appears in conftest.cpp. Nevertheless, my tests indicated that MPICH is working. Please, I need help. Do these error messages harm the MPICH running? Best regards, -- Pedro Ivo Diï¿½genis Belo Environmental Engineer -------------------------------------------------------------------------------- EcoSoftConsultoria e Softwares Ambientais Ltda Environmental Engineering Rua Anabyr Lopes Franï¿½a, 111 - Santa Lï¿½cia - Vitï¿½ria - ES CEP: 29.056-195 Tel. (27)3315-4493

1 0

MPI_GET
by Pradeep Jha 15 Jan '14

15 Jan '14

I have been googling but I am still not getting a simple example to show how to use the MPI-2's *one-sided communications*, MPI_GET*. *Can anyone provide me with a very basic example of MPI_GET using fortran90?

1 0

Re: [Mpi-comments] Missing definition of MPI_INTEGER_KIND
by William Gropp 26 Dec '13

26 Dec '13

Thanks - there's no need for an MPI_INTEGER_KIND; those constants were intended to identify the Fortran integer kinds of the corresponding MPI type, and there is no MPI integer. We'll discuss removing the mention of them as an errata. Bill William Gropp Director, Parallel Computing Institute Deputy Director for Research Institute for Advanced Computing Applications and Technologies Thomas M. Siebel Chair in Computer Science University of Illinois Urbana-Champaign On Dec 21, 2013, at 7:23 AM, Michael Hofmann wrote: > Hi, > > the MPI standard version 3.0 misses a definition of the constant > MPI_INTEGER_KIND. The constant is mentioned on page 15 and page 664, but > it is neither used nor defined (even tough the definition is obvious). > > MPI standard version 2.2 had a definition of MPI_INTEGER_KIND in a > subsection about the language interoperability of addresses, but this > subsection seems to be gone. > > > Best regards, > Michael > _______________________________________________ > mpi-comments mailing list > mpi-comments(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments

1 0

Missing definition of MPI_INTEGER_KIND
by Michael Hofmann 21 Dec '13

21 Dec '13

Hi, the MPI standard version 3.0 misses a definition of the constant MPI_INTEGER_KIND. The constant is mentioned on page 15 and page 664, but it is neither used nor defined (even tough the definition is obvious). MPI standard version 2.2 had a definition of MPI_INTEGER_KIND in a subsection about the language interoperability of addresses, but this subsection seems to be gone. Best regards, Michael

1 0

Re: [Mpi-comments] buffer error
by Jim Dinan 12 Jun '13

12 Jun '13

MPICH is reporting that your call to MPI_Gather is not valid. Your src_buf and recv_buf are the same buffer, which is not allowed. Also, what Wesley said. :) ~Jim. On Mon, Jun 10, 2013 at 9:10 AM, Wesley Bland <wbland(a)mcs.anl.gov> wrote: > This mailing list isn't the correct place to ask questions about using > MPI. This is for asking questions about standardizing MPI. I'd encourage > you to repost your question on discuss(a)mpich.org and you'll get > assistance with MPICH there. > > Thanks, > Wesley > > On Jun 10, 2013, at 9:04 AM, amin izadi <izadi.amin(a)gmail.com> wrote: > > > hi to all > > I want to use mpich for running my SUNTANS code > > when I dont use mpich my example code runs. but when I use mpich > > this error creates. > > what's the problem and how can I fix it? > > thanks in advance > > > > Fatal error in PMPI_Gather: Invalid buffer pointer, error stack: > > PMPI_Gather(856): MPI_Gather(sbuf=0xe176a0, scount=1, MPI_INT, > rbuf=0xe176a0, rcount=1, MPI_INT, root=0, comm=0x84000000) failed > > PMPI_Gather(797): Buffers must not be aliased > > > > > =================================================================================== > > = BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES > > = EXIT CODE: 1 > > = CLEANING UP REMAINING PROCESSES > > = YOU CAN IGNORE THE BELOW CLEANUP MESSAGES > > > > _______________________________________________ > > mpi-comments mailing list > > mpi-comments(a)lists.mpi-forum.org > > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments > > > _______________________________________________ > mpi-comments mailing list > mpi-comments(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-comments >

1 0