Re: [OMPI users] readline and mpirun

[s anwar]

Thanks.
Saadat.


On 7/11/06, Ralph Castain  wrote:


 I'm afraid that the current comm_spawn system really can't run unless
started via mpirun. I'm going to take a shot at fixing it in the near future
and can let you know when that is accomplished, but it might take a little
while before I get the time.

Ralph



On 7/11/06 4:26 PM, "s anwar"  wrote:

 Jeff:

I've tried my application with MPICH2 and OpenMPI only. The readline stuff
works in OpenMPI as long as I don't start my application with mpirun. It
does not work in MPICH2 irrespective of whether I start my application with
mpirun or not.

My application starts on a workstation and spawns slave processes on
cluster nodes. The application provides an interactive command shell and
provides some GUI functionality using X.

Do you know how bad is the MPI_Comm_spawn issue if I don't start my
application via an mpirun?

Thanks.
Saadat.

On 7/11/06, *Jeff Squyres (jsquyres)*  wrote:

Sorry for not replying earlier.

It is likely that Open MPI won't work properly in this situation -- Open
MPI provides basic I/O forwarding.  I don't know if curses-based or
readline-based applications will work through our forwarding.

Do you know if this application works with other MPI implementations?

 --
*From:* users-boun...@open-mpi.org [mailto: users-boun...@open-mpi.org ] *On Behalf Of *s anwar


*Sent:* Friday, July 07, 2006 12:46 PM
*To:* Open MPI Users
*Subject:* [OMPI users] readline and mpirun



When I run my MPI enabled application via mpirun, my application
command-prompt looses its readline editing capability. I was wondering if
there is workaround.

Thanks.
Saadat.

___
users mailing list
us...@open-mpi.org   

http://www.open-mpi.org/mailman/listinfo.cgi/users



--
 ___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users



___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] OMPI 1.1 build failure with Intel 9.0

[Greg Lindahl]

On Tue, Jul 11, 2006 at 12:23:16PM -0400, George Bosilca wrote:

> I doubt that icc should know anything about  
> the gxx_personality. In fact it look like icc is trying to use some  
> libraries compiled with g++.

As an aside, both Intel C++ and PathScale C++ are 100% g++ compatible.
Symbols like this are part of the g++ compatibility:

[lindahl@eng-23 2.4]$ nm ipl.so| grep gxx
000a21dc V DW.ref.__gxx_personality_v0
 U __gxx_personality_v0@@CXXABI_1.2

-- greg

Re: [OMPI users] readline and mpirun

[s anwar]

Jeff:

I've tried my application with MPICH2 and OpenMPI only. The readline stuff
works in OpenMPI as long as I don't start my application with mpirun. It
does not work in MPICH2 irrespective of whether I start my application with
mpirun or not.

My application starts on a workstation and spawns slave processes on cluster
nodes. The application provides an interactive command shell and provides
some GUI functionality using X.

Do you know how bad is the MPI_Comm_spawn issue if I don't start my
application via an mpirun?

Thanks.
Saadat.

On 7/11/06, Jeff Squyres (jsquyres)  wrote:


 Sorry for not replying earlier.

It is likely that Open MPI won't work properly in this situation -- Open
MPI provides basic I/O forwarding.  I don't know if curses-based or
readline-based applications will work through our forwarding.

Do you know if this application works with other MPI implementations?

 --
*From:* users-boun...@open-mpi.org [mailto:users-boun...@open-mpi.org] *On
Behalf Of *s anwar
*Sent:* Friday, July 07, 2006 12:46 PM
*To:* Open MPI Users
*Subject:* [OMPI users] readline and mpirun



 When I run my MPI enabled application via mpirun, my application
command-prompt looses its readline editing capability. I was wondering if
there is workaround.

Thanks.
Saadat.


___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] Problem with Openmpi 1.1

[Galen M. Shipman]

Hey Justin,

Any further details?

Thanks,

Galen


On Jul 8, 2006, at 9:10 AM, Justin Bronder wrote:

1.)  Compiling without XL will take a little while, but I have the  
setup

for the
other questions ready now.  I figured I'd answer them right away.

