On Tue, 13 Mar 2012 at 5:31pm, Ralph Castain wrote
FWIW: I have a Centos6 system myself, and I have no problems running
OMPI on it (1.4 or 1.5). I can try building it the same way you do and
see what happens.
I can run as many threads as I like on a single system with no problems,
even if th
On Tue, 13 Mar 2012 at 11:28pm, Gutierrez, Samuel K wrote
Can you rebuild without the "--enable-mpi-threads" option and try again.
I did and still got segfaults (although w/ slightly different backtraces).
See the response I just sent to Ralph.
--
Joshua Baker-LePain
QB3 Shared Cluster Sysa
On Tue, 13 Mar 2012 at 6:05pm, Ralph Castain wrote
I started playing with this configure line on my Centos6 machine, and
I'd suggest a couple of things:
1. drop the --with-libltdl=external ==> not a good idea
2. drop --with-esmtp ==> useless unless you really want pager messages
notifying
MPI_TAG_UB is not a constant, it is a predefined attribute. As such it should
be accessed using the attribute accessors (MPI_COMM_GET_ATTR page 229 in the
MPI 2.2 standard).
george.
On Mar 13, 2012, at 13:51 , Timothy Stitt wrote:
> Hi Jeff,
>
> I went through the procedure of compiling and
Hi Joshua
Can you your int counter "i" get so large?
> for(i=0; i<=1; i++)
I may be mistaken, but
1,000,000,000,000 = 10**12 > 2**31=2,147,483,647=maximum int.
Unless they are 64-bit long[s].
Just a thought.
Gus Correa
On Mar 13, 2012, at 4:54 PM, Joshua Baker-LePain wrote:
I started playing with this configure line on my Centos6 machine, and I'd
suggest a couple of things:
1. drop the --with-libltdl=external ==> not a good idea
2. drop --with-esmtp ==> useless unless you really want pager messages
notifying you of problems
3. drop --enable-mpi-threads for now
Hmmm….you might try removing the -enable-mpi-threads from the configure to be
safe.
FWIW: I have a Centos6 system myself, and I have no problems running OMPI on it
(1.4 or 1.5). I can try building it the same way you do and see what happens.
On Mar 13, 2012, at 5:22 PM, Joshua Baker-LePain wro
Can you rebuild without the "--enable-mpi-threads" option and try again.
Thanks,
Sam
On Mar 13, 2012, at 5:22 PM, Joshua Baker-LePain wrote:
> On Tue, 13 Mar 2012 at 10:57pm, Gutierrez, Samuel K wrote
>
>> Fooey. What compiler are you using to build Open MPI and how are you
>> configuring yo
On Tue, 13 Mar 2012 at 10:57pm, Gutierrez, Samuel K wrote
Fooey. What compiler are you using to build Open MPI and how are you
configuring your build?
I'm using gcc as packaged by RH/CentOS 6.2:
[jlb@opt200 1.4.5-2]$ gcc --version
gcc (GCC) 4.4.6 20110731 (Red Hat 4.4.6-3)
I actually tried
On Tue, 13 Mar 2012 at 5:06pm, Ralph Castain wrote
Out of curiosity: could you send along the mpirun cmd line you are using
to launch these jobs? I'm wondering if the SGE integration itself is the
problem, and it only shows up in the sm code.
It's about as simple as it gets:
mpirun -np $NSLO
Out of curiosity: could you send along the mpirun cmd line you are using to
launch these jobs? I'm wondering if the SGE integration itself is the problem,
and it only shows up in the sm code.
On Mar 13, 2012, at 4:57 PM, Gutierrez, Samuel K wrote:
>
> On Mar 13, 2012, at 4:07 PM, Joshua Baker
On Mar 13, 2012, at 4:07 PM, Joshua Baker-LePain wrote:
> On Tue, 13 Mar 2012 at 9:15pm, Gutierrez, Samuel K wrote
>
Any more information surrounding your failures in 1.5.4 are greatly
appreciated.
>>>
>>> I'm happy to provide, but what exactly are you looking for? The test code
>>
On Tue, 13 Mar 2012 at 9:15pm, Gutierrez, Samuel K wrote
Any more information surrounding your failures in 1.5.4 are greatly
appreciated.
I'm happy to provide, but what exactly are you looking for? The test
code I'm running is *very* simple:
If you experience this type of failure with 1.4.
On Mar 13, 2012, at 2:54 PM, Joshua Baker-LePain wrote:
> On Tue, 13 Mar 2012 at 7:53pm, Gutierrez, Samuel K wrote
>
>> The failure signature isn't exactly what we were seeing here at LANL, but
>> there were misplaced memory barriers in Open MPI 1.4.3. Ticket 2619 talks
>> about this issue (h
On Tue, 13 Mar 2012 at 7:53pm, Gutierrez, Samuel K wrote
The failure signature isn't exactly what we were seeing here at LANL,
but there were misplaced memory barriers in Open MPI 1.4.3. Ticket 2619
talks about this issue (https://svn.open-mpi.org/trac/ompi/ticket/2619).
This doesn't explain,
The failure signature isn't exactly what we were seeing here at LANL, but there
were misplaced memory barriers in Open MPI 1.4.3. Ticket 2619 talks about this
issue (https://svn.open-mpi.org/trac/ompi/ticket/2619). This doesn't explain,
however, the failures that you are experiencing within Op
On Tue, 13 Mar 2012 at 7:20pm, Gutierrez, Samuel K wrote
Just to be clear, what specific version of Open MPI produced the
provided backtrace? This smells like a missing memory barrier problem.
The backtrace in my original post was from 1.5.4 -- I took the 1.5.4
source and put it into the 1.5
Hi,
Just to be clear, what specific version of Open MPI produced the provided
backtrace? This smells like a missing memory barrier problem.
--
Samuel K. Gutierrez
Los Alamos National Laboratory
On Mar 13, 2012, at 1:07 PM, Joshua Baker-LePain wrote:
> I run a decent size (600+ nodes, 4000+ co
I run a decent size (600+ nodes, 4000+ cores) heterogeneous (multiple
generations of x86_64 hardware) cluster. We use SGE (currently 6.1u4,
which, yes, is pretty ancient) and just upgraded from CentOS 5.7 to 6.2.
We had been using MPICH2 under CentOS 5, but I'd much rather use OpenMPI
as packa
Hi Jeff,
I went through the procedure of compiling and running, then copied the
procedure verbatim from the command line (see below).
[tstitt@memtfe] /pscratch/tstitt > more mpitag.f90
program mpitag
use mpi
implicit none
integer :: err
call MPI_INIT(err)
print *,MPI_TAG_
Tim --
I am unable to replicate this problem with a 1.4 build with icc.
Can you share your test code?
On Mar 10, 2012, at 7:30 PM, Timothy Stitt wrote:
> Hi all,
>
> I was experimenting with MPI_TAG_UB in my code recently and found that its
> value is set to 0 in my v1.4.3 and v1.4.5 builds
On Mar 9, 2012, at 5:17 PM, Jeremiah Willcock wrote:
> On Open MPI 1.5.1, when I call MPI_Testsome with incount=0 and the two output
> arrays NULL, I get an argument error (MPI_ERR_ARG). Is this the intended
> behavior? If incount=0, no requests can complete, so the output arrays can
> never
22 matches
Mail list logo
