Re: [OMPI users] OpenMPI hangs across multiple nodes.

2009-02-11 Thread Ralph Castain
We plan to release a version soon that will use static ports, which should help with this problem as the IT folks will only have to open specified ports that they can select. Unfortunately, that isn't possible with the current version :-/ Ralph On Feb 11, 2009, at 7:49 PM, Robertson Burgess

Re: [OMPI users] OpenMPI hangs across multiple nodes.

2009-02-11 Thread Robertson Burgess
My apologies for not changing the subject to something suitable just then. Thankyou for that. I have not yet been able to get the IT department to help me with disabling the firewalls, but hopefully that is the problem. Sorry for the late response, I was hoping the IT department would be faster.

Re: [OMPI users] users Digest, Vol 1142, Issue 1

2009-02-11 Thread Robertson Burgess
Thankyou for that. I have not yet been able to get the IT department to help me with disabling the firewalls, but hopefully that is the problem. Sorry for the late response, I was hoping the IT department would be faster. Robertson Message: 2 List-Post: users@lists.open-mpi.org Date: Fri, 6 Feb

Re: [OMPI users] openmpi/ib noob question

2009-02-11 Thread Ralph Castain
The ^ applies to everything that follows, so you just turned off all of the tcp, self, and openib comm paths. :-) If you just wanted to drop tcp from that list, you should just use - mca btl self,openib. Ralph On Feb 11, 2009, at 2:01 PM, Gary Draving wrote: Hello, When running the follo

[OMPI users] openmpi/ib noob question

2009-02-11 Thread Gary Draving
Hello, When running the followng program on 4 of my nodes I get the expected response: "/usr/local/bin/mpirun --mca btl tcp,self,openib --hostfile ibnodes -np 4 hello_c" Hello, world, I am 0 of 4 Hello, world, I am 2 of 4 Hello, world, I am 1 of 4 Hello, world, I am 3 of 4 But when I run it

Re: [OMPI users] undefined symbol: tm_init

2009-02-11 Thread Ralph Castain
Actually, this was also the subject of another email thread on the user list earlier today. The user noted that we had lost an important line in our Makefile.am for the tm plm module, and that this was the root cause of the problems you and others have been seeing. We don't see it here beca

Re: [OMPI users] undefined symbol: tm_init

2009-02-11 Thread Brett Pemberton
Ralph Castain wrote: On Feb 9, 2009, at 6:41 PM, Brett Pemberton wrote: Hey, I've just installed OpenMPI 1.3 on our cluster, and am getting this issue on jobs > 1 node. mpiexec: symbol lookup error: /usr/local/openmpi/1.3-pgi/lib/openmpi/mca_plm_tm.so: undefined symbol: tm_init As repo

Re: [OMPI users] Supporting OpenMPI compiled for multiple compilers

2009-02-11 Thread Ashley Pittman
On 11 Feb 2009, at 14:13, Prentice Bisbal wrote: Douglas Guptill wrote: Thanks. I did end up building for all the compilers under separate trees. It looks like the --exec-prefix option is only of use if your compiling 32-bit and 64-bit versions using the same compiler. This is what I decided

Re: [OMPI users] strange error, seems inable to launch job

2009-02-11 Thread Ralph Castain
Never seen that one before, though we did put the test in there "just in case". Basically, this message indicates that the system returned an error when we attempted to dup2 the stdout/err file descriptors so we could setup a pipe by which we can forward that output to you. I have no idea

Re: [OMPI users] Bug in openmpi 1.3 orte/mca/plm/tm/Makefile.am

2009-02-11 Thread Ralph Castain
ARG! You are quite correct - the line got dropped somehow. This is now fixed in 1.3.1, which should come out soon. Thanks for picking up on this! Ralph On Feb 11, 2009, at 5:38 AM, Åke Sandgren wrote: Hi! orte/mca/plm/tm/Makefile.am is missing a mca_plm_tm_la_LIBADD = $(plm_tm_LIBS) like t

Re: [OMPI users] Supporting OpenMPI compiled for multiple compilers

2009-02-11 Thread Prentice Bisbal
Douglas Guptill wrote: > Hello Prentice: > > On Tue, Feb 10, 2009 at 12:04:47PM -0500, Prentice Bisbal wrote: >> I need to support multiple compilers: Portland, Intel and GCC, so I've >> been compiling OpenMPI with each compiler, to avoid the Fortran symbol >> naming problems. When compiling, I'd

[OMPI users] Bug in openmpi 1.3 orte/mca/plm/tm/Makefile.am

2009-02-11 Thread Åke Sandgren
Hi! orte/mca/plm/tm/Makefile.am is missing a mca_plm_tm_la_LIBADD = $(plm_tm_LIBS) like the corresponding line in orte/mca/ras/tm/Makefile.am mca_ras_tm_la_LIBADD... I think this is the cause for the "undefined symbol: tm_init" mail from 2009-02-09 20:41:45 by Brett Pemberton I have the same pro

[OMPI users] strange error, seems inable to launch job

2009-02-11 Thread Mr Yann JOBIC
Hello all, I compiled ompi v1.3 (tarball) with the intel compiler on debian etch. Everything went fine, thanks for the FAQ (quite complet) But, when i'm running a job, i've got this error : Trixy03-jobic% mpirun --verbose --debug-daemons -np 4 ./exe [Trixy03:15140] [[19525,0],0] orted_cmd: re

Re: [OMPI users] again on "...mpif90, mpif77 compiler is non-functional"

2009-02-11 Thread simone marras
On Wed, Feb 11, 2009 at 12:11 AM, George Bosilca wrote: > What output do you get if you run /usr/local/bin/mpif77 or > /usr/local/bin/mpif90 ? > > george. Hi there George, thanks for replying; thanks to your question I figured what was going wrong and solved it. The default mpif90 and mpif77 t