Ralph Castain
76b6ae3b29
Fix the ziatest to report correct times
...
This commit was SVN r21059.
2009-04-23 01:12:56 +00:00
Ralph Castain
3c3c306ee4
Simplify test
...
This commit was SVN r21058.
2009-04-22 23:03:04 +00:00
Jeff Squyres
9b5e194d9b
Fix opal_basename. Wow; how long has that been broken?
...
This commit was SVN r21057.
2009-04-22 20:48:24 +00:00
Shiqing Fan
0037f55424
Correctly set the compile flags of 'mpicc' for static version.
...
This commit was SVN r21055.
2009-04-22 13:17:25 +00:00
Ralph Castain
d7a8b3038f
Ensure new files are included in tarball
...
This commit was SVN r21052.
2009-04-21 20:08:54 +00:00
Ralph Castain
3069c9dc40
Update LANL platform files
...
This commit was SVN r21051.
2009-04-21 20:07:43 +00:00
Ethan Mallove
0f4c18472c
Remove unused {{{malloc.h}}} include.
...
(see http://www.open-mpi.org/community/lists/devel/2009/04/5845.php )
This commit was SVN r21049.
2009-04-21 17:35:58 +00:00
Jeff Squyres
26d6f37d42
Add bullet about openib infinite loop fix.
...
This commit was SVN r21048.
2009-04-21 17:00:21 +00:00
Jeff Squyres
9d94fa2308
Fixes trac:1890: we weren't checking the return status of
...
_endpoint_post_send(), which could result in an infinite loop (see the
comment in the code).
This is part one of a proper fix; it's suitable for the v1.3 tree and
for an immediate release. Pasha and I plan to spend a little more
time and clean up this stuff properly, but it does not need to be
included in v1.3.2.
This commit was SVN r21047.
The following Trac tickets were found above:
Ticket 1890 --> https://svn.open-mpi.org/trac/ompi/ticket/1890
2009-04-21 16:57:17 +00:00
Nysal Jan
5353236a53
Reduce the size of FIN header by 8 bytes. This is done by rearranging the fields to reduce the amount of compiler padding
...
This commit was SVN r21046.
2009-04-21 14:41:51 +00:00
Jeff Squyres
c4b307d57e
Fix an incorrect comment.
...
This commit was SVN r21045.
2009-04-21 13:38:43 +00:00
Jeff Squyres
6f78420900
Correctly check for the case where we didn't find the mpool that we
...
were looking for. This makes the openib btl fail a little more
gracefully (for example) if you specify a bogus value to
btl_openib_mpool.
Thanks to Roberto Ammendola for identifying the exact issue.
This commit was SVN r21044.
2009-04-21 12:40:50 +00:00
Rainer Keller
732c80d9bc
- Update ORNL's machine specific files
...
This commit was SVN r21043.
2009-04-20 20:16:53 +00:00
Brian Barrett
2ca0b7fe44
remove some checks which are not needed after the recent ptmalloc2 changes
...
This commit was SVN r21042.
2009-04-19 18:17:05 +00:00
Jeff Squyres
e90ecb6020
Fix a compiler warning. Put in a good comment explaining why it is
...
declared the way it is. Sigh.
This commit was SVN r21040.
2009-04-17 21:59:31 +00:00
Eugene Loh
2b8b48e46d
Add a NEWS item for autosizing of the shared-memory area.
...
This commit was SVN r21039.
2009-04-17 21:02:12 +00:00
Ralph Castain
65f0a1759d
Relentless pursuit of parameters...
...
This commit was SVN r21034.
2009-04-16 18:54:19 +00:00
Ralph Castain
afe1950da5
Make the error message clearer - this error only is used when two buffer types don't match, thus preventing an operation from being executed
...
This commit was SVN r21033.
2009-04-16 16:23:28 +00:00
Ralph Castain
543287e599
Add news items on checksum, openib padding options
...
This commit was SVN r21032.
2009-04-16 15:36:28 +00:00
Jeff Squyres
25249c9843
Roll back r20926, r20941, r20950: Iain's changes from last week.
...
This has turned into an MPI spec interpretation issue. :-(
Open MPI has intrepreted the spec one way for the past several years;
these commits reflect a different interpretation that changes how we
treat the EXTRA_STATE parameter to the Fortran attribute copy and
delete callbacks. This new way breaks our internal copy of the Intel
Fortran attribute tests. So after talking with Terry/Sun, we're going
to back out these changes (both here and on the v1.3 branch) until we
get further clarification from the Forum.
This commit was SVN r21028.
The following SVN revision numbers were found above:
r20926 --> open-mpi/ompi@0a24eadaad
r20941 --> open-mpi/ompi@045b0e8871
r20950 --> open-mpi/ompi@73af921c22
2009-04-16 14:29:32 +00:00
Ralph Castain
1f7281957f
Need this one too...
...
This commit was SVN r21027.
2009-04-16 02:23:57 +00:00
Ralph Castain
4f90b678d1
Crud - this didn't get committed due to too many interruptions this afternoon. My apologies for crashing the nightly tarball.
...
This commit was SVN r21026.
2009-04-16 02:23:33 +00:00
Jeff Squyres
35fc9fedd2
MTT is your friend: Cisco tests --enable-static --disable-shared, but
...
we had already tested this scenario manually to know that it seemed to
be working. What we ''didn't'' test was --enable-static
--disable-shared --disable-dlopen -- but my MTT '''did.''' Yay!
This commit fixes that scenario. Essentially we need to call a dummy
function in hooks.c to ensure that the linker pulls in all those
symbols into the final executable (and therefore pulls in the
malloc_initialize_hook, etc.). Thanks for the heads-up from Brian in
fixing this one!
