1
1

8284 Коммитов

Автор SHA1 Сообщение Дата
Nathaniel Graham
8f4c16da27 Java null handle bugfix
A helper method in Request.java could cause a crash
if the request array that was passed contained nulls.

Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
2015-08-10 15:54:36 -06:00
Nathan Hjelm
624a4a0f82 Merge pull request #699 from hjelmn/libnbc_fixes
coll/libnbc: rewrite parts of libnbc
2015-08-10 14:51:42 -06:00
Jeff Squyres
87db836800 Merge pull request #788 from yburette/topic/deprioritize_some_providers
mtl/ofi: Deprioritize some OFI providers.
2015-08-10 14:45:59 -04:00
Nathan Hjelm
d42e0968b1 coll/libnbc: rewrite parts of libnbc
This commit rewrites parts of libnbc to fix issues identified by
coverity and myself. The changes are as follows:

 - libnbc function would return invalid error codes (internal to
   libnbc) to the mpi layer. These codes names are of the form
   NBC_. They do not match up with the error codes expected by the mpi
   layer. I purged the use of all these error codes with the exception
   of NBC_OK and NBC_CONTINUE in progress. These codes are used to
   identify when a request handle is complete.

 - Handles and schedules were leaked by all collective routines on
   error. A new routine was added to return a collective handle
   (NBC_Return_handle).

 - Temporary buffers containting in/out neighbors for neighborhood
   collectives were always leaked.

 - Neigborhood collectives contained code to handle MPI_IN_PLACE which
   is never a valid input for the send or receive buffer. Stipped this
   code out.

 - Files were inconsistently named. Most are nbc_isomething.c but one
   was named coll_libnbc_ireduce_scatter_block.c.

 - Made the NBC_Schedule "structure" and object so it can be
   retained/released. This may enable the use of schedule caching at a
   later time. More testing will be needed to ensure the caching code
   works. If it doesn't the code should be stripped out completely.

 - Added code to simply common case of scheduling send/recv +
   barrier.

 - Code cleanup for readability.

The code now passes the clang static analyzer.

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-08-10 11:53:25 -06:00
George Bosilca
0a91d7af4d Fix issues identified by Coverity. 2015-08-08 16:41:30 -04:00
Howard Pritchard
acf64b20c7 Merge pull request #786 from nrgraham23/add_implements_cloneable
Add explicit implementation of Cloneable
2015-08-08 13:02:43 -06:00
Jeff Squyres
bd5bf4a224 Merge pull request #781 from hppritcha/topic/suppress_picky_warning
mca/topo: suppress picky warning
2015-08-08 06:14:52 -04:00
yohann
88038b5261 mtl/ofi: Deprioritize some OFI providers.
Some OFI providers such as "sockets" are used for debugging
purposes mostly. For these providers, other components usually
offer better performance -- e.g. for sockets, the BTL/TCP would
be a better choice.
Thus, we chose to ignore some providers unless explicitly asked
by the user on the command line:

e.g. --mca mtl_ofi_provider sockets
2015-08-07 16:09:51 -07:00
Edgar Gabriel
d719497f82 Performance tuning: increase the priority of the sm sharedfp component to ensure that it is selected if it can run. 2015-08-07 16:32:53 -05:00
Edgar Gabriel
9e29edf15c remove a erroneous paranthesis which prevents the compilation of the lustre adio 2015-08-07 15:22:41 -05:00
Edgar Gabriel
1293d9c69b free memory correctly in case of an error. Fixes CID 131540 and CID 1315419 2015-08-07 13:30:50 -05:00
Nathaniel Graham
8fcc317a57 Add explicit implementation of Cloneable
Added Cloneable to the implemented interface list as per
Coverity suggestion.  The required methods were already
implemented, but it was not explicitly stated.  This is
an intent revealing change.

Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
2015-08-07 12:16:06 -06:00
Edgar Gabriel
0aa3049bfc Performance tuning: change the default behavior of ompio to *not* segment individual read/write operations.
In most cases, performance seems to be better if not segmented.
2015-08-07 13:06:39 -05:00
Edgar Gabriel
db5af26de7 Performance tuning. make sure we catch if the user wants to set the default fileview and replace it with our optimized default file view. Otherwise, performance will suffer. file_get_view should still return the correct filetype, not our optimized default file view. This is the correct version compared to ffa67b96933acafb3cfacf39a074d3dc1fe134ae, which unfortunately broke
some test cases in mpi_test_suite. Thanks for @ggouaillardet for reporting this!
2015-08-07 12:49:58 -05:00
Edgar Gabriel
6f6c01ee8d free the datatypes that were created using type_dup during file_set_view 2015-08-07 11:50:25 -05:00
Edgar Gabriel
1ae4f8c7e6 Revert "Performance tuning. make sure we catch if the user wants to set the default fileview and replace it with"
This reverts commit ffa67b96933acafb3cfacf39a074d3dc1fe134ae.
2015-08-07 09:53:07 -05:00
Gilles Gouaillardet
907c095f66 Merge pull request #779 from edgargabriel/topic/fcoll_fixes
Topic/fcoll fixes
2015-08-07 09:14:31 +09:00
Howard Pritchard
10aac8037f mca/topo: suppress picky warning
When configured with --enable-picky

topo_base_lazy_init.c compiles with a warning:

  CC       base/topo_base_lazy_init.lo
base/topo_base_lazy_init.c:46:67: warning: implicit conversion from enumeration type 'enum mca_base_register_flag_t' to different enumeration type 'mca_base_open_flag_t' (aka 'enum mca_base_open_flag_t') [-Wenum-conversion]
        err = mca_base_framework_open (&ompi_topo_base_framework, MCA_BASE_REGISTER_DEFAULT);

This commit fixes this implicit conversion problem.

Signed-off-by: Howard Pritchard <howardp@lanl.gov>
2015-08-05 16:11:04 -06:00
Rolf vandeVaart
cb84a85d17 Build always and fix return value 2015-08-05 17:23:55 -04:00
Edgar Gabriel
16d4171f6b the individual component should call internal ompio functions directly. The reason is that otherwise
the redirection to the ompi_file_t structure (and back to the ompio internal structure) is ambiguise and wrong
for the shared file pointer scenario.
2015-08-05 14:31:11 -05:00
Edgar Gabriel
02a4eb2f13 add the ompi_file_t pointer correctly on the ompio file handle for the sm and individual component. 2015-08-05 14:28:27 -05:00
Jeff Squyres
a36d7e6026 treematch: __FUNCTION__ -> __func__ fixes 2015-08-05 05:39:38 -07:00
Jeff Squyres
a0ebbee6ef libnbc: __FUNCTION__ -> __func__ fixes 2015-08-05 05:27:23 -07:00
Gilles Gouaillardet
3d1780f1a2 sharedfp: set f_fh when opening a shared file 2015-08-05 15:07:21 +09:00
Howard Pritchard
36d7855280 Merge pull request #763 from nrgraham23/status_x_java_bindings
Status x java bindings
2015-08-03 09:26:16 -06:00
Gilles Gouaillardet
2fa8f4d53a Revert "fortran: optimize testall and waitall when MPI_STATUSES_IGNORE is used"
Optimization was incorrect, so revert this commit.

This reverts commit 83375bcc5c69121ebad7c1df67211ac08729c570.
2015-08-03 08:45:12 +09:00
Jeff Squyres
047eccef8d Merge pull request #725 from bosilca/treematch
Add a new topo module: Treematch
2015-07-31 15:17:54 -04:00
Howard Pritchard
8649a9f6ef Merge pull request #757 from roblatham00/lustre-excl-open-fix
hint processing should not open files
2015-07-31 12:16:14 -06:00
Howard Pritchard
f18988c06f Merge pull request #764 from nrgraham23/Datatype.java_comment_fixes
Commenting fixes for Datatype.java
2015-07-31 12:03:04 -06:00
rhc54
a9b10cfbf0 Merge pull request #761 from jithinjosepkl/master
Fix warnings in direct (pml-cm,mtl-ofi) build
2015-07-31 09:15:30 -07:00
Edgar Gabriel
ffa67b9693 Performance tuning. make sure we catch if the user wants to set the default fileview and replace it with
our optimized default file view. Otherwise, performance will suffer. file_get_view should still return the correct filetype, not our optimized default file view
2015-07-30 19:15:00 -05:00
Edgar Gabriel
93a303ba89 Performance tuning: make sure the individual component is selected for 1 and 2 process communicators (important for some benchmarks) 2015-07-30 17:31:16 -05:00
Edgar Gabriel
9b2a7e41f0 make sure the final number of aggregators is recorded correctly when not using
our aggregator selection logic.
2015-07-30 17:24:01 -05:00
Nathaniel Graham
57b95fff2e Commenting fixes for Datatype.java
Some of the @code tags were incorrect.

Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
2015-07-30 15:17:55 -06:00
Nathaniel Graham
17c606b35c White Space Fixes
Github revealed some wierd spacing issues.

Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
2015-07-30 15:07:19 -06:00
Nathaniel Graham
2fecb06059 Status X Functons
Includes java bindings for MPI_GET_ELEMENTS_X and
MPI_STATUS_SET_ELEMENTS_X.  This PR also adds the
Count object which represents MPI_Count.

Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
2015-07-30 15:00:13 -06:00
Howard Pritchard
ac4197fb1b Merge pull request #760 from nrgraham23/request_get_status_java
Java binding for MPI_REQUEST_GET_STATUS
2015-07-30 13:57:06 -06:00
Rob Latham
6e9cbe397f hint processing should not open files
move opening of files from hint processing and into open routines.

This is MPICH commit 92f1c69f0de8 and 22a77dceda11

see https://trac.mpich.org/projects/mpich/ticket/2261
Ref: https://github.com/open-mpi/ompi/issues/158

Signed-off-by: Pavan Balaji <balaji@anl.gov>
2015-07-30 12:25:20 -05:00
Nysal Jan K.A
5a7bd898f9 Fix an invalid memory access in mrecv & imrecv
After the call to PML mrecv/imrecv, the message handle
is set to MPI_MESSAGE_NULL. Use the cached communicator
while invoking the error handler.
2015-07-30 19:52:40 +05:30
Jithin Jose
bc4e8b7e73 Fix warnings in direct (pml-cm,mtl-ofi) build
Signed-off-by: Jithin Jose <jithin.jose@intel.com>
2015-07-29 15:49:37 -07:00
Howard Pritchard
ea6f5b31fd Merge pull request #749 from nrgraham23/additional_comm_java_bindings
Additional java bindings for the Comm class
2015-07-29 16:17:54 -06:00
Edgar Gabriel
477083bca3 the memory chunk that has to be allocated for the llapi_get_stripe function seems to have changed compared to earlier version. This implementation now follows the code snipplet from the man pages. 2015-07-29 17:13:55 -05:00
Edgar Gabriel
217dcca853 - the memory chunk that has to be allocated for the llapi_get_stripe function seems to have changed compared to earlier version. This implementation now follows the code snipplet from the man pages.
- implementation of file_get_size and set_size
2015-07-29 17:10:39 -05:00
yohann
6eba52a121 mtl/ofi: add missing return. 2015-07-29 14:14:34 -07:00
Nathaniel Graham
9b5786d954 Java binding for MPI_REQUEST_GET_STATUS
This adds the java binding for MPI_REQUEST_GET_STATUS.

Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
2015-07-29 12:04:46 -06:00
Howard Pritchard
569764cd98 Merge pull request #759 from nrgraham23/status_java_bindings
Java bindings for Status methods
2015-07-29 10:36:56 -06:00
Nathaniel Graham
efe69c89a7 Java bindings for Status methods
Includes java bindings for the MPI_STATUS_SET_ELEMENTS and
MPI_STATUS_SET_CANCELLED.

Signed-off-by: Nathaniel Graham <ngraham@lanl.gov>
2015-07-29 09:47:03 -06:00
Ralph Castain
023936e84b Silence coverity warnings 2015-07-29 07:28:08 -07:00
Gilles Gouaillardet
83375bcc5c fortran: optimize testall and waitall when MPI_STATUSES_IGNORE is used 2015-07-29 10:00:27 +09:00
Edgar Gabriel
a3327fe299 Merge pull request #756 from edgargabriel/pr/nb-sharedfp-splitcoll2
- make the split collective shared file pointer operations work
2015-07-28 19:53:27 -05:00