Re: [OMPI users] Fault Tolerance & Behavior

On Tue, 31 Oct 2006 08:43:10 -0700, Galen M. Shipman wrote: Okay, so these are percentage not modulus, the formula makes some sense now.. so the timeout is between 4.9 and 10.3 ms, you had better plug the cable in/out very quickly The Flash could do it. -- Troy Telford

Re: [OMPI users] psm.h not found for include mtl_psm.h. configure: error: PSM support requested but not found. Aborting

PSM depends on InfiniPath 2.0, to be released in early November. We are currently packaging psm.h as part of the infinipath-devel rpm. cheers, . . christian On Tue, 31 Oct 2006, Mike Aho wrote: > Jeff, Thank you for moving this over to the right place. If you look > inside mtl_psm.h, t

Re: [OMPI users] Problem starting rank other than zero

Just out of curiosity ­ what environment (i.e., allocator and launcher) are you running in? POE? I¹m not sure the POE support is all that good, which is why I ask. Ralph On 10/31/06 12:37 PM, "Nader Ahmadi" wrote: > Hello, > > I am a new OpenMPI user. We are planing to move from IBM AIX POE

[OMPI users] Problem starting rank other than zero

Hello, I am a new OpenMPI user. We are planing to move from IBM AIX POE to OpenMPI. I had noproblem to install, configure, and compile my application, using OpenMPI 1.1.2. (thank you, for making it so easy). "ompi_inf -all" runs fine (see attached ompi_info.txt file), my application runs with n

Re: [OMPI users] ompi_info fails: ...invalid ELF header (ignored)

Hello dear Florian, right across the corner at the University of Stuttgart ,-] On Tuesday 31 October 2006 18:08, Florian Fleissner wrote: > I sucessfully build and installed OpenMPI on a Debian machine running > Sarge. I am not so sure, that the compilation and installation went through correctly,

[OMPI users] psm.h not found for include mtl_psm.h. configure: error: PSM support requested but not found. Aborting

Jeff, Thank you for moving this over to the right place. If you look inside mtl_psm.h, there is a #include . Here is what we are seeing: here's the specific error (happens during configuration) --- MCA component mtl:psm (m4 configuration macro) checking for MCA component mtl:psm compile mode.

Re: [OMPI users] [openib-general] psm.h not found

Moving this post over from openib-general... Open MPI v1.2 is not yet released. Where exactly are you getting it from? If you're getting it from SVN, mtl_psm.h is in ompi/mca/mtl/ psm/mtl_psm.h. What error message, exactly, are you getting? Please see: http://www.open-mpi.org/commu

[OMPI users] ompi_info fails: ...invalid ELF header (ignored)

Hi, I sucessfully build and installed OpenMPI on a Debian machine running Sarge. > uname -a > Linux karush 2.6.11-1-686-smp #1 SMP Mon Jun 20 20:18:45 MDT 2005 i686 GNU/Linux As I am not root, I installed OpenMPI into my home to ~/bin/OpenMPI. I added /OpenMPI/bin to my PATH and /Op

Re: [OMPI users] Fault Tolerance & Behavior

Galen M. Shipman wrote: Gleb Natapov wrote: On Mon, Oct 30, 2006 at 11:45:53AM -0700, Troy Telford wrote: On Sun, 29 Oct 2006 01:34:06 -0700, Gleb Natapov wrote: If you use OB1 PML (default one) it will never recover from link down error no matter how many other tran

Re: [OMPI users] Fault Tolerance & Behavior

Gleb Natapov wrote: On Mon, Oct 30, 2006 at 11:45:53AM -0700, Troy Telford wrote: On Sun, 29 Oct 2006 01:34:06 -0700, Gleb Natapov wrote: If you use OB1 PML (default one) it will never recover from link down error no matter how many other transports you have. The reason is that OB1

[OMPI users] tickets 39 & 55

OpenMPI tickets 39 & 55 deal with problems with the Fortran 90 large interface with regards to: #39: MPI_IN_PLACE in MPI_REDUCE #55: MPI_GATHER with arrays of different dimensions Attached is a p

Re: [OMPI users] Fault Tolerance & Behavior

On Mon, Oct 30, 2006 at 11:45:53AM -0700, Troy Telford wrote: > On Sun, 29 Oct 2006 01:34:06 -0700, Gleb Natapov > wrote: > > > If you use OB1 PML (default one) it will never recover from link down > > error no matter how many other transports you have. The reason is that > > OB1 never tracks w

Re: [OMPI users] MPI_Comm_spawn multiple bproc support

Aha! Thanks for your detailed information - that helps identify the problem. See some thoughts below. Ralph On 10/31/06 3:49 AM, "hpe...@infonie.fr" wrote: > Thank you for you quick reply Ralf, > > As far as I know, the NODES environment variable is created when a job is > submitted to the bj

[OMPI users] Re: Re: MPI_Comm_spawn multiple bproc support

Thank you for you quick reply Ralf, As far as I know, the NODES environment variable is created when a job is submitted to the bjs scheduler. The only way I know (but I am a bproc newbe) is to use the bjssub command. Then, I have retried my test with the following running command: "bjssub -i mp