This commit was SVN r21022.
2009-04-15 19:09:10 +00:00
Terry Dontje
20faf6a1a9
special case xldscope for sun cc compilers so icc doesn't falsely think it
...
should use the xldscop option.
This commit was SVN r21021.
2009-04-15 18:13:27 +00:00
Ralph Castain
201c2323be
Update LANL platform files
...
This commit was SVN r21019.
2009-04-15 18:02:19 +00:00
Jeff Squyres
93c36bcc0f
Add bullet about LSF fix (the problem does not exist on the trunk;
...
must be some transcription error or we had already fixed it on the
trunk and forgot to move it over to 1.3).
This commit was SVN r21017.
2009-04-15 17:46:46 +00:00
Jeff Squyres
61b2f0b9ea
Fix typo preventing compilation (!)
...
This commit was SVN r21016.
2009-04-15 16:50:41 +00:00
Ralph Castain
2b0b9dd227
Sync to change in a tmp branch
...
This commit was SVN r21015.
2009-04-15 13:09:51 +00:00
Shiqing Fan
e8f5ad04d4
Don't collect files recursively.
...
This commit was SVN r21013.
2009-04-15 09:47:14 +00:00
Ralph Castain
96d1ff506e
Be silent when the lifeline is lost - we don't want to hear about it
...
This commit was SVN r21011.
2009-04-15 01:34:04 +00:00
Ralph Castain
e52dc0bb9e
Search for the perfect platform file...
...
This commit was SVN r21010.
2009-04-15 01:33:41 +00:00
Jeff Squyres
8287943ce1
Various updates for the 1.3.2 release (and a few others).
...
This commit was SVN r21007.
2009-04-14 20:58:59 +00:00
Jeff Squyres
c1206fac4b
Use a better word. :-)
...
This commit was SVN r21006.
2009-04-14 20:37:06 +00:00
Jeff Squyres
df2ace7a55
Add a bunch of 1.3.2 bullets.
...
This commit was SVN r21005.
2009-04-14 20:34:19 +00:00
Ralph Castain
4f4af6e8cb
Update LANL files again in the endless search through the weeds of the OMPI configure system.
...
I no longer wonder why people say OMPI is so hard to use. :-/
This commit was SVN r21004.
2009-04-14 20:11:17 +00:00
Ralph Castain
8b0a470543
Continue work to cleanup user options for slave launch
...
This commit was SVN r21003.
2009-04-14 20:05:51 +00:00
Ralph Castain
46d6c6d516
Sync the csum module with the recent ob1 changes
...
This commit was SVN r21002.
2009-04-14 18:40:54 +00:00
Nysal Jan
221447ef17
Fix checksum mismatch on Big-endian systems when heterogeneous mode is enabled
...
This commit was SVN r21001.
2009-04-14 17:21:38 +00:00
Ralph Castain
9fd834268c
Ensure we exit with a non-zero status if terminated by user signal
...
This commit was SVN r20991.
2009-04-14 15:58:54 +00:00
Ralph Castain
a952dca062
Fix a bug where we created the correct path to the file, but didn't use it
...
This commit was SVN r20990.
2009-04-14 14:17:43 +00:00
Ralph Castain
9c39a3edd7
Enable the passing of MCA params to dynamically spawned jobs. This creates a new info_key "ompi_param" that allows a user to specify MCA params for a dynamically spawned job.
...
We currently apply all of the MCA params in the parent job to the child. This commit allows a user to specify additional params for the child job, and to override any pre-existing params with the new value so they can better control behavior of the child job.
This commit was SVN r20989.
2009-04-14 14:15:49 +00:00
Shiqing Fan
339948928d
Only include unistd.h, if we have it.
...
This commit was SVN r20988.
2009-04-14 13:39:06 +00:00
Shiqing Fan
0ea6d48320
Add a missed .windows file for timer component, which should be built always statically.
...
This commit was SVN r20987.
2009-04-14 12:19:21 +00:00
Nysal Jan
697f1837f4
Move fix for ticket #1875 to csum PML
...
This commit was SVN r20986.
2009-04-14 10:44:29 +00:00
George Bosilca
05ee4c280e
Mismatch between the reported subversion and the one in the mpi.h.
...
Thanks to Rob Egan for the report.
This commit was SVN r20985.
2009-04-14 05:29:07 +00:00
Jeff Squyres
778c8c86d2
Make mpool fail-to-unregister-freed-memory errors be fatal. Try to
...
make that routine a bit more safe, too (ensure to not call malloc and
friends if from_alloc==true).
This commit was SVN r20984.
2009-04-14 00:54:20 +00:00
George Bosilca
b5deb228f3
Allow the BTL to release the descriptor. In fact the only thing the PML
...
needs is to be involved in the RMA completion process, which is insured
by the MCA_BTL_DES_SEND_ALWAYS_CALLBACK flag. Fixes trac:1875.
This commit was SVN r20983.
The following Trac tickets were found above:
Ticket 1875 --> https://svn.open-mpi.org/trac/ompi/ticket/1875
2009-04-13 23:41:50 +00:00
Jeff Squyres
8de80e9297
mca_mpool_base_mem_cb_array is no longer used anywhere in the code
...
base. Remove it.
This commit was SVN r20982.
2009-04-13 23:41:45 +00:00
Ralph Castain
9f7c605166
More cleanup of pointer array usage
...
This commit was SVN r20981.
2009-04-13 19:06:54 +00:00
Jeff Squyres
cd512599bf
Fix svn:ignore
...
This commit was SVN r20980.
2009-04-10 23:37:51 +00:00