Edgar Gabriel
ac3a01c39c
Silence coverty warnings 1321702, 1321701, 1321700, 72331, 72330, 72327, 72326, 72325,
2015-09-03 09:10:25 -05:00
rhc54
f4a3a86c86
Merge pull request #856 from rhc54/topic/pub
...
Bring the MPI_Publish functions online
2015-09-02 13:51:17 -07:00
Ralph Castain
a772b46c15
Bring the MPI_Publish and friends online
2015-09-02 12:04:07 -07:00
rhc54
5b49dc156f
Merge pull request #854 from rhc54/topic/pmix3
...
Sync to PMIx 1.1, sha- 51479b0
2015-09-01 14:55:41 -07:00
Edgar Gabriel
e95d01be97
Merge pull request #847 from edgargabriel/topic/fcoll-dynamic-cleanup
...
Topic/fcoll dynamic cleanup
2015-09-01 16:10:55 -05:00
Ralph Castain
95dbd70f44
Sync to PMIx 1.1, sha- 51479b0
2015-09-01 14:09:25 -07:00
Nathan Hjelm
83153aca94
Merge pull request #853 from hjelmn/osc_pt2pt_fixes
...
osc/pt2pt: remove outstanding lock only after lock/flush ack received
2015-09-01 13:55:21 -06:00
Rolf vandeVaart
30b1a6e003
Merge pull request #836 from rolfv/pr/fix-cuda-war
...
Add config code to check for need of workaround. Add runtime way to turn oiff just in case.
2015-09-01 15:05:29 -04:00
Nathan Hjelm
2a8cc5e637
osc/pt2pt: remove outstanding lock only after lock/flush ack received
...
fixes #840
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-09-01 10:54:47 -06:00
Nathan Hjelm
f926796e57
Merge pull request #828 from hjelmn/openib_thread_fix
...
openib thread fixes
2015-09-01 09:12:50 -06:00
Edgar Gabriel
82efc23e8d
iclean up indenting and tabs/space of fcoll_static_file_read/write_all
2015-09-01 09:39:33 -05:00
Edgar Gabriel
a1778406d6
Re-enable the contiguous buffer optimization to the read_all and the write_all routines.
...
After long debugging, I found last week the reason this optimization originally broke
some hdf5 tests. We now pass the hdf5 test suite with the optimization being actively used.
2015-09-01 09:29:07 -05:00
Edgar Gabriel
c2c44b11dc
Code cleanup for dynamic read_all and write_all
...
Specifically:
- reduce the number of realloc's and malloc's by moving
some arrays out of the cycle loop, if we know that there
size is not changing
- store the rank of the aggregator in a separate variable to avoid
continuous dereferencing
- change the wait_all logic in write_all to use a fix number of requests
(even if they are MPI_REQUEST_NULL)
- fix the timing to considere the two initial allgather and the one
allgatherv operation to be a part of it
- add more comments.
2015-09-01 09:29:07 -05:00
Edgar Gabriel
cf1e4e0d35
step 0: clean up indenting and space vs. tabs
2015-09-01 09:29:07 -05:00
rhc54
d8cb3fe705
Merge pull request #852 from rhc54/topic/pmix
...
Sync to PMIx tarball - includes:
2015-09-01 06:54:34 -07:00
Gilles Gouaillardet
6dfa996760
configury: fix a typo in opal/mca/pmix/pmix1xx/configure.m4
2015-09-01 14:59:07 +09:00
Ralph Castain
c1bbd7bc78
Sync to PMIx tarball - includes:
...
* update to configury to silence ident messages (thanks Gilles!)
* fix for warnings Jeff saw when get didn't find the requested data
* fix for Mac OSX operations
2015-08-31 21:51:02 -07:00
rhc54
2d3c6af8ad
Merge pull request #851 from rhc54/topic/copyfix
...
Only copy the value across if the "get" operation succeeded
2015-08-31 19:51:13 -07:00
Ralph Castain
ef69958e01
Only copy the value across if the "get" operation succeeded
2015-08-31 17:11:26 -07:00
Jeff Squyres
8558458bb9
usnic: adjust for new PMIX argument type
2015-08-31 14:55:58 -07:00
Rolf vandeVaart
54ab0d1a51
Add config code to check for need of workaround. Add runtime way to turn it off just in case
2015-08-31 17:18:47 -04:00
Nathan Hjelm
3c34f6f25c
Merge pull request #517 from hjelmn/class_fix
...
opal/class: enable use of opal classes after opal_class_finalize
2015-08-31 12:13:58 -07:00
Nathan Hjelm
faf06edb5b
Merge pull request #824 from hjelmn/opal_mutex_mod
...
opal/mutex: remove unnecessary ()s from OPAL_SCOPED_LOCK macro
2015-08-31 12:08:25 -07:00
rhc54
6e78e2c89b
Merge pull request #846 from rhc54/topic/pmix
...
Sync to PMIx tarball
2015-08-31 08:53:07 -07:00
Nathan Hjelm
2aab6ad90f
Merge pull request #827 from hjelmn/recursive_locks
...
