Hello all,
I have the same problem on Vista x64 using 1.5.4. But my configuration is
different:
I have a Jenkins server that launches the executable in a remote Windows
machine, so I suppose that something is missing in my environment.
If I manually launch the application in the machine locall
I have to admit this is driving me a bit crazy,
Trying to debug orterun from vs2010 says "Cannot attach to process", even if
I do "Start debugging" from the UI.
I'll keep digging,
PS: if anyone has time and can join on a openmpi IRC channel :-) that would
be great,
-Original Message-
F
debugging mpirund arrives to
openmpi-1.5.4\opal\mca\base\mca_base_components_select.c:
function mca_base_select
components_available list appears to be empty, ie
orte_debugger_base_components_available appears to be empty (opal list
length=0)
Is this an indication of something meaningful?
Note,
Hi MM,
That doesn't really help.
Do you need a debug version on your 32 bit Windows XP? Maybe I can build
one for you. Will send it to you off the mailing list.
Regards,
Shiqing
On 2011-11-29 2:59 PM, MM wrote:
debugging mpirund arrives to
openmpi-1.5.4\opal\mca\base\mca_base_components_sel
fantastic, thank you very much,
-Original Message-
From: Shiqing Fan [mailto:f...@hlrs.de]
Sent: 29 November 2011 14:10
To: MM
Cc: 'Open MPI Users'
Subject: Re: [OMPI users] orte_debugger_select and orte_ess_set_name failed
Hi MM,
That doesn't really help.
Do you need a debug version o
On Nov 28, 2011, at 11:53 PM, arnaud Heritier wrote:
> I do have a contract and i tried to open a case, but their support is ..
What happens if you put a delay between the two jobs? E.g., if you just delay
a few seconds before the 2nd job starts? Perhaps the ipath device just needs a
litt
That's quite weird/surprising that you would need to set it down to *5* --
that's really low.
Can you share a simple reproducer code, perchance?
On Nov 15, 2011, at 11:49 AM, Tom Rosmond wrote:
> Ralph,
>
> Thanks for the advice. I have to set 'coll_sync_barrier_before=5' to do
> the job. T
Ask and you shall receive!
I got a tip from the MPICH2 guys about how they handle this stuff; it seems
that the magic gfortran compiler flag is -Wl,-commons,use_dylibs. Thanks Dave
Goodell!
I will commit this to the OMPI SVN trunk tonight (because it's an
autotools-level change, which we try
On Wed, Nov 16, 2011 at 03:52:05PM +, Kharche, Sanjay wrote:
>
> Dear All
>
> I am sure this issue has been discussed before on the forum, but I will
> appreciate your comments.
>
> I have a package that tries to do parallel file output using MPI_File_Write:
>
> /* Write to file. */
> mp
