ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
22 223 коммитов 3 Ветки 0 Теги
Граф коммитов

22223 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Todd Kordenbrock
0cf45df1a0 osc-portals4: fix incomplete free list conversion 2015-02-26 10:53:45 -06:00
Todd Kordenbrock
b2696edeef mtl-portals4: fix incomplete free list conversion 2015-02-26 10:53:45 -06:00
Todd Kordenbrock
c73e4fd98b coll-portals4: fix incomplete free list conversion 2015-02-26 10:53:45 -06:00
Nathan Hjelm
5a47f68fd4 Merge pull request #434 from hjelmn/master 
Remove ompi_free_list_t
 2015-02-26 09:43:36 -07:00
Rolf vandeVaart
bbdcf9ff33 Fix missing cast change from opal_free_list_changes. Fixes warning 2015-02-26 11:24:49 -05:00
Nathan Hjelm
587d3c2e13 Remove ompi_free_list_t 2015-02-26 09:17:57 -07:00
Howard Pritchard
918540dd06 Merge pull request #430 from ggouaillardet/issue/404 
romio: always set err_ status in MPIO_DATATYPE_ISCOMMITTED
 2015-02-26 09:02:34 -07:00
Gilles Gouaillardet
05140df1e6 coll/tuned: regression fix 
fix the regression introduced in open-mpi/ompi@004160f8da
 2015-02-26 13:58:06 +09:00
Gilles Gouaillardet
b888768ca3 btl/scif: fix a typo 
this is likely a typo introduced by open-mpi/ompi@5f1254d710
@hjelmn could you please double check this ?
 2015-02-26 13:45:51 +09:00
Gilles Gouaillardet
74a46863ca romio: always set err_ status in MPIO_DATATYPE_ISCOMMITTED 
from the ROMIO sources :
/* Any MPI implementation that wishes to follow the thread-safety and
   error reporting features provided by MPICH must implement these
   four functions.  Defining these as empty should not change the behavior
   of correct programs */
the MPIO_DATATYPE_ISCOMMITTED macro now always set err_=0
this is an optimistic approach for Open MPI, but it is likely other upper
layers already checked the datatype was committed.
not setting err_ is incorrect since it can lead to some use of uninitialized
variable.

Fixes open-mpi/ompi#404
 2015-02-26 13:39:05 +09:00
Howard Pritchard
dc80863589 Merge pull request #428 from hppritcha/topic/fix_gni_btl_build 
btl/ugni: fix breakage in ugni btl
 2015-02-25 16:50:48 -07:00
Jeff Squyres
8d38ac3cee java MPI bindings: use strdup() 2015-02-25 14:21:42 -08:00
Howard Pritchard
a6b9bd36e5 btl/ugni: fix breakage in ugni btl 
Signed-off-by: Howard Pritchard <hppritcha@gmail.com>
 2015-02-25 11:50:36 -08:00
Nathan Hjelm
8a17e69067 btl/ugni: fix typos introduced by free list update 2015-02-25 12:43:05 -07:00
Nathan Hjelm
883d09376f Fix coverity #1271536 2015-02-25 11:35:45 -07:00
Howard Pritchard
309dfd6d3d Merge pull request #427 from roblatham00/romio-extended-greq-fix 
fix build error if greq extensions not available
 2015-02-25 10:49:00 -07:00
George Bosilca
d4c2fc9d41 Merge branch 'master' of github.com:open-mpi/ompi 2015-02-25 12:01:57 -05:00
Mike Dubman
a0afb7d96e Merge pull request #424 from miked-mellanox/topic/master_fix_yalla 
fixes issue #414
 2015-02-25 19:01:47 +02:00
George Bosilca
f3b58006c8 Merge branch 'master' of github.com:open-mpi/ompi 2015-02-25 12:01:35 -05:00
Rob Latham
24a6f14257 fix build error if greq extensions not available 
Fall back to immediately completing the non-blocking request if we are
unable to use the extended generalized request routines.
 2015-02-25 10:52:22 -06:00
rhc54
efbb57430b Merge pull request #419 from nkogteva/master 
grpcomm brcks: fix copy-paste bug which affects performance
 2015-02-25 07:39:55 -08:00
Jeff Squyres
9381f38a98 libevent2021: remove stale owner.txt file 
I'm guessing this directory was accidentally left in the tree when
creating the owner.txt files.
 2015-02-25 07:37:27 -08:00
Jeff Squyres
16573b5bc5 Merge pull request #425 from jsquyres/pr/ob1-peruse-fix 
ob1: fix another PERUSE compile error
 2015-02-25 10:32:47 -05:00
Jeff Squyres
c3381150de ob1: fix another PERUSE compile error 2015-02-25 05:53:12 -08:00
Jeff Squyres
f3c9354d4b usnic: restore compatibility with the v1.8 branch 
Also include two other minor changes:

1. More C99-style member initialization in the component struct
1. Fix the BTL module member initialization to not be redundant
 2015-02-25 05:37:51 -08:00
yosefe
0332ab4d8b Initialize pml_yalla bsend request status. 2015-02-25 15:33:26 +02:00
Nysal Jan K A
b28e1d1b51 Merge pull request #387 from nysal/issue-383 
Fix cache line size detection on power
 2015-02-25 18:47:06 +05:30
Nysal Jan K.A
881a9f3d58 Fix cache line size detection on power 
Due to the nature of the cache architecture on power,
we don't export coherency_line_size for L2 in sysfs.
If we are unable to get the L2 cache line size, try L1.

