Hi George,
Thanks for your response.
I confirmed that your commit fixed the issue.
Regards,
Akihiro
On 2016/05/22 5:05, George Bosilca wrote:
16d9f71d01cc should provide a fix for this issue.
George.
On Sat, May 21, 2016 at 12:08 PM, Akihiro Tabuchi mailto:tabu...@hpcs.cs.tsukuba.ac.jp>>
Hi,
I installed openmpi-v2.x-dev-1441-g402abf9 on my "SUSE Linux Enterprise
Server 12 (x86_64)" with Sun C 5.14 and gcc-6.1.0. Unfortunately I
don't get the expected output with "--slot-list". It's the same behaviour
for both compilers.
loki hello_2 114 ompi_info | grep -e "OPAL repo revision:
Hi,
I installed openmpi-v2.x-dev-1441-g402abf9 on my "SUSE Linux Enterprise
Server 12 (x86_64)" with Sun C 5.14 and gcc-6.1.0. Unfortunately I get
a timeout error for "--slot-list". It's the same behaviour for both
compilers.
loki spawn 143 mpiexec -np 1 --host loki,loki,loki,nfs1,nfs1 spawn_m
Hi,
I am using 2 software, one is called Open Foam and the other called EMPIRE that
need to run together at the same time.Open Foam uses Open MPI implementation
and EMPIRE uses either MPICH or intel mpi.The version of Open MPI that comes
with Open Foam is 1.6.5.I am using Intel (R) MPI Library
Hi,
The short answer: Environment module files are probably the best
solution for your problem.
The long answer: See
,
which pretty much addresses your question.
Andy
On 05/23/2016 07:40 AM, Megdich Islem
wrote:
Hi,
I installed openmpi-1.10.3rc2 on my "SUSE Linux Enterprise Server
12 (x86_64)" with Sun C 5.13 and gcc-6.1.0. Unfortunately I get
a segmentation fault for "--slot-list" for one of my small programs.
loki spawn 119 ompi_info | grep -e "OPAL repo revision:" -e "C compiler
absolute:"
O
On May 21, 2016, at 11:31 PM, dour...@aol.com wrote:
>
> I encountered a problem about mpirun and SSH when using OMPI 1.10.0 compiled
> with gcc, running on centos7.2.
> When I execute mpirun on my 2 node cluster, I get the following errors pasted
> below.
>
> [douraku@master home]$ mpirun -np
modules are way more friendly that manually setting and exporting your
environment.
the issue here is you are setting your environment in your .bashrc, and
that cannot work if your account is used with various MPI implementations.
(unless your .bashrc checks a third party variable to select the
app
I cannot replicate the problem - both scenarios work fine for me. I’m not
convinced your test code is correct, however, as you call Comm_free the
inter-communicator but didn’t call Comm_disconnect. Checkout the attached for a
correct code and see if it works for you.
FWIW: I don’t know how many
Dear all,
I'm using openmpi for Java.
I've a problem when I try to use more option parameters in my java command.
More in detail I run mpirun as follow:
mpirun -n 5 java -cp path1:path2 -Djava.library.path=pathLibs
classification.MyClass
It seems that the option "-Djava.library.path" is ignored
I thought the 1.10 branch had been fixed to use clock_gettime for
MPI_Wtime where it's available, a la
https://www.open-mpi.org/community/lists/users/2016/04/28899.php -- and
have been telling people so! However, I realize it hasn't, and it looks
as if 1.10 is still being maintained.
Is there a g
Nobody ever filed a PR to update the branch with the patch - looks like you
never responded to confirm that George’s proposed patch was acceptable. I’ll
create the PR and copy you for review
> On May 23, 2016, at 9:17 AM, Dave Love wrote:
>
> I thought the 1.10 branch had been fixed to use cl
Hello Claudio,
mpirun should be combining your java.library.path option with the one
needed to add
the Open MPI's java bindings as well.
Which version of Open MPI are you using?
Could you first try to compile the Ring.java code in ompi/examples and run
it with the
following additional mpirun par
I tested with OpenMPI 1.10.1 and it works.
See this example, which prints java.library.path
mpijavac LibPath.java
mpirun -np 2 java -Djava.library.path=path LibPath
On Mon, May 23, 2016 at 1:38 PM, Howard Pritchard
wrote:
> Hello Claudio,
>
> mpirun should be combining your java.library.path o
Jeff, Thank you for your advice.
By bad. I took the wrong shot, because I tested so many different settings.
After I came back to the original network settings, "permission denied', of
course disappeared, but the other messages were still there. The master node
has two NICs, one for WAN (via an
You might want to test with some known-good MPI applications first. Try
following the steps in this FAQ item:
https://www.open-mpi.org/faq/?category=running#diagnose-multi-host-problems
> On May 23, 2016, at 2:31 PM, dour...@aol.com wrote:
>
> Jeff, Thank you for your advice.
>
> By bad.
Hi Howard.
Thank you for your reply.
I'm using version 1.10.2
I executed the following command:
mpirun -np 2 --mca odls_base_verbose 100 java -cp alot:of:jarfile
-Djava.library.path=/Users/stamile/Applications/IBM/ILOG/CPLEX_Studio1263/cplex/bin/x86-64_osx
clustering.TensorClusterinCplexMPI
t
Looks to me like there is a bug in the orterun parser that is trying to add
java library paths - I can take a look at it
> On May 23, 2016, at 1:05 PM, Claudio Stamile wrote:
>
> Hi Howard.
>
> Thank you for your reply.
>
> I'm using version 1.10.2
>
> I executed the following command:
>
>
HI Ralph,
Yep, If you could handle this that would be great. I guess we'd like a fix
in 1.10.x and for 2.0.1
that would be great.
Howard
2016-05-23 14:59 GMT-06:00 Ralph Castain :
> Looks to me like there is a bug in the orterun parser that is trying to
> add java library paths - I can take a
mm_free the
inter-communicator but didn?t call Comm_disconnect. Checkout the attached for a
correct code and see if it works for you.
FWIW: I don?t know how many cores you have on your sockets, but if you have 6
cores/socket, then your slot-list is equivalent to ??bind-to none? as the
slot-list
our test code is correct, however, as you call
Comm_free the inter-communicator but didn?t call Comm_disconnect.
Checkout the attached for a correct code and see if it works for you.
FWIW: I don?t know how many cores you have on your sockets, but if you
have 6 cores/socket, then your slot-list is
21 matches
Mail list logo
