Josh
Thanks for addressing the issue. I will try the new version that has
your fix and let you know.
BTW, I have been in touch with mpi4py team also to debug this issue.
According to mpi4py team, MPI_Bcast() is implemented with two collective
calls: First one with MPI_Bcast() of single intege
On Aug 17, 2010, at 12:32 AM, Eloi Gaudry wrote:
> would it help if i use the upcoming 1.5 version of openmpi ? i read that a
> huge effort has been done to clean-up the valgrind output ? but maybe that
> this doesn't
> concern this btl (for the reasons you mentionned).
I do not believe that
I just fixed the --stop bug that you highlighted in r23627.
As far as the mpi4py program, I don't really know what to suggest. I don't have
a setup to test this locally and am completely unfamiliar with mpi4py. Can you
reproduce this with just a C program?
-- Josh
On Aug 16, 2010, at 12:25 PM,
If you're using IB for HPC/MPI, you probably want an unlimited memlock limit.
Keep in mind that you need to start the slurm daemons with the desired memlock
limit, too -- if they're started via init.d, for example, they won't be subject
to /etc/security/limits.conf.
On Aug 18, 2010, at 12:08 P
ulimit basically states that a normal user can increase a specific limit up to
the maximum specified by root, either via system limit settings or during
configuration of the OS.
So the 256 limit you are seeing is one set locally. I would suggest asking your
sys admin for a higher limit if you r
Hello,
I've done a good bit of reading and still cannot get my mpirun programs to
execute without giving warnings about the memory lock limit not being
"unlimited".
I'm on an infiniband-(openib)-networked cluster under slurm resource mgmt
using openmpi.
Initially I did not want to set max
As of MPI 2.2 there is no longer a restriction against read access to a
live send buffer. The wording was changed to now prohibit the user to
"modify". You can look the subsection of Communication Modes in chapter 3
but you will need to compare MPI 2.1 and 2.2 carefully to see the change.
The
At: Richard Treumann . You said "The Forum has decided the send buffer
rule is to restrictive. " Do you mean that you are planning to change
the rule?
At: Terry Frankcombe. If they are going to change the rule everything
will be fine. Do you know why I don't you want to be standard-compliant?
S
Hi Rick,
All the steps you've done were absolutely correct. The CMake output
messages are not errors but the feature check results; if a real error
occurs, CMake will just stop and pop up an error message window.
Unfortunately, 1.4.2 doesn't have the VS 2010 support yet, it will be
added in
Hi Jeff,
Please find enclosed the output (valgrind.out.gz) from
/opt/openmpi-debug-1.4.2/bin/orterun -np 2 --host pbn11,pbn10 --mca btl
openib,self --display-map --verbose --mca mpi_warn_on_fork 0 --mca
btl_openib_want_fork_support 0 -tag-output /opt/valgrind-3.5.0/bin/valgrind
--tool=memcheck
10 matches
Mail list logo