2.)  TCP works fine, and is quite quick compared to mpich-1.2.7p1  
by the

way.
I just reverified this.
WR11C2R45000   160 1 2  10.10   
8.253e+00
||Ax-b||_oo / ( eps * ||A||_1  * N) = 
0.0412956 .. PASSED
||Ax-b||_oo / ( eps * ||A||_1  * ||x||_1  ) = 
0.0272613 .. PASSED
||Ax-b||_oo / ( eps * ||A||_oo * ||x||_oo ) = 
0.0053214 .. PASSED



3.)  Exactly same setup, using mpichgm-1.2.6..14b
WR11C2R45000   160 1 2  10.43   
7.994e+00
-- 
--
||Ax-b||_oo / ( eps * ||A||_1  * N) = 
0.0353693 .. PASSED
||Ax-b||_oo / ( eps * ||A||_1  * ||x||_1  ) = 
0.0233491 .. PASSED
||Ax-b||_oo / ( eps * ||A||_oo * ||x||_oo ) = 
0.0045577 .. PASSED


It also worked with mpichgm-1.2.6..15  (I believe this is the  
version, I

don't have
a node up with it at the moment).

Obviously mpich-1.2.7p1 works as well over ethernet.


Anyways, I'll begin the build with the standard gcc compilers that are
included
with OS X.  This is powerpc-apple-darwin8-gcc-4.0.1.

Thanks,

Justin.

Jeff Squyres (jsquyres) wrote:

Justin --

Can we eliminate some variables so that we can figure out where the
error is originating?

- Can you try compiling without the XL compilers?
- Can you try running with just TCP (and not Myrinet)?
- With the same support library installation (such as BLAS, etc.,
assumedly also compiled with XL), can you try another MPI (e.g., LAM,
MPICH-gm, whatever)?

Let us know what you find.  Thanks!


 
- 
---

*From:* users-boun...@open-mpi.org
[mailto:users-boun...@open-mpi.org] *On Behalf Of *Justin Bronder
*Sent:* Thursday, July 06, 2006 3:16 PM
*To:* Open MPI Users
*Subject:* Re: [OMPI users] Problem with Openmpi 1.1

With 1.0.3a1r10670 the same problem is occuring.  Again the same
configure arguments
as before.  For clarity, the Myrinet drive we are using is 2.0.21

node90:~/src/hpl/bin/ompi-xl-1.0.3 jbronder$ gm_board_info
GM build ID is "2.0.21_MacOSX_rc20050429075134PDT
r...@node96.meldrew.clusters.umaine.edu:/usr/src/gm-2.0.21_MacOSX
Fri Jun 16 14:39:45 EDT 2006."

node90:~/src/hpl/bin/ompi-xl-1.0.3 jbronder$
/usr/local/ompi-xl-1.0.3/bin/mpirun -np 2 xhpl
This succeeds.
||Ax-b||_oo / ( eps * ||A||_1  * N) =0.1196787
.. PASSED
||Ax-b||_oo / ( eps * ||A||_1  * ||x||_1  ) =0.0283195
.. PASSED
||Ax-b||_oo / ( eps * ||A||_oo * ||x||_oo ) =0.0063300
.. PASSED

node90:~/src/hpl/bin/ompi-xl-1.0.3 jbronder$
/usr/local/ompi-xl-1.0.3/bin/mpirun -mca btl gm -np 2 xhpl
This fails.
||Ax-b||_oo / ( eps * ||A||_1  * N) =
717370209518881444284334080.000 .. FAILED
||Ax-b||_oo / ( eps * ||A||_1  * ||x||_1  ) =  
226686309135.4274597

.. FAILED
||Ax-b||_oo / ( eps * ||A||_oo * ||x||_oo ) = 2386641249.6518722
.. FAILED
||Ax-b||_oo  . . . . . . . . . . . . . . . . . =
2037398812542965504.00
||A||_oo . . . . . . . . . . . . . . . . . . . = 
2561.554752
||A||_1  . . . . . . . . . . . . . . . . . . . = 
2558.129237

||x||_oo . . . . . . . . . . . . . . . . . . . =
300175355203841216.00
||x||_1  . . . . . . . . . . . . . . . . . . . =
31645943341479366656.00

Does anyone have a working system with OS X and Myrinet (GM)?  If
so, I'd love to hear
the configure arguments and various versions you are using.   
Bonus

points if you are
using the IBM XL compilers.

