ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
14 239 коммитов 3 Ветки 0 Теги 130 MiB
84ecb6a81a
Граф коммитов

14239 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Ralph Castain
3905d38bc5 No need for a separate tarball script - add -no-ompi support to the main tarball script and get rid of the orte_tarball ones 
This commit was SVN r22385.
 2010-01-09 01:06:52 +00:00
Ralph Castain
add84178ef Fix a silly typo that prevented tcp multicast messages from being delivered 
This commit was SVN r22384.
 2010-01-08 20:30:27 +00:00
Jeff Squyres
40a8846b75 Disable the --enable-openib-ibcm switch. IBCM support is broken, so there's no point in even offering this config switch; it just confuses people. Closes trac:2158. 
This commit was SVN r22383.

The following Trac tickets were found above:
  Ticket 2158 --> https://svn.open-mpi.org/trac/ompi/ticket/2158
 2010-01-07 18:21:41 +00:00
Jeff Squyres
8f824177cd Closes trac:2158. 
Special-case the before MPI_INIT / after MPI_FINALIZE error messages
so that they can be a bit more clear than the general "an error
occurred" messages that are displayed in the middle of MPI jobs.

This is not really a "bug fix", but it is helpful for usability.  I
leave it up to the v1.4 RM's to decide if they want it for the 1.4
series or not.

This commit was SVN r22382.

The following Trac tickets were found above:
  Ticket 2158 --> https://svn.open-mpi.org/trac/ompi/ticket/2158
 2010-01-07 18:16:39 +00:00
Brian Barrett
86d8356b13 Updates to allow OMPI to build on Cray XT platforms running Catamount 
This commit was SVN r22381.
 2010-01-07 18:14:03 +00:00
Jeff Squyres
e96032dec9 Fix a type (otherwise we get a compiler warning). 
This commit was SVN r22380.
 2010-01-07 17:39:18 +00:00
Edgar Gabriel
5c6384e771 clean up the comm_cid code by removing everything related to the block_cid 
algorithm. This makes it much easier to read again.

This commit was SVN r22379.
 2010-01-07 16:26:30 +00:00
Ralph Castain
09763ec711 Since we modified ORTE to declare that any process that terminates after calling "init" while at least one other process has not yet called "init" is an error, we have to ensure that non-MPI ORTE apps (i.e., apps that call orte_init but not mpi_init) include a barrier in orte_init. Otherwise, fast ORTE apps almost always wind up triggering the "abnormal termination" condition. 
The barrier is protected with a test to ensure that MPI apps don't execute it and wind up doing two barriers during their init.

This commit was SVN r22378.
 2010-01-07 06:58:01 +00:00
Ralph Castain
ef1bfaa823 Add the ability to track how many times a process has been restarted, and to communicate that value to a process when it is restarted in case it needs to take action when it is restarted as opposed to being started for the first time. 
This commit was SVN r22377.
 2010-01-07 01:19:44 +00:00
Ethan Mallove
f1f285c575 If CR is disabled, do not create ompi-checkpoint/restart symlinks and CR man pages. 
This commit was SVN r22373.
 2010-01-06 16:56:54 +00:00
Josh Hursey
9adffe709e Add some news bullets for the 3 C/R related fixed that were recently moved to v1.4 
This commit was SVN r22371.
 2010-01-06 14:35:44 +00:00
Jeff Squyres
f3120f70af Add some NEWS bullets for what has changed in 1.4.1 
This commit was SVN r22370.
 2010-01-06 13:44:29 +00:00
Ralph Castain
c54db934d2 Okay, smarty pants - track Jeff's tarball logic changes 
This commit was SVN r22369.
 2010-01-06 01:50:22 +00:00
Jeff Squyres
3796e530d5 Add bullet about PLPA version update. 
This commit was SVN r22368.
 2010-01-06 00:47:31 +00:00
Jeff Squyres
dbb29663e8 Update the embedded PLPA version to v1.3.2. Since this is a 3rd 
party/"vendor" import, the changes are actually far smaller than the
size of this changeset implies.  Here's a list of the changes:

 * Update the AMD license header in plpa_map.c to be less restrictive
   (see https://svn.open-mpi.org/trac/plpa/changeset/262 for details)
   -- '''this is the most/only important change of this update.'''  No
   code is changed by this; only removing a clase from a license
   header in plpa_map.c.
 * Changes to the generated {{{configure}}}, {{{config.guess}}}, and
   {{{config.sub}}} scripts (which aren't used by OMPI).
 * soname version tracking changes (which also aren't used by OMPI;
   they're only used when PLPA is built/installed in "standalone"
   mode).
 * Update the "get version" m4 (which was stolen from OMPI's m4 to
   begin with, and is only used during OMPI's autogen.sh step).
 * Update various PLPA version numbers to 1.3.2.
 * Bug fix in plpa-taskset (which is not built in the OMPI PLPA build).

