Err... I'm a little confused. We've been emailing about this exact
issue for a week or two (off list); you just re-started the
conversation from the beginning, moved it to the user's list, and
dropped all the CC's (which include several people who are not on this
list). Why did you do tha
Jeff:
That patch didn't work. However, I hacked the configure file and got it to work
by forcing OMPI_PTRDIFF_TYPE to be long:
line 65040 of configure
#define OMPI_PTRDIFF_TYPE long
It compiled just fine after this.
Thanks for all your efforts
--- On Fri, 2/20/09, Jeff Squyres wrote:
From:
Yes, Eugene fomulates my question in a clear way.
I have indeed been successfully using NULL for all those arguments
in MPI_Gatherv (for instance) where it is explicitly stated that
the argument in question is ignored.
So i have been wondering whether a buffer argument is also ignored
when the buf
It would be interesting to see what happens with the 1.3 build.
It's hard to interpret the output of your user's test program without
knowing exactly what that printf means...
On Feb 23, 2009, at 4:44 PM, Jim Kusznir wrote:
I haven't had time to do the openmpi build from the nightly yet, b
I haven't had time to do the openmpi build from the nightly yet, but
my user has run some more tests and now has a simple program and
algorithm to "break" openmpi. His notes:
hey, just fyi, I can reproduce the error readily in a simple test case
my "way to break mpi" is as follows: Master proc ru
I think the question is about passing NULL as a buffer pointer. E.g.,
MPI_Send(NULL, 0, mytype,dst, tag,comm);
vs
MPI_Send(&dummy,0,mytype,dst,tag,comm);
George Bosilca wrote:
The only restriction the MPI standard impose on the sendcounts and
recvcounts arrays is that the values be non-neg
Hi George
I have run into the argument that in a case where the number of array
elements that will be accessed is == 0 it is "obviously" valid to pass NULL
as the array address. I recognize the argument has merit but I am not clear
that it really requires that an MPI implementation that tries to
The only restriction the MPI standard impose on the sendcounts and
recvcounts arrays is that the values be non-negative, so zero is a
legal value.
I don't really understand your second question. Where do you want to
use NULL ? In general NULL is not accepted in MPI as an argument for
any
The description of the problem is included in Problem txt-file in the zipped
attachment.
Thank you.
ompi_support.tar.gz
Description: GNU Zip compressed data
I am not 100% sure I understand your situation. It it this?
Process A has an ongoing stream of inputs. For each input unit, A does some
processing and then passes on work to B via a message. B receives the
message from A and does some additional work before sending a message to C.
C receives th
On Feb 23, 2009, at 10:44 AM, Olaf Lenz wrote:
I think that a simple solution would be to put a link onto the Trac
Timeline page that says something like: "To report bugs, please
refer to the mailing list. This tracker is mostly for the OpenMPI
developers." or something like that. But I bel
Hi!
PS: It is not obvious on the OpenMPI web site where to report bugs. When
clicking on "Bug Tracking", which seems most obvious, I'm redirected to
the Trac Timeline, and there is no place where I can report bugs or
anything.
Bummer; I had thought the Big Red Links for "Getting Help/Support"
I would suggest that if C receives some kind of quit command, it
should send that command to both A & B, and then call MPI_Finalize.
When A & B receive the quit command, they can complete whatever they
are currently doing (you'll have to set a flag so they know they
should do this), and the
On Feb 20, 2009, at 9:53 AM, Olaf Lenz wrote:
However, I'm using OpenMPI to run a program that we currently develop
(http://www.espresso-pp.de). The software uses Python as a front-end
language, which loads the MPI-enabled shared library. When I start
python with a script using this parallel lib
On Feb 20, 2009, at 6:54 PM, -Gim wrote:
I am trying to use the mpi_bcast function in fortran. I am using
open-mpi-v-1.2.7
Say x is a real variable of size 100. np =100 I try to bcast this
to all the processors.
I use call mpi_bcast(x,np,mpi_real,0,ierr)
Aren't you missing the communi
Hi Ralph,
Ralph Castain wrote:
...
The man page will describe all the various options. Which one is best
for your app really depends on what the app is doing, the capabilities
and topology of your cluster, etc. A little experimentation can help you
get a feel for when to use which one.
Th
Hi
I have an application in which various processes create different
amounts of data (including no data at all).
I have found that MPI_Scatterv and MPI_Gatherv do work with arrays
sendcounts or receivecounts containing zeros.
Since i didn't find the case of 0 sizes in the descriptions
of these fun
17 matches
Mail list logo