Thanks,
Justin.


On 7/6/06, *Justin Bronder* > wrote:

Yes, that output was actually cut and pasted from an OS X
run.  I'm about to test
against 1.0.3a1r10670.

Justin.

On 7/6/06, *Galen M. Shipman* < gship...@lanl.gov
> wrote:

Justin,

Is the OS X run showing the same residual failure?

- Galen

On Jul 6, 2006, at 10:49 AM, Justin Bronder wrote:

Disregard the failure on Linux, a rebuild from scratch of
HPL and OpenMPI
seems to have resolved the issue.  At least I'm not
getting the errors during
the residual checks.

However, this is persisting under OS X.

Thanks,
Justin.

On 7/6/06, *Justin Bronder* < jsbron...@gmail.com
> wrote:

Re: [OMPI users] users Digest, Vol 328, Issue 1

[George Bosilca]

Yvan,

Shame on me for bringing this bug back into the 1.1. Until we release  
the 1.1.1 please use the nightly build or the beta from our web site.  
Starting with the revision 10710 this bug was removed. Forever I hope :)


  Thanks,
george.

On Jul 10, 2006, at 5:27 PM, Yvan Fournier wrote:


Hello,

I just retried replicating the datatype bug on a SUSE Linux 10.1  
system

(on a 32-bit Pentium-M system). Actually, I even get a segmentation
fault at some point. I attach the logfile for the test case
compiled in debug mode, run once directly, the again with valgrind,
as well as my ompi_info output.

I have also encountered the bug on the "parent" case (similar, but
more complex) on my work machine (dual Xeon under Debian Sarge),
but I'll check this simpler test on it just in case.

Best regards,

Yvan Fournier



On Sun, 2006-07-09 at 12:00 -0400, users-requ...@open-mpi.org wrote:

Send users mailing list submissions to
us...@open-mpi.org

To subscribe or unsubscribe via the World Wide Web, visit
http://www.open-mpi.org/mailman/listinfo.cgi/users
or, via email, send a message with subject or body 'help' to
users-requ...@open-mpi.org

You can reach the person managing the list at
users-ow...@open-mpi.org

When replying, please edit your Subject line so it is more specific
than "Re: Contents of users digest..."


Today's Topics:

   1. Re: Datatype bug regression from Open MPI 1.0.2 to Open MPI
  1.1 (George Bosilca)


- 
-


Message: 1
Date: Sat, 8 Jul 2006 13:47:05 -0400 (Eastern Daylight Time)
From: George Bosilca 
Subject: Re: [OMPI users] Datatype bug regression from Open MPI 1.0.2
to Open MPI 1.1
To: Open MPI Users 
Message-ID: 
Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed

Yvan,

I'm unable to replicate this one with the latest Open MPI trunk  
version.
As there is no difference between the trunk and the latest 1.1  
version on
the datatype, I think the bug cannot be reproduced using the 1.1  
either. I
compiled the test twice once using the indexed datatype and once  
without
and the output is exactly the same. I run it on my Apple G5  
desktop as
well as on a cluster of AMD 64, over shared memory and TCP. Can  
you please

recheck that your error is comming from the type indexed please.

   Thanks,
 george.


On Sat, 1 Jul 2006, Yvan Fournier wrote:


Hello,

I had encountered a bug in Open MPI 1.0.1 using indexed datatypes
with MPI_Recv (which seems to be of the "off by one" sort), which
was corrected in Open MPI 1.0.2.

It seems to have resurfaced in Open MPI 1.1 (I encountered it using
different data and did not recognize it immediately, but it seems
it can reproduced using the same simplified test I had sent
the first time, which I re-attach here just in case).

Here is a summary of the case:

--

Each processor reads a file ("data_p0" or "data_p1") giving a  
list of
global element ids. Some elements (vertices from a partitionned  
mesh)

may belong to both processors, so their id's may appear on both
processors: we have 7178 global vertices, 3654 and 3688 of them  
being

known by ranks 0 and 1 respectively.

