[OMPI users] Is Iprobe fast when there is no message to recieve

2009-10-01 Thread Peter Lonjers
I am not sure if this is the right place the ask this question but here it goes. Simplified abstract version of the question. I have 2 MPI processes and I want one to make an occasional signal to the other process. These signals will not happen at predictable times. I want the other process

Re: [OMPI users] Profiling OpenMPI routines

2009-10-01 Thread Eugene Loh
Aniruddha Marathe wrote: I am trying to profile (get the call graph/call sequence of) Open MPI communication routines using GNU Profiler (gprof) since the communication calls are implemented using macros and it's harder to trace them statically. In order to do that I compiled the OpenMPI source

Re: [OMPI users] memalign usage in OpenMPIand it's consequencesforTotalVIew

2009-10-01 Thread Jeff Squyres
On Oct 1, 2009, at 3:27 PM, Åke Sandgren wrote: Yes, but perhaps you need to verify that posix_memalign is also intercepted? Er... right. Of course. :-) https://svn.open-mpi.org/trac/ompi/changeset/22045 I commented on memalign being obsolete since there are a couple of uses of it

[OMPI users] Profiling OpenMPI routines

2009-10-01 Thread Aniruddha Marathe
Hi All, I am trying to profile (get the call graph/call sequence of) Open MPI communication routines using GNU Profiler (gprof) since the communication calls are implemented using macros and it's harder to trace them statically. In order to do that I compiled the OpenMPI source code with

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesforTotalVIew

2009-10-01 Thread Åke Sandgren
On Thu, 2009-10-01 at 15:19 -0400, Jeff Squyres wrote: > On Oct 1, 2009, at 2:19 PM, Åke Sandgren wrote: > > > No it didn't. And memalign is obsolete according to the manpage. > > posix_memalign is the one to use. > > > > > This particular call is testing the memalign intercept in the ptmalloc

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesforTotalVIew

2009-10-01 Thread Jeff Squyres
On Oct 1, 2009, at 2:19 PM, Åke Sandgren wrote: No it didn't. And memalign is obsolete according to the manpage. posix_memalign is the one to use. This particular call is testing the memalign intercept in the ptmalloc component during startup; we can't replace it with posix_memalign.

Re: [OMPI users] memalign usage in OpenMPI and it's consequences for TotalVIew

2009-10-01 Thread Peter Thompson
The value of 4 might be invalid (though maybe on a 32b machine, it would be okay?) but it's enough to allow TotalView to continue on without raising a memory event, so I'm okay with it ;-) PeterT Ashley Pittman wrote: Simple malloc() returns pointers that are at least eight byte aligned

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesfor TotalVIew

2009-10-01 Thread Samuel K. Gutierrez
Good point. That particular call to memalign, however, is part of a series of OMPI memory hook tests. The memory allocated by that memalign call is promptly freed (opal/mca/memory/ptmalloc2/ opal_ptmalloc2_component.c : line 111). The change is to silence TotalView's memory alignment

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesfor TotalVIew

2009-10-01 Thread Åke Sandgren
On Thu, 2009-10-01 at 19:56 +0100, Ashley Pittman wrote: > Simple malloc() returns pointers that are at least eight byte aligned > anyway, I'm not sure what the reason for calling memalign() with a value > of four would be be anyway. That is not necessarily true on all systems. -- Ake Sandgren,

[OMPI users] Are there ways to reduce the memory used by OpenMPI?

2009-10-01 Thread Blosch, Edwin L
Are there are tuning parameters than I can use to reduce the amount of memory used by OpenMPI? I would very much like to use OpenMPI instead of MVAPICH, but I'm on a cluster where memory usage is the most important consideration. Here are three results which capture the problem: With the

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesfor TotalVIew

2009-10-01 Thread Ashley Pittman
Simple malloc() returns pointers that are at least eight byte aligned anyway, I'm not sure what the reason for calling memalign() with a value of four would be be anyway. Ashley, On Thu, 2009-10-01 at 20:19 +0200, Åke Sandgren wrote: > No it didn't. And memalign is obsolete according to the

