We will disagree on that, but your datatype is contiguous. It doesn't matter
that there are gaps in the beginning and at the end, as long as you only send
one such datatype the real data that has to go over the network _is_
contiguous. And this is what the Open MPI datatype engine is reporting b
Hi all,
Sorry, I missed my porting from MPICH2 to OpenMPI concerning the file
romio/adio/comm/flatten.c
(flatten.c in OpenMPI does not support MPI_COMBINER_RESIZED).
Here is the diff:
diff -u flatten.c flatten.c.old
--- flatten.c 2010-03-18 17:07:43.0 +0100
+++ flatten.c.old 2
I would agree with George's comment on this particular bug. I doubt
that the problem is with the datatype engine, but it is more likely
that it is a problem with how the crcp/bkmrk component uses the
datatype engine. I'll have to look into it more later.
-- Josh
On Mar 18, 2010, at 9:00 AM
Takayuki,
ompi_ddt_type_size return the size in bytes of the content of the datatype,
ignoring the gaps. This function is useful to know the amount of data one has
to send over the network, and obviously in this case one should avoid sending
the useless gaps/spaces. This function correspond to
Thank you for your bug reports on the crcp/bkmrk component. It is nice
to have someone else going through the logic and checking it. Please
keep reporting issues as you find them, and the repeater programs are
useful. If you develop any patches that fix these bugs, let me know
and I will be
7th question is as follows:
(7) The result of communication which use derived datatype after taking
checkpoint is incorrect.
Framework : crcp
Component : bkmrk
The source file : ompi/mca/crcp/bkmrk/crcp_bkmrk_pml.c
The function name : traffic_message_append
Framework
6th question is as follows:
(6) About the first_continue_pass static variable in the ft_event functions.
Related frameworks are following.
Framework : bml
Component : r2
The source file : ompi/mca/bml/r2/bml_r2_ft.c
The function name : mca_bml_r2_ft_event
Framework :
5th question is as follows:
(5) Receving with MPI_ANY_SOURCE,MPI_ANY_TAG.
This problem might have already been announced by the Open MPI Trac with
"Ticket #1769".
This problem will occur with usual MPI program.
Framework : crcp
Component : bkmrk
The source file : ompi/mca/crc
Hi Jing
Someone else took a look at this off-list a few years ago. It was mostly a
problem with the build system (some flags are different) and header file names.
I don't believe the port was ever completed though.
I have appended the results of that conversation - the last message contained a
