Fixes:
- Segmentation fault when using watermark variables.
- Segmentation fault when using a handle bound to a no longer valid
performance variable.
- Incorrect return codes from MPI_T_pvar_* functions.
cmr=v1.7.4:reviewer=jsquyres
This commit was SVN r29481.
Thanks to Charles Gerlach for identifying the issue.
Oddly, this issue exists in trunk and v1.7, but ''not'' in the v1.6
tree (!).
cmr=v1.7.4:reviewer=hjelmn
This commit was SVN r29463.
Also, removed an MPI_Aint snuck through (which is a C type, not a Fortran
type). Oddly, the Intel compiler complained about neither of these
issues. :-\
This commit was SVN r29411.
Since this header is included in .F90 files (which are preprocessed,
vs. .f90 files, which are *not* preprocessed), we don't want to
accidentally start C-style comments, which are recognized by some
Fortran compiler preprocessors (e.g., Absoft).
This commit was SVN r29394.
So just move the comment to the prior line, and it's all good. This
is obviosuly not *necessary*, but it helps cut down on warning noise.
This commit was SVN r29393.
BIND(C) doesn't let us have LOGICAL parameters, so we have to be
creative in how we invoke back-end ompi_*_f() C functions.
Additionally, the mpi_f08 type for MPI_Status presented some
difficulties, too.
See the large comment in
ompi/mpi/fortran/use-mpi-f08/mpi-f-interfaces-bind.h that explains
this in much more detail.
This commit was SVN r29384.
There is no "MPI_Aint" in the Fortran interface. Surprisingly, the
Intel compiler didn't choke on this, but the Absoft compiler did.
This commit was SVN r29371.
the fortran handle. Use a seperate opal_pointer_array to keep track of
the fortran handles of communicators.
This commit also fixes a bug in ompi_comm_idup where the newcomm was not
set until after the operation completed.
cmr=v1.7.4:reviewer=jsquyres:ticket=trac:3796
This commit was SVN r29342.
The following Trac tickets were found above:
Ticket 3796 --> https://svn.open-mpi.org/trac/ompi/ticket/3796
Thanks to Jeff for finding and fixing compilation issues with
the new fortran bindings.
cmr=v1.7.4:reviewer=jsquyres:ticket=trac:3796
This commit was SVN r29335.
The following Trac tickets were found above:
Ticket 3796 --> https://svn.open-mpi.org/trac/ompi/ticket/3796
MPI_Comm_idup.
As part of this work I implemented a basic request scheduler in
ompi/comm/comm_request.c. This scheduler might be useful for more
than just communicator requests and could be moved to ompi/request
if there is a demand. Otherwise I will leave it where it is.
Added a non-blocking version of ompi_comm_set to support ompi_comm_idup.
The call makes a recursive call to comm_dup and a non-blocking version
was needed. To simplify the code the blocking version calls the nonblocking
version and waits on the resulting request if one exists.
cmr=v1.7.4:reviewer=jsquyres:ticket=trac:3796
This commit was SVN r29334.
The following Trac tickets were found above:
Ticket 3796 --> https://svn.open-mpi.org/trac/ompi/ticket/3796
Use the same trick for send/recvtypes as we did in r29298 for
![I]Alltoallw. Also, add all prototypes for all the back-end
ompi_neighbor_*_f functions.
Refs trac:3802
This commit was SVN r29299.
The following SVN revision numbers were found above:
r29298 --> open-mpi/ompi@0acebc0a1f
The following Trac tickets were found above:
Ticket 3802 --> https://svn.open-mpi.org/trac/ompi/ticket/3802
Use proper array types for the sendtypes and recevtypes params in the
definition of these subroutines (since they're prototyped to be array
parameters in the module). See the comment in the code for a more
complete explanation.
Note that after talking to Craig Rasumussen, he says that this is
fairly common practice in the Fortran community (i.e., pass a scalar
that is part of an array to effectively pass an offset into that
array, since Fortran passes by reference). So this might be a hack,
but it's a commonly-accepted hack.
Reviewed by Craig Rasmussen.
cmr=v1.7.3:subject=Fix [I]Alltoallw mpi_f08 wrapper functions
This commit was SVN r29298.
arrays.
The MPI 3.0 standard added const to all in buffers in the C bindings. This
commit adds the const keyword and in most cases casts const away. We will
eventually should go through and update the various interfaces (coll, pml,
io, etc) to take the const keyword. The group, comm, win, and datatype
interfaces have been updated with const.
cmr=v1.7.4:ticket=trac:3785:reviewer=jsquyres
This commit was SVN r29266.
The following Trac tickets were found above:
Ticket 3785 --> https://svn.open-mpi.org/trac/ompi/ticket/3785
Blocking versions are simple linear algorithms implemented in coll/basic. Non-
blocking versions are from libnbc 1.1.1. All algorithms have been tested with
simple test cases.
cmr=v1.7.4:reviewer=jsquyres
This commit was SVN r29265.
Includes all MPI functions supported by Open MPI, including MPI-3
functions (as of about 2 weeks ago). Many changes compared to the
prior generation of Java bindings; not much is left from the prior
generation, actually. The changes include (but are not limited to):
* Add support for more than just a subset of MPI-1 functions
* Use typical Java case for symbol names
* Support Java Direct buffers (giving darn-near "native C"
performance)
* Support "type struct" better than the prior generation
* Make more of an effort for the Java bindings to be a thin layer
over the back-end C bindings
* ...and more
A proper README with more information about what is supported, how to
use these bindings, etc. will be committed shortly.
This commit was SVN r29263.
The intercomm "merge" function can create a linkage between procs that was not reflected anywhere in a modex, and so at least some of the procs in the resulting communicator don't know how to talk to some of the new communicator's peers.
For example, consider the case where:
1. parent job A comm_spawns a process (job B) - these processes exchange modex and can communicate
2. parent job A now comm_spawns another process (job C) - again, these can communicate, but the proc in C knows nothing of B
3. do an intercomm merge across the communicators created by the two comm_spawns. This puts B and C into the same communicator, but they know nothing about how to talk to each other as they were not involved in any exchange of contact info. Hence, collectives on that communicator now fail.
This fix adds an API to the ompi/dpm framework that (a) exchanges the modex info across the procs in the merge to ensure all procs know how to communicate, and (b) calls add_procs to give the btl's a chance to select transports to any new procs.
cmr:v1.7.3:reviewer=jsquyres
This commit was SVN r29166.
The following Trac tickets were found above:
Ticket 2904 --> https://svn.open-mpi.org/trac/ompi/ticket/2904
is enabled and fix a bug in the handling of watermark performance
variables.
cmr=v1.7.3:ticket=trac:3725:reviewer=jsquyres
This commit was SVN r29068.
The following Trac tickets were found above:
Ticket 3725 --> https://svn.open-mpi.org/trac/ompi/ticket/3725