Re: [OMPI users] memalign usage in OpenMPI and it's consequences for TotalVIew

2009-10-01 Thread Peter Thompson
Took a look at the changes and that looks like it should work. It's certainly not in 1.3.3, but as long as you guys are on top of it, that relieves my concerns ;-) Thanks, PeterT Samuel K. Gutierrez wrote: Ticket created (#2040). I hope it's okay ;-). -- Samuel K. Gutierrez Los Alamos

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesfor TotalVIew

2009-10-01 Thread Åke Sandgren
On Thu, 2009-10-01 at 13:58 -0400, Jeff Squyres wrote: > Did that make it over to the v1.3 branch? No it didn't. And memalign is obsolete according to the manpage. posix_memalign is the one to use. > > > > I think Jeff has already addressed this problem. > > > >

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesfor TotalVIew

2009-10-01 Thread Samuel K. Gutierrez
Ticket created (#2040). I hope it's okay ;-). -- Samuel K. Gutierrez Los Alamos National Laboratory On Oct 1, 2009, at 11:58 AM, Jeff Squyres wrote: Did that make it over to the v1.3 branch? On Oct 1, 2009, at 1:39 PM, Samuel K. Gutierrez wrote: Hi, I think Jeff has already addressed

Re: [OMPI users] openmpi 1.4 and barrier

2009-10-01 Thread Michael Di Domenico
Hmm, i don't recall seeing that... On Thu, Oct 1, 2009 at 1:51 PM, Jeff Squyres wrote: > FWIW, I saw this bug to have race-condition-like behavior. I could run a > few times and then it would work. > > On Oct 1, 2009, at 1:42 PM, Michael Di Domenico wrote: > >> On Thu, Oct

Re: [OMPI users] memalign usage in OpenMPI and it's consequencesfor TotalVIew

2009-10-01 Thread Jeff Squyres
Did that make it over to the v1.3 branch? On Oct 1, 2009, at 1:39 PM, Samuel K. Gutierrez wrote: Hi, I think Jeff has already addressed this problem. https://svn.open-mpi.org/trac/ompi/changeset/21744 -- Samuel K. Gutierrez Los Alamos National Laboratory On Oct 1, 2009, at 11:25 AM, Peter

Re: [OMPI users] openmpi 1.4 and barrier

2009-10-01 Thread Jeff Squyres
FWIW, I saw this bug to have race-condition-like behavior. I could run a few times and then it would work. On Oct 1, 2009, at 1:42 PM, Michael Di Domenico wrote: On Thu, Oct 1, 2009 at 1:37 PM, Jeff Squyres wrote: > On Oct 1, 2009, at 1:24 PM, Michael Di Domenico

Re: [OMPI users] openmpi 1.4 and barrier

2009-10-01 Thread Michael Di Domenico
On Thu, Oct 1, 2009 at 1:37 PM, Jeff Squyres wrote: > On Oct 1, 2009, at 1:24 PM, Michael Di Domenico wrote: > >> I just upgraded to the devel snapshot of 1.4a1r22031 >> >> when i run a simple hello world with a barrier i get >> >>

Re: [OMPI users] memalign usage in OpenMPI and it's consequences for TotalVIew

2009-10-01 Thread Samuel K. Gutierrez
Hi, I think Jeff has already addressed this problem. https://svn.open-mpi.org/trac/ompi/changeset/21744 -- Samuel K. Gutierrez Los Alamos National Laboratory On Oct 1, 2009, at 11:25 AM, Peter Thompson wrote: We had a question from a user who had turned on memory debugging in TotalView and

[OMPI users] memalign usage in OpenMPI and it's consequences for TotalVIew

2009-10-01 Thread Peter Thompson
We had a question from a user who had turned on memory debugging in TotalView and experience a memory event error Invalid memory alignment request. Having a 1.3.3 build of OpenMPI handy, I tested it and sure enough, saw the error. I traced it down to, surprise, a call to memalign. I find

[OMPI users] openmpi 1.4 and barrier

2009-10-01 Thread Michael Di Domenico
I just upgraded to the devel snapshot of 1.4a1r22031 when i run a simple hello world with a barrier i get btl_tcp_endpoint.c:484:mca_btl_tcp_endpoint_recv_connect_ack] received unexpected process identifier if i pull the barrier out the hello world runs fine interestingly enough, i can run IMB

Re: [OMPI users] How to force the configure, and make to build a 32 bit opmi on a 64 bit linux ?