In this simplified version, we assign coordinates {x, y, z} to each
vertex equal to it's global id number for rank 1, and the  
negative of

that for rank 0 (assigning the same values to x, y, and z). After
finishing the "ordered gather", rank 0 prints the global id and
coordinates of each vertex.

lines should print (for example) as:
 6456 ;   6455.0   6455.0   6456.0
 6457 ;  -6457.0  -6457.0  -6457.0
depending on whether a vertex belongs only to rank 0 (negative
coordinates) or belongs to rank 1 (positive coordinates).

With the OMPI 1.0.1 bug (observed on Suse Linux 10.0 with gcc 4.0  
and on
Debian sarge with gcc 3.4), we have for example for the last  
vertices:

 7176 ;   7175.0   7175.0   7176.0
 7177 ;   7176.0   7176.0   7177.0
seeming to indicate an "off by one" type bug in datatype handling

Not using an indexed datatype (i.e. not defining  
USE_INDEXED_DATATYPE

in the gather_test.c file), the bug dissapears.

--

Best regards,

   Yvan Fournier




"We must accept finite disappointment, but we must never lose  
infinite

hope."
   Martin Luther King



--

___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

End of users Digest, Vol 328, Issue 1
*





___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] OMPI 1.1 build failure with Intel 9.0

[Daryl W. Grunau]

> Message: 2
> Date: Tue, 11 Jul 2006 12:23:16 -0400
> From: George Bosilca 
> Subject: Re: [OMPI users] OMPI 1.1 build failure with Intel 9.0
> To: Open MPI Users 
> Message-ID: <507769b7-8495-478b-b9a8-189826653...@cs.utk.edu>
> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed
> 
> I'm using the Intel compiler 9.0 on several platforms to compile Open  
> MPI. I never get such kind of errors. I look into the attached file  
> and I notice 2 things. First, there is a -m64 flag on the command  
> line, and icc complain about not knowing anything about it (and it's  
> right). Second, at the end of the file, it complain about a missing  
> symbol (gxx_personality). I doubt that icc should know anything about  
> the gxx_personality. In fact it look like icc is trying to use some  
> libraries compiled with g++. Can you check the library path used by  
> your compiler ?
> 
>Thanks,
>  george.

George, my problem was solved by the fix below.  I didn't realize the
difference between icc and icpc - thanks Bernie!

Daryl

> Date: Tue, 11 Jul 2006 09:11:26 -0700
> To: 
> Subject: problem buiding openmpi 1.1
> 
> Daryl,
> 
>   You need to set the C++ compiler to icpc, not icc for things to work.
> 
> Bernie Borenstein
> The Boeing Company
> 

Re: [OMPI users] MPI_Info for MPI_Open_port

[George Bosilca]

The MPI standard definition of a port is not the one you expect. It  
is nothing like a TCP port, even if they support similar operations  
(open and close). This port is an opaque value (however MPI stadard  
define it as being a TEXT) than will be used internally by the MPI  
library in order to allow you to connect to the remote application.  
Moreover, contrary to other MPI library, Open MPI allow you to  
publish and connect over networks that are not Ethernet based (such  
as Myrinet, Infiniband ...).


If you want to know how to find such a port once it is published by  
one MPI application read the MPI_Lookup_name (http://www.ualberta.ca/ 
AICT/RESEARCH/LinuxClusters/doc/mpich2/www3/MPI_Lookup_name.html).


  Good luck,
George.

On Jul 11, 2006, at 2:40 PM, Abhishek Agarwal wrote:


I have a seprate process which is not linked to this process and hence
doesnot know anything about this MPI process. I wants to receive  
some data

for this server process.

Hence I wanted to know if i could specify a specific port. I have used
MPI_publish and it seem to work fine.

Please advice further is there is a way to start a service at a  
particular

port.