See open-mpi/ompi#383 for more information.
 2015-02-25 17:26:28 +05:30
Nysal Jan K.A
ded408f485 Fix a crash while closing libnbc 
If the free list initialization fails in libnbc_open()
mca_coll_libnbc_component.active_requests remain uninitialized,
resulting in a crash while closing the component
 2015-02-25 17:26:28 +05:30
Alina Sklarevich
e4c4e7df5e Fix the calls to ibv_fork_init and remove btl_openib_want_fork_support. 
In order to have an effect, ibv_fork_init should be called in the
beginning of the verbs initialization flow - before the calls to the
ibv_create_qp and ibv_create_cq verbs.
These functions are called from the oob/ud code and by the time the
other verbs components (btl openib, pml yalla, ...) call ibv_fork_init,
it's too late. This commit forces the call to ibv_fork_init (if it's
requested) right at the beginning of all the components that are using
verbs.
(ibv_fork_init() can be safely called multiple times)

This commit also removes the btl_openib_want_fork_support mca parameter
and adds a new mca parameter instead - opal_verbs_want_fork_support.
Through this new parameter, fork support may be requested for ALL
components.
The default value for this parameter is set to 1.

Before this commit the btl_openib_want_fork_support parameter didn't
provide fork support for the openib btl if its value was set to 1.
(because when openib called ibv_fork_init, it was already after the
calls to ibv_create_* in oob/ud and thereofre it failed).
 2015-02-25 10:58:50 +02:00
Nathan Hjelm
0ac2f08460 pml/ob1: fix peruse compile error 
Fixes #416
 2015-02-24 15:39:46 -07:00
Jeff Squyres
a85a392896 Merge pull request #422 from jsquyres/topic/coverity-fixes 
Some Coverity fixes
 2015-02-24 17:00:10 -05:00
Jeff Squyres
bd99b741d2 java: update to new mpool API 2015-02-24 13:31:23 -08:00
Jeff Squyres
d3699fe50e configure.ac: remove some dead code 
These variables are not used anywhere, and the comment was out of date.
 2015-02-24 13:15:10 -08:00
Jeff Squyres
05f00aface plm base: ensure mca_base_var_get_value() and mca_base_var_find() succeed 
This was CID 993712
 2015-02-24 15:48:50 -05:00
Ralph Castain
451bd16a10 Remove dead code 2015-02-24 12:41:12 -08:00
Jeff Squyres
4f54fedf05 orterun: ensure to set used_num_procs=true after finding that token 
This was CID 71687.
 2015-02-24 15:25:39 -05:00
Jeff Squyres
1c3cf068a4 nbc ireduce_scatter: ensure to check the correct return code 
This was CID 1196644 and 1196621
 2015-02-24 15:24:11 -05:00
Jeff Squyres
e9980654a8 nbc ireduce_scatter_block: ensure to check the correct return code 
This was CID 1196643 and 1196615
 2015-02-24 15:24:11 -05:00
Jeff Squyres
398ae15533 rmaps_base_frame: remove dead code 
This was CID 1196641
 2015-02-24 15:24:11 -05:00
Jeff Squyres
71ae0ad5ec oob_tcp_component: add #if OPAL_ENABLE_IPV6 around IPv6-specific code 
This was CID 1196629
 2015-02-24 15:24:11 -05:00
Jeff Squyres
657d2cf77b io_ompi: check the correct returned value 
This was CID 731273
 2015-02-24 15:24:11 -05:00
Jeff Squyres
b35eb6fe10 nbc ireduce_scatter_block: ensure to check the correct return code 
This was CID 709594 and 709592
 2015-02-24 15:24:10 -05:00
Jeff Squyres
b0acef6f2d nbc_ireduce_scatter: ensure to check the proper return code 
This was CID 709229 and 709224.
 2015-02-24 15:24:10 -05:00
Jeff Squyres
fd815bba22 bcol basesmuma allreduce: remove redundant assignment 
This was CID 1196655 and 1196656
 2015-02-24 15:24:10 -05:00
Jeff Squyres
3cd36ab12a openib: fix double free 
This was CID 1269989
 2015-02-24 15:24:10 -05:00
Jeff Squyres
0bd2783b91 oob_usock: don't try to close the socket if it didn't open 
This was CID 1196663
 2015-02-24 15:24:09 -05:00
Jeff Squyres
04d9085c3b opal_info_support: protect against (group->group_component==NULL) 
This was CID 1196660
 2015-02-24 15:24:09 -05:00
Jeff Squyres
10b93e3f6f cart_rank: protect against (cart==NULL) possibilities 
This was CID 1041230
 2015-02-24 15:24:09 -05:00
Jeff Squyres
3758e3a242 topo base: ensure topo is != NULL before acting on it 
This was CID 1041229
 2015-02-24 15:24:09 -05:00