Add support for recursive locks (revisited)
2015-08-31 07:52:23 -07:00
Ralph Castain
a3842af709
Sync to PMIx tarball
2015-08-31 07:47:46 -07:00
Jeff Squyres
596557e61b
Fortran: update a comment
...
Split the list of subroutines into cases #1 and #2 , just for clarity.
2015-08-31 03:10:09 -07:00
rhc54
c84335804c
Merge pull request #844 from rhc54/topic/updatepmix
...
Sync with PMIx tarball
2015-08-30 21:15:57 -07:00
Ralph Castain
bcabd1e282
Sync with PMIx tarball, bringing across the warning fixes pointed out by Gilles
2015-08-30 21:13:55 -07:00
Gilles Gouaillardet
21642a2407
osc: do not cast way the const modifier when this is not necessary
...
update the osc framework and mpi c bindings
2015-08-31 10:34:05 +09:00
Gilles Gouaillardet
21b1e7f8c5
mpi conformance: fix prototypes
...
- MPI_Compare_and_swap
- MPI_Fetch_and_op
- MPI_Raccumulate
- MPI_Win_detach
Thanks to Michael Knobloch and Takahiro Kawashima for bringing this
to our attention
2015-08-31 10:34:05 +09:00
Gilles Gouaillardet
7e6a213465
pmix: fix compilation error
...
compilation failed because of missing prototypes when configure'd with --enable-debug --enable-picky on a CentOS 7 box
2015-08-31 10:33:13 +09:00
rhc54
51a8a0f5d7
Merge pull request #842 from rhc54/topic/smfix
...
Fix shared memory operations by resolving local peers
2015-08-30 14:49:43 -07:00
Ralph Castain
b0d7564400
Sync to PMIx 1.1 - do not check pmix version when making connections
2015-08-30 12:15:30 -07:00
Ralph Castain
38ba54366c
Fix shared memory operations by resolving local peers
2015-08-30 12:07:14 -07:00
rhc54
305dc5317b
Merge pull request #841 from rhc54/topic/cov
...
Cleanup Coverity issues
2015-08-30 01:49:47 -07:00
Ralph Castain
0d5814b5ca
Cleanup Coverity issues
2015-08-29 21:19:27 -07:00
Ralph Castain
3cab860a01
Some cleanups - still some errors that impact shared memory operations
2015-08-29 18:11:11 -07:00
Ralph Castain
1d71037139
Update some APIs
2015-08-29 17:26:32 -07:00
Ralph Castain
79827ceaa8
Remove stale directory
2015-08-29 17:15:17 -07:00
rhc54
b32ef3514c
Merge pull request #775 from rhc54/topic/pmix2
...
Integrate PMIx 1.0 into OMPI master
2015-08-29 16:51:11 -07:00
Ralph Castain
cf6137b530
Integrate PMIx 1.0 with OMPI.
...
Bring Slurm PMI-1 component online
Bring the s2 component online
Little cleanup - let the various PMIx modules set the process name during init, and then just raise it up to the ORTE level. Required as the different PMI environments all pass the jobid in different ways.
Bring the OMPI pubsub/pmi component online
Get comm_spawn working again
Ensure we always provide a cpuset, even if it is NULL
pmix/cray: adjust cray pmix component for pmix
Make changes so cray pmix can work within the integrated
ompi/pmix framework.
Bring singletons back online. Implement the comm_spawn operation using pmix - not tested yet
Cleanup comm_spawn - procs now starting, error in connect_accept
Complete integration
2015-08-29 16:04:10 -07:00
Jeff Squyres
447eb4238a
unpack_ooo: fix empty initializer
2015-08-29 04:57:02 -07:00
Jeff Squyres
d17497b4af
Merge pull request #835 from Zhiming-Wang/master
...
Correct the wrong "Name Binding" of functions
2015-08-28 06:38:10 -04:00
Zhi Ming Wang
c8d4751ae6
Correct the wrong "Name Binding" of functions
2015-08-28 03:28:09 -04:00
rhc54
0a9fa494c8
Merge pull request #837 from rhc54/topic/listener
...
Only start a listener for processes that will actually receive connec…
2015-08-27 17:46:44 -07:00
Jeff Squyres
556c32e1d1
ompi_mpi_abort.c: use _exit(), not exit()
...
In an abort situation, just bail out immediately -- don't try to
invoke any atexit()/on_exit()-registered functions.
This is similar rationale to
open-mpi/ompi@17846411c3 .
2015-08-27 17:08:25 -07:00
Ralph Castain
89c80b2294
Only start a listener for processes that will actually receive connection requests. Tools such as orte-submit always initiate connections and thus do not need to start a listener.
2015-08-27 16:41:00 -07:00
Edgar Gabriel
10e3ac4cd5
Merge pull request #834 from edgargabriel/topic/sharedfp-individual-merge-fix
...
Topic/sharedfp individual merge fix
2015-08-26 13:02:33 -05:00
Edgar Gabriel
f214ccf499
fix the merge algorithm in the individual sharedfp component, which could
...
lead to file inconsistency in case of identical timestamps
Also fixes a potential buffer size problem.
2015-08-26 11:22:54 -05:00