Thanks
Abhishek



From: Edgar Gabriel 
Reply-To: Open MPI Users 
To: Open MPI Users 
Subject: Re: [OMPI users] MPI_Info for MPI_Open_port
Date: Tue, 11 Jul 2006 13:29:53 -0500

John Robinson wrote:
The MPI publish/lookup calls should handle this, if OpenMPI has  
them.  I

haven't tried this with OpenMPI yet, but it claims MPI-2 compilance,
right?  ;-)


of course, but MPI does not say what an MPI port has to be. For  
Open MPI

this is *not* equal to a TCP port number... So you can open a port,
publish it, and another process can look this port-name up



/jr
---
Ralph H Castain wrote:

On 7/11/06 11:59 AM, "Edgar Gabriel"  wrote:



Abhishek Agarwal wrote:


Hello,

Is there a way of providing a specific port number in MPI_Info
when using a MPI_Open_port command so that clients know which
port number to connect.

the MPI port-name in Open MPI has nothing to do with a TCP port
number. The port-name right now is a combination of the process
name ( a tuple of cell id, job id and process id) and a tag used
for the communication.

Maybe somebody from the RTE group could comment on whether  
there is

a possibility to specify a specific port number for OOB
communication, I am not aware of any right now...


I'm afraid not - the port number for OOB communications is  
determined

 dynamically be each process, and then communicated between them.

I'm not sure what your intended purpose is here, of course, but you
don't need to worry about your process being able to "talk" via the
OOB - it's all done automatically during launch.

Ralph




Thanks Edgar



Do advice of any solution so that we can create the portname
inside the client once we know the port number of server.

Thanks Abhishek


___ users mailing
list us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

___ users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users



___ users mailing list
us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/ 
users

___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users



--
Edgar Gabriel
Assistant Professor
Department of Computer Science  email:gabr...@cs.uh.edu
University of Houston   http://www.cs.uh.edu/~gabriel
Philip G. Hoffman Hall, Room 524Tel: +1 (713) 743-3857
Houston, TX-77204, USA  Fax: +1 (713) 743-3335
___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users



___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] MPI_Info for MPI_Open_port

[John Robinson]

Hi Edgar,

I really was responding to the original poster, not to you.

The MPI port should be treated as an opaque object, really, right?

I was also wondering whether the user was worried about the TCP port
that MPI daemons use to communicate with each other (assuming there
are daemons involved), but i didn't want to go there.  ;-)

thanks,
/jr
---
Edgar Gabriel wrote:

John Robinson wrote:

The MPI publish/lookup calls should handle this, if OpenMPI has them.  I 
haven't tried this with OpenMPI yet, but it claims MPI-2 compilance, 
right?  ;-)



of course, but MPI does not say what an MPI port has to be. For Open MPI 
this is *not* equal to a TCP port number... So you can open a port, 
publish it, and another process can look this port-name up




/jr
---
Ralph H Castain wrote:


On 7/11/06 11:59 AM, "Edgar Gabriel"  wrote:




Abhishek Agarwal wrote:



Hello,

Is there a way of providing a specific port number in MPI_Info
when using a MPI_Open_port command so that clients know which
port number to connect.


the MPI port-name in Open MPI has nothing to do with a TCP port
number. The port-name right now is a combination of the process
name ( a tuple of cell id, job id and process id) and a tag used
for the communication.

Maybe somebody from the RTE group could comment on whether there is
a possibility to specify a specific port number for OOB
communication, I am not aware of any right now...


I'm afraid not - the port number for OOB communications is determined
dynamically be each process, and then communicated between them.

I'm not sure what your intended purpose is here, of course, but you
don't need to worry about your process being able to "talk" via the
OOB - it's all done automatically during launch.

Ralph





Thanks Edgar




Do advice of any solution so that we can create the portname
inside the client once we know the port number of server.

Thanks Abhishek


___ users mailing
list us...@open-mpi.org 
http://www.open-mpi.org/mailman/listinfo.cgi/users


___ users mailing list 
us...@open-mpi.org 
http://www.open-mpi.org/mailman/listinfo.cgi/users



___ users mailing list 
us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users


___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] MPI_Info for MPI_Open_port

[John Robinson]

The MPI publish/lookup calls should handle this, if OpenMPI has them.  I 
haven't tried this with OpenMPI yet, but it claims MPI-2 compilance, 
right?  ;-)


/jr
---
Ralph H Castain wrote:

On 7/11/06 11:59 AM, "Edgar Gabriel"  wrote:



Abhishek Agarwal wrote:


Hello,

Is there a way of providing a specific port number in MPI_Info
when using a MPI_Open_port command so that clients know which
port number to connect.


the MPI port-name in Open MPI has nothing to do with a TCP port
number. The port-name right now is a combination of the process
name ( a tuple of cell id, job id and process id) and a tag used
for the communication.