This commit was SVN r22367.
 2010-01-06 00:44:14 +00:00
Jeff Squyres
6105c71561 r22365 wasn't quite right -- Libtool 2.2.6b ''does'' report the "b" in 
the --version output (ugh!).  So fix it so that if there are letters
in the release number, don't use -lt and -gt to compare; just print
"we found the wrong version" (don't try to determine if it's higher or
lower).

This commit fixes ompi's make_dist_tarball -- I'll let Ralph adapt for
the ORTE tarball script.

This commit was SVN r22366.

The following SVN revision numbers were found above:
  r22365 --> open-mpi/ompi@b4a77591d2
 2010-01-06 00:10:09 +00:00
Ralph Castain
b4a77591d2 You cannot check for a "b" sub-release as the tests are looking for integers (doing < and > comparisons). Indeed, libtool doesn't report the "b" when doing --version, probably just for that reason. 
This commit was SVN r22365.
 2010-01-05 23:40:10 +00:00
Ralph Castain
a12de9d1e8 Oh, the pain one little word can make...sigh. 
This commit was SVN r22364.
 2010-01-05 23:29:56 +00:00
Jeff Squyres
715d866da6 Minor fixes: 
* Fix typo in echo message
 * Only traverse into orte/ and ompi/ if they exist (i.e., properly
   handle --no-orte and --no-ompi tarballs).  Note that this was only
   a minor error -- before, they just output error messages and
   (correctly) kept going.  This fix just removes the error messages.

This commit was SVN r22353.
 2010-01-05 15:11:41 +00:00
Ralph Castain
5faf857840 Add a new tag for pnp/multicast send of direct messages 
This commit was SVN r22352.
 2009-12-31 20:34:58 +00:00
Ralph Castain
b3a58f8b83 Pass the correct address when packing iovec bytes for multicast. 
Thanks to Rick Payne for the correction.

This commit was SVN r22351.
 2009-12-30 20:59:31 +00:00
Ralph Castain
bb7aa9797f Not sure why the nightly tarball had a problem as this wasn't changed, but comment out the orte wrapper compiler man pages for now 
This commit was SVN r22350.
 2009-12-30 02:52:29 +00:00
Ralph Castain
89a6131032 Check the return status code on all dss operations within the rmcast modules 
This commit was SVN r22349.
 2009-12-30 01:45:31 +00:00
Ralph Castain
fad1ba15b0 Move the test for case-sensitive file system from ompi to opal so that all layers can have that knowledge. 
Use that for the orte wrapper compilers

This commit was SVN r22348.
 2009-12-29 23:26:45 +00:00
Shiqing Fan
c37308b8eb Remove the deleted windows file from the tarball. 
This commit was SVN r22347.
 2009-12-29 16:11:32 +00:00
Shiqing Fan
b8555448b5 Remove the unnecessary/duplicated unistd.h. 
This commit was SVN r22346.
 2009-12-28 16:22:16 +00:00
Shiqing Fan
e6c0133d08 Add a definition for CMake to disable KNEM on Windows. 
This commit was SVN r22345.
 2009-12-28 16:13:41 +00:00
Shiqing Fan
d0f85beaf3 Correctly include those header files. 
This commit was SVN r22344.
 2009-12-28 16:13:06 +00:00
Shiqing Fan
90e3092ce5 Fix a type cast. 
This commit was SVN r22343.
 2009-12-28 16:12:46 +00:00
Shiqing Fan
a2d00d4ab8 Exclude a pml component that is not necessary for Windows. 
This commit was SVN r22342.
 2009-12-28 16:12:28 +00:00
Ralph Castain
d6003e3369 Update the mpirun man page to include info on the "!" option to the xterm cmd line option that holds the xterm window open after process termination so the user can see the process' output. 
This commit was SVN r22341.
 2009-12-26 16:01:03 +00:00
Ralph Castain
50074f0770 Remove unused (and uninitialized) variable 
This commit was SVN r22340.
 2009-12-24 01:36:47 +00:00
Ralph Castain
7edb80a0c5 Further update cisco platform files 
This commit was SVN r22339.
 2009-12-23 16:58:00 +00:00
Ralph Castain
ea8b2dc752 Update the Cisco platform files. Create a make_tarball variant for creating orte-level tarballs 
This commit was SVN r22338.
 2009-12-23 16:44:57 +00:00
Ralph Castain
170da86ae5 Add a missing file to the tarball, and clean it up a little 
This commit was SVN r22337.
 2009-12-22 20:38:39 +00:00
George Bosilca
e127b20038 Correct a type in the name of the help string. 
This commit was SVN r22336.
 2009-12-21 19:13:25 +00:00
Jeff Squyres
c542048dc9 Reword George's bullet about the shared memory fix so that normal 
people will understand it.  :-) Also moved it to the v1.4.1 section.

