Hi Ralph ,
Thank you for your immediate and useful help . I will try out what you have
posted to see if the porting can be successful .
Regards,
Jing Zhang
2010/3/18 Ralph Castain
> Hi Jing
>
> Someone else took a look at this off-list a few years ago. It was mostly a
> problem with the build
Pascal,
Patch accepted. In the trunk r22864. I'll create CMR for the 1.4 and 1.5 and
push them there asap.
Thanks,
george.
On Mar 22, 2010, at 06:28 , Pascal Deveze wrote:
> George,
>
> You are right.
> - I agree with you: The Open MPI ompi_datatype_is_contigous_memory runs
> correctly
Hello
There are --preload-binary and --preload-files mpirun options mentioned
in man page which do the same as the script that you're going to write.
В Пнд, 22/03/2010 в 11:18 -0400, herbey zepeda пишет:
> Yes Tim it's along these lines,
> I see, so if I understand correctly we have two options:
Yes Tim it's along these lines,
I see, so if I understand correctly we have two options:
1-Using a network file system (it will be the file system's responsibility
to export P binaries from C to A and B)
2-manually copy the binaries to the machines that will be executing the
program P (in this ca
If I understood your question correctly, it's not really the MPI
implementation's duty to solve this issue. You either have to copy the
binaries to each machine manually or (more usually) each machine is given
access to a common shared file system.
Tim
On 22 March 2010 15:42, herbey zepeda wrote
Hi,
In open MPI, where are the binaries stored.
Let's say I have a program P that adds the numbers in an array of length 10
I want to distribute the execution between 2 computers A and B
A adds from array[0] to array[4]
B adds from array[5] to array[9]
I understand that I have to tell mpi that ma
Fixed! Thanks for this hint.
On Friday 19 March 2010 20:08:53 Terry Dontje wrote:
> I was trying to compile the trunk head using Linux and Sun Studio
> compilers and saw the following error. I am not sure that the compiler
> really is the smoking gun. I see that State.cpp was last modified in
>
George,
You are right.
- I agree with you: The Open MPI ompi_datatype_is_contigous_memory runs
correctly.
- The problem comes with ROMIO: They need a function that returns true
if the content is contiguous AND the content start at the pointer
position (displacement zero).
- MPI Datatypes are
George,
You are right.
- I agree with you: The Open MPI ompi_datatype_is_contigous_memory runs
correctly.
- The problem comes with ROMIO: They need a function that returns true
if the content is contiguous AND the content start at the pointer
position (displacement zero).
- MPI Datatypes are
