Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] Problems Broadcasting/Scattering Data
From: Dino Rossegger (dino.rossegger_at_[hidden])
Date: 2008-01-08 13:31:51


Hi,
thanks for the programm, but sadly I can't get it work :(.
It's the same error as in my programm. I get the following output:
0
0
0
10
0
0
11
0
0

Which as far as I know can't be correct. It's the same problem that I
had in my programm. The process with the rank 0 has the right data in
it's array, all the others only 0.
Andreas Schäfer schrieb:
> Hi Dino,
>
> On 18:05 Tue 08 Jan , Dino Rossegger wrote:
>> In fact it is initialized, as I stated in my first mail I only left out
>> the code where it gets initialized, since it reads the data from a file
>> and that works (I have tested it).
>
> (you should have provided a self contained excerpt)
>
> I have reworked your program to check what's running wrong. In fact it
> seems to work as expected, although you might want to double check
> your array sizes, they're named a bit confusingly.
>
> Maybe it didn't work because there was no MPI_Finalize() at the
> end. But then again I might not understand your problem. The other
> machines do no output, so how can their output be wrong? If you expect
> the other processors to have the same data in stat3 as rank 0 does,
> then you should rather use MPI_Allgather than MPI_Gather, as
> MPI_Gather will only concentrate the data on the root node, which is 0
> in your case. Thus, the other nodes cannot produce the same output as
> node 0.

No, I had a MPI_Finalize only cutted it away when I was pasting the
programm. And I also understand that ther can't be the same output but
only 0 is a little bit confusing for me.
> I've attached my reworked version (including some initialization
> code for clarity). If you want me again to debug a program of yours,
> send a floppy along with a pizza Hawai (cartwheel size) to:
> Andreas Schäfer
> Cluster and Metacomputing Working Group
> Friedrich-Schiller-Universität Jena
> Ernst-Abbe-Platz 2
> 07743 Jena
> Germany
>
> Seriously, that would be cool :P
>
> HTH
> -Andi
>

I would send you a pizza haway with a floppy but I fear that it will be
cold until it gets to you ;).
>
>
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users