2009-10-01 Thread Jeff Squyres
You probably just want to pass the relevant compiler/linker flags to Open MPI's configure script, such as: ./configure CFLAGS=-m32 CXXFLAGS=-m32 FFLAGS=-m32 FCFLAGS=-m32 ... You need to pass them to all four language flags (C, C++, F77, F90). I used -m32 as an example here; use whatever

[OMPI users] How to force the configure, and make to build a 32 bit opmi on a 64 bit linux ?

2009-10-01 Thread Nader Ahmadi
Hello, We have 64 bit linux box. For a number of reason I need to build a 32 bit openMPI. I have searched FAQ and archived mail, but I couldn't find a good answer. There are some references to this question, in the developer mailing list with no clear response. I am I looking for

Re: [OMPI users] how to SPMD on openmpi

2009-10-01 Thread Jeff Squyres
Open MPI is a compliant MPI-2.1 implementation, meaning that your MPI applications are source compatible with other MPI 2.1 implementations. In short: use MPI_Send and all the other MPI_* functions that you're used to. On Oct 1, 2009, at 6:36 AM, ankur pachauri wrote: hi vipin, thanks

Re: [OMPI users] MPI_Comm_accept()/connect() errors

2009-10-01 Thread Blesson Varghese
The following is the information regarding the error. I am running Open MPI 1.2.5 on Ubuntu 4.2.4, kernel version 2.6.24 I ran the server program as mpirun -np 1 server. This program gave me the output port as 0.1.0:2000. I used this port name value as the command line argument for the client

Re: [OMPI users] how to SPMD on openmpi

2009-10-01 Thread ankur pachauri
hi vipin, thanks for the answer but one thing more, do openmpi had bit different library functions than mpi or it's usage is different (such as i'll have to use ompi_** insted of mpi_** functions) thanks in advance On Thu, Oct 1, 2009 at 2:53 PM, vipin kumar wrote: >

[OMPI users] job fails with "Signal: Bus error (7)"

2009-10-01 Thread Sangamesh B
Hi, A fortran application which is compiled with ifort-10.1 and open mpi 1.3.1 on Cent OS 5.2 fails after running 4 days with following error message: [compute-0-7:25430] *** Process received signal *** [compute-0-7:25433] *** Process received signal *** [compute-0-7:25433] Signal: Bus

Re: [OMPI users] how to SPMD on openmpi

2009-10-01 Thread vipin kumar
Hi Ankur, try this command, $ mpirun -np 2 -host firstHostIp,secondHostIp a.out for details read manual page for "mpirun". $ man mpirun Regards, On Wed, Sep 30, 2009 at 3:22 PM, ankur pachauri wrote: > Dear all, > > I have been able

Re: [OMPI users] error in checkpointing an mpi application

2009-10-01 Thread Constantinos Makassikis
Hi, from what you describe below, seems as if you did not configure well OpenMPI. You issued ./configure --with-ft=cr --enable-mpi-threads --with-blcr=/usr/local/bin --with-blcr-libdir=/usr/local/lib while according to the installation paths you gave it should have been more like

[OMPI users] error in checkpointing an mpi application

2009-10-01 Thread Mallikarjuna Shastry
dear sir i am sending the details as follows 1. i am using openmpi-1.3.3 and blcr 0.8.2 2. i have installed blcr 0.8.2 first under /root/MS 3. then i installed openmpi 1.3.3 under /root/MS 4 i have configured and installed open mpi as follows #./configure --with-ft=cr --enable-mpi-threads

Re: [OMPI users] Openmpi setup with intel compiler.

2009-10-01 Thread vighnesh
Dear Peter, I got info from the net that OPenmpi requires F77 bindings for F90 support. Thats where I was making mistake, i didnt configured for F77 bindings during openmpi setup. I rectified my mistake and after that openmpi was installed successfully for both PGI and INTEL compiler. It was

Re: [OMPI users] Openmpi setup with intel compiler.

2009-10-01 Thread vighnesh
Dear Peter, Your suggestions did worked, it didnt showed any error during make and make install. But it didnt got installed with mpif90 support. I tried to compile my mpi code, but it gave following error. [vighnesh@test_node SIVA]$ /share/apps/mpi/openmpi/intel/bin/mpif90 code.f -o