Maybe somebody from the RTE group could comment on whether there is
a possibility to specify a specific port number for OOB
communication, I am not aware of any right now...



I'm afraid not - the port number for OOB communications is determined
 dynamically be each process, and then communicated between them.

I'm not sure what your intended purpose is here, of course, but you
don't need to worry about your process being able to "talk" via the
OOB - it's all done automatically during launch.

Ralph




Thanks Edgar



Do advice of any solution so that we can create the portname
inside the client once we know the port number of server.

Thanks Abhishek


___ users mailing
list us...@open-mpi.org 
http://www.open-mpi.org/mailman/listinfo.cgi/users


___ users mailing list 
us...@open-mpi.org 
http://www.open-mpi.org/mailman/listinfo.cgi/users




___ users mailing list 
us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] MPI_Info for MPI_Open_port

[Ralph H Castain]

On 7/11/06 11:59 AM, "Edgar Gabriel"  wrote:

> Abhishek Agarwal wrote:
>> Hello,
>> 
>> Is there a way of providing a specific port number in MPI_Info when using a
>> MPI_Open_port command so that clients know which port number to connect.
> 
> the MPI port-name in Open MPI has nothing to do with a TCP port number.
> The port-name right now is a combination of the process name ( a tuple
> of cell id, job id and process id) and a tag used for the communication.
> 
> Maybe somebody from the RTE group could comment on whether there is a
> possibility to specify a specific port number for OOB communication, I
> am not aware of any right now...

I'm afraid not - the port number for OOB communications is determined
dynamically be each process, and then communicated between them.

I'm not sure what your intended purpose is here, of course, but you don't
need to worry about your process being able to "talk" via the OOB - it's all
done automatically during launch.

Ralph


> 
> Thanks
> Edgar
> 
>> 
>> Do advice of any solution so that we can create the portname inside the
>> client once we know the port number of server.
>> 
>> Thanks
>> Abhishek
>> 
>> 
>> ___
>> users mailing list
>> us...@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
> ___
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] OMPI 1.1 build failure with Intel 9.0

[George Bosilca]

I'm using the Intel compiler 9.0 on several platforms to compile Open  
MPI. I never get such kind of errors. I look into the attached file  
and I notice 2 things. First, there is a -m64 flag on the command  
line, and icc complain about not knowing anything about it (and it's  
right). Second, at the end of the file, it complain about a missing  
symbol (gxx_personality). I doubt that icc should know anything about  
the gxx_personality. In fact it look like icc is trying to use some  
libraries compiled with g++. Can you check the library path used by  
your compiler ?


  Thanks,
george.

On Jul 11, 2006, at 11:53 AM, Daryl W. Grunau wrote:

I'm trying to build version 1.1 with Intel 9.0 compilers and  
getting an
error at the very end in the tools directory: ompi/tools/ 
ompi_info.  The
build appears to die with undefined references to things that  
belong to the
C++ string class (see long attachment).  Strange thing is that this  
same
code compiles fine with the GNU compilers (FC3), PGI (6.1) and  
Pathscale (2.4).
FWIW, my arch is x86_64 ...  I wrote a simple hello.cc program that  
used

the string class and it also compiled/linked/executed fine with icc.
Anyone else seeing this problem or is my compiler not installed  
correctly?

TIA,

Daryl

P.s.  Here's my configure line from config.log:

  $ ./configure --build=x86_64-redhat-linux-gnu --host=x86_64- 
redhat-linux-gnu --target=x86_64-redhat-linux-gnu --program-prefix=  
--prefix=/opt/OpenMPI/openmpi-intel-1.1/ib --exec-prefix=/opt/ 
OpenMPI/openmpi-intel-1.1/ib --bindir=/opt/OpenMPI/openmpi- 
intel-1.1/ib/bin --sbindir=/opt/OpenMPI/openmpi-intel-1.1/ib/sbin -- 
sysconfdir=/etc --datadir=/opt/OpenMPI/openmpi-intel-1.1/ib/share -- 
includedir=/opt/OpenMPI/openmpi-intel-1.1/ib/include --libdir=/opt/ 
OpenMPI/openmpi-intel-1.1/ib/lib64 --libexecdir=/opt/OpenMPI/ 
openmpi-intel-1.1/ib/libexec --localstatedir=/var --sharedstatedir=/ 
opt/OpenMPI/openmpi-intel-1.1/ib/com --mandir=/usr/share/man -- 
infodir=/usr/share/info --prefix=/opt/OpenMPI/openmpi-intel-1.1/ib  
--sysconfdir=/opt/OpenMPI/openmpi-intel-1.1/ib/etc --mandir=/opt/ 
OpenMPI/openmpi-intel-1.1/ib/man --disable-shared --enable-static -- 
with-bproc --with-openib=/opt/IB/ibgd-2.0.1



___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

[OMPI users] MPI_Info for MPI_Open_port

[Abhishek Agarwal]

Hello,

Is there a way of providing a specific port number in MPI_Info when using a 
MPI_Open_port command so that clients know which port number to connect.


Do advice of any solution so that we can create the portname inside the 
client once we know the port number of server.


Thanks
Abhishek

Re: [OMPI users] OMPI 1.1 build failure with Intel 9.0

[David Gunter]

What machine is this on, Daryl?  I have a conference call with Intel  
re: compiler problems today.  If I can verify this is an Intel  
problem I can bring it up to them.


Thanks,
david

On Jul 11, 2006, at 9:53 AM, Daryl W. Grunau wrote:

I'm trying to build version 1.1 with Intel 9.0 compilers and  
getting an
error at the very end in the tools directory: ompi/tools/ 
ompi_info.  The
build appears to die with undefined references to things that  
belong to the
C++ string class (see long attachment).  Strange thing is that this  
same
code compiles fine with the GNU compilers (FC3), PGI (6.1) and  
Pathscale (2.4).
FWIW, my arch is x86_64 ...  I wrote a simple hello.cc program that  
used

the string class and it also compiled/linked/executed fine with icc.
Anyone else seeing this problem or is my compiler not installed  
correctly?

TIA,

Daryl

P.s.  Here's my configure line from config.log:

  $ ./configure --build=x86_64-redhat-linux-gnu --host=x86_64- 
redhat-linux-gnu --target=x86_64-redhat-linux-gnu --program-prefix=  
--prefix=/opt/OpenMPI/openmpi-intel-1.1/ib --exec-prefix=/opt/ 
OpenMPI/openmpi-intel-1.1/ib --bindir=/opt/OpenMPI/openmpi- 
intel-1.1/ib/bin --sbindir=/opt/OpenMPI/openmpi-intel-1.1/ib/sbin -- 
sysconfdir=/etc --datadir=/opt/OpenMPI/openmpi-intel-1.1/ib/share -- 
includedir=/opt/OpenMPI/openmpi-intel-1.1/ib/include --libdir=/opt/ 
OpenMPI/openmpi-intel-1.1/ib/lib64 --libexecdir=/opt/OpenMPI/ 
openmpi-intel-1.1/ib/libexec --localstatedir=/var --sharedstatedir=/ 
opt/OpenMPI/openmpi-intel-1.1/ib/com --mandir=/usr/share/man -- 
infodir=/usr/share/info --prefix=/opt/OpenMPI/openmpi-intel-1.1/ib  
--sysconfdir=/opt/OpenMPI/openmpi-intel-1.1/ib/etc --mandir=/opt/ 
OpenMPI/openmpi-intel-1.1/ib/man --disable-shared --enable-static -- 
with-bproc --with-openib=/opt/IB/ibgd-2.0.1



___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] Tutorial

[Eric Thibodeau]

www.clustermonkey.net is a very good place to start, click on the "Columns" 
section in the "Main Menu" in the left pane.

Le mardi 11 juillet 2006 07:25, Tony Power a écrit :
> Hi!
> Where can I find a introductory tutorial on open-mpi?
> Thank you ;)
> ___
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
> 

-- 
Eric Thibodeau
Neural Bucket Solutions Inc.
T. (514) 736-1436
C. (514) 710-0517