If you don't know the size a priori, you could always make a derived
type that covers the memory region you want, send the size of that
first, and then send the message with the real data (i.e., likely a
derived type).
On Jul 21, 2009, at 2:55 AM, Prasadcse Perera wrote:
Hi,
Its C bindings and if I clear the picture a bit more, what it does
is partitioning the original matrix in to a set of sub matrices to
be processed by the a other processes. And it seems that the only
option left is to bundle off in to a temp buffer before sending as
you have suggested. It would have been nice if there was a derived
data type to do the trick :) ?
Thanks,
Prasad.
On Tue, Jul 21, 2009 at 12:00 PM, Terry Frankcombe
<te...@chem.gu.se> wrote:
Which language bindings?
For Fortran, consider pack or reshape. (I *think* whether array
sections are bundled off into temporary, contiguous storage is
implementation-dependent.)
Isn't it easier to broadcast the size first?
On Tue, 2009-07-21 at 11:53 +0530, Prasadcse Perera wrote:
> Hi all,
> I'm writing an application which requires sending some variable size
> of sub matrices to a set of processes by a lead process who holds
the
> original matrix. Here, the matrices are square matrices and the
> receiving process doesn't know the size of the receiving matrix. In
> MPI_Bcast, I have seen that we can broadcast a whole matrix. Is
there
> a similar way to do this with a derived data type for the matrices
> which we can send a matrix without looping the blocks ?.
>
> Thanks,
> Prasad.
> --
> http://www.codeproject.com/script/Articles/MemberArticles.aspx?amid=3489381
> _______________________________________________
> 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
--
http://www.codeproject.com/script/Articles/MemberArticles.aspx?amid=3489381
_______________________________________________
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Jeff Squyres
jsquy...@cisco.com
