On Fri, Mar/20/2009 01:09:56PM, Ethan Mallove wrote:
> Let me try this again. Below is the error from OMPI 1.3r20826. In my
> last email, I accidentally posted the compiler error from Sun's
> internal OMPI source repository.
>
> $ cd opal/mca/memory/ptmalloc2
> $ make
> /bin/sh ../../../../l
On Friday, 20 March 2009, at 12:49:06 (-0500),
Ethan Mallove wrote:
> Has anyone successfully compiled Open MPI with the PGI compilers in
> 32-bit mode (e.g., using -tp=k8-32 flag)? I am getting the following
> error with 32-bit:
>
>$ cd opal/mca/memory/ptmalloc2
>$ make
>/bin/sh ../
Ethan Mallove wrote:
> On Fri, Mar/20/2009 11:06:00AM, Doug Reeder wrote:
>>Ethan,
>>It looks likesome of the object files that you are trying to link to the
>>malloc.o and malloc-stats.o were compiled as 64 bit objects. Are you using
>>the 32 bit compiler flag for the compile step
Prentice Bisbal wrote:
> Ethan,
>
> I agree with Doug. Did you try to build for 64-bit in the same
> directory? If so, you need to do a 'make clean' or 'make distclean'
> before compiling for 32-bit.
>
> Even if you didn't try to compile for 64-bit yourself, try doing 'make
> clean' or 'make dist
On Fri, Mar/20/2009 11:06:00AM, Doug Reeder wrote:
>Ethan,
>It looks likesome of the object files that you are trying to link to the
>malloc.o and malloc-stats.o were compiled as 64 bit objects. Are you using
>the 32 bit compiler flag for the compile step as well as the link step.
Ethan,
I agree with Doug. Did you try to build for 64-bit in the same
directory? If so, you need to do a 'make clean' or 'make distclean'
before compiling for 32-bit.
Even if you didn't try to compile for 64-bit yourself, try doing 'make
clean' or 'make distclean'. ;)
--
Prentice
Doug Reeder w
Let me try this again. Below is the error from OMPI 1.3r20826. In my
last email, I accidentally posted the compiler error from Sun's
internal OMPI source repository.
$ cd opal/mca/memory/ptmalloc2
$ make
/bin/sh ../../../../libtool --tag=CC --mode=link pgcc -O -DNDEBUG
-tp=k8-32-exp
Ethan,
It looks likesome of the object files that you are trying to link to
the malloc.o and malloc-stats.o were compiled as 64 bit objects. Are
you using the 32 bit compiler flag for the compile step as well as the
link step.
Doug Reeder
On Mar 20, 2009, at 10:49 AM, Ethan Mallove wrote:
Hi,
Has anyone successfully compiled Open MPI with the PGI compilers in
32-bit mode (e.g., using -tp=k8-32 flag)? I am getting the following
error with 32-bit:
$ cd opal/mca/memory/ptmalloc2
$ make
/bin/sh ../../../../libtool --tag=CC --mode=link pgcc -O -DNDEBUG -tp=k8-32
-export-dyna
It is the F-2M but I think for inter-node communication should be
equivalents.
I have not run and MPI pingpong benchmark yet.
The truth is I have a 10 days travel coming next week and I thought I can
take some optimization "light reading" with me.
so I know what I must look for when I came bac
On Mar 20, 2009, at 11:33 AM, Ricardo Fernández-Perea wrote:
This are the results initially
Running 1000 iterations.
Length Latency(us)Bandwidth(MB/s)
0 2.738 0.000
1 2.718 0.368
2 2.707 0.739
10485764392.217
On Fri, Mar 20, 2009 at 2:21 PM, Scott Atchley wrote:
> On Mar 20, 2009, at 5:59 AM, Ricardo Fernández-Perea wrote:
>
> Hello,
>>
>> I am running DL_POLY in various Xserver 8 processor with a myrinet
>> network.using mx-1.2.7
>>
>> While I keep in the same node the process scales reasonably well
On Mar 20, 2009, at 5:59 AM, Ricardo Fernández-Perea wrote:
Hello,
I am running DL_POLY in various Xserver 8 processor with a myrinet
network.using mx-1.2.7
While I keep in the same node the process scales reasonably well but
in the moment I hit the network ...
I will like to try to max
Thanks, I was starting the suspect our mix and match of hardware was
causing some problems.
Gary
Jeff Squyres wrote:
On Mar 19, 2009, at 4:02 PM, Gary Draving wrote:
I have written a simple ring program that seems to run fine but I get
the following warning even though I am not explicitly de
On Mar 20, 2009, at 4:21 AM, Cristian KLEIN wrote:
Jeff Squyres a écrit :
I believe that this was just fixed in OMPI v1.3.1 -- could you try
upgrading?
Yup, the issue is well solved. :)
I would just want to add one thing. Isn't the current solution a
little
bit error prone. I mean, instea
On Mar 19, 2009, at 4:02 PM, Gary Draving wrote:
I have written a simple ring program that seems to run fine but I get
the following warning even though I am not explicitly defining the
btl_openib_ib_max_inline_data with an MCA parm. I'm only getting the
warning in the 3 machines that have the
http://www.cebacad.net/files/openmpi_1.3.1_amd64.deb
http://www.cebacad.net/files/openmpi_1.3.1_amd64.deb.md5
--
Marcelo Soares Souza
http://marcelo.cebacad.net
Short version:
--
The Open MPI development team would like to announce a change in its
release methodology. Starting with the v1.3 series, the second digit
in the Open MPI version number will carry additional significance:
* _Even_ minor release numbers are part of "super-stab
Jeff Squyres a écrit :
> I believe that this was just fixed in OMPI v1.3.1 -- could you try
> upgrading?
Yup, the issue is well solved. :)
I would just want to add one thing. Isn't the current solution a little
bit error prone. I mean, instead of having to check before each call to
ORTE_UPDATE_EX
Hello,
I am running DL_POLY in various Xserver 8 processor with a myrinet
network.using mx-1.2.7
While I keep in the same node the process scales reasonably well but in the
moment I hit the network ...
I will like to try to maximize the mx network before trying to touch the
program code.
Is the
20 matches
Mail list logo