This commit was SVN r22334.
 2009-12-17 21:20:51 +00:00
Ralph Castain
aaf1119f40 Garrr...ensure we accurately know when to update the contact info so we don't do it incorrectly as procs terminate, thus causing the system to think that perfectly good apps are incorrectly terminating. 
Thanks to George for pointing out the problem

This commit was SVN r22332.
 2009-12-17 20:40:21 +00:00
Ralph Castain
db2cbd3166 Okay, okay - do it at destruct time too. 
This commit was SVN r22331.
 2009-12-17 20:08:49 +00:00
Ralph Castain
a56e09c874 Per suggestion from Josh, init the sender field of the msg_packet object to INVALID 
This commit was SVN r22330.
 2009-12-17 20:03:35 +00:00
Ralph Castain
8ab962411c Detect the scenario where one or more procs fail to call orte/ompi_init while others in the job do. This scenario can cause the job to hang as MPI_Init contains a barrier operation that will not complete. Although ORTE does not contain such a barrier, it still will be considered as an error scenario so that we can detect the MPI case - otherwise, ORTE has no knowledge of OMPI and wouldn't know how to differentiate the use-cases. 
Take advantage of the changes to update the routed_base_receive code to avoid message overlap.

This commit was SVN r22329.
 2009-12-17 19:39:53 +00:00
Ralph Castain
06d1f2cfe2 Add some new tests to the ORTE collection 
This commit was SVN r22328.
 2009-12-17 19:30:57 +00:00
Josh Hursey
313acba4ce Move the mca_base_is_component_required() functionality to mca/base per suggestion so that it can be reused in other components. 
This commit was SVN r22327.
 2009-12-17 15:12:26 +00:00
Jeff Squyres
e8b4507c51 Add the possibility for 3rd party projects to drop in .m4 files that AC_DEFUN ompi_CONFIG_LOCAL, orte_CONFIG_LOCAL, and/or opal_CONFIG_LOCAL in any of the <project>/config directories. If these macros are defined in <project>/config/<foo>.m4 files, autogen.sh will pick up their definitions and the top-level configure script will invoke them. This allows 3rd parties to add more configury to Open MPI (or ORTE or OPAL) without needing to patch configure. 
This commit was SVN r22326.
 2009-12-16 23:32:47 +00:00
George Bosilca
5dac5ee19f Don't forget to update the NEWS file regarding the cmpxchg changes. 
This commit was SVN r22325.
 2009-12-16 22:39:51 +00:00
George Bosilca
7ba371cd92 Correct the atomics on x86 and x86_64. Thanks to Iain for the catch, 
to Eugene, Jeff, and Briand for the help. This patch is supposed to
fix several outstanding issues, notably the one on tickets #2043.

This commit was SVN r22324.
 2009-12-16 22:34:56 +00:00
Josh Hursey
a418a7dc43 Make sure to look in not only the env var, but also {{{orte_routed_base_components}}} to confirm that this is the only component available, and intended for selection. 
This commit was SVN r22323.
 2009-12-16 20:17:26 +00:00
Josh Hursey
646f90a90a Small fix for a egde case 
This commit was SVN r22322.
 2009-12-16 18:06:05 +00:00
Vasily Filipov
897b7c0aa8 Fix orte_show_help message type error. 
This commit was SVN r22321.
 2009-12-16 14:11:43 +00:00
Vasily Filipov
e73274f9a9 Disabling SRQ limit event for devices that doesn't support this feature. 
This commit was SVN r22320.
 2009-12-16 14:05:35 +00:00