Hi,
I am using autogen.subdirs files to make autogen.sh parse my subdirs. In
each subdirs I have a configure.params file describing the Makefile to
be build (as usual).
The problem is that instead of adding the component to the variable in
the toplevel configure, it creates a separate
Ralph H Castain wrote:
This change has finally been merged into the trunk as r15517. It will
unfortunately require an autogen (sorry).
Please let me know if you encounter any problems. As noted in the commit, I
tried to catch all the places that required change, but cannot guarantee
that I got
I know. This is the reason it was missing in the first commit.
The problem is that because we wanted to make as little changes as
possible to the original trunk, we designed the framework as a "PML"
instead of a new framework (at the mca level). For that reason the
autogen/configure mechanism
Ralph H Castain wrote:
After some investigation, I'm afraid that I have to report that this - as
far as I understand what you are doing - may no longer work in Open MPI in
the future (and I'm pretty sure isn't working in the trunk today except
[maybe] in the special case of hostfile - haven't
mpirun -hostfile big_pool -n 10 -host 1,2,3,4 application : -n 2 -host
99,100 ft_server
This will not work: this is a way to launch MIMD jobs, that share the
same COMM_WORLD. Not the way to launch two different applications that
interact trough Accept/Connect.
Direct consequence on simple
I basically agree with Terry, even if your proposal would solve all
the issue I currently face. I think we need to read the MPI2 standard
to make sure we are not on the brink of breaking the standard.
Aurelien
On Jul 27, 2007, at 10:13 , Ralph Castain wrote:
On 7/27/07 7:58 AM, "Terry
Le 6 sept. 07 à 09:27, Terry D. Dontje a écrit :
Gleb Natapov wrote:
On Thu, Sep 06, 2007 at 06:50:43AM -0600, Ralph H Castain wrote:
WHAT: Decide upon how to handle MPI applications where one or more
processes exit without calling MPI_Finalize
WHY:Some applications can
Hi Sajjad,
First it will depend wether you are writing a new component in an
existing framework (let say you are writing a new BTL for a new type
of interconnect) or a totally new framework (you want to have a
family of component that can manage a totally new functionality in
Open MPI).
Sounds great to me.
Aurelien
Le 11 sept. 07 à 13:03, Jeff Squyres a écrit :
If you genericize the concept, I think it's compatible with FT:
1. during MPI_INIT, one of the MPI processes can request a "notify"
exit pattern for the job: a process must notify the RTE before it
actually exits
This usually means something have been freed twice.
Aurelien
Le 20 sept. 07 à 09:02, Tim Prins a écrit :
Hi folks,
In our nightly runs with the trunk I have started seeing cases
where we
appear to be segfaulting within/below malloc. Below is a typical
output.
Note that this appears to
for stripping out grequest from
critical path when they are not used.
--
Aurelien Bouteiller, PhD
Innovative Computing Laboratory - MPI group
+1 865 974 6321
1122 Volunteer Boulevard
Claxton Education Building Suite 350
Knoxville, TN 37996
anybody in that process. You also need to change names in
makefile.am. The autogen.sh will do all the smart things and
recognize and configure your new component. This is that simple :]
Aurelien
--
Aurelien Bouteiller, PhD
Innovative Computing Laboratory - MPI group
+1 865 974 6321
1122 Volunteer
ad safe accessors could
be added to allow components to change the functions at anytime during
execution and not only during MPI_Init/Finalize. Please make noise if
you find this useful.
If comments does not suggest extra work, I expect this code to be
committed in trunk next week.
Aurelien
This option is still available under a new name in PRTE:
`—map-by :oversubscribe` in parameter form
`OMPI_MCA_rmaps_default_mapping_policy=:oversubscribe` in env form
You can get more details using `prte_info —param all`:
`MCA rmaps: parameter "rmaps_default_mapping_policy" (current value:
14 matches
Mail list logo
