1
1
Граф коммитов

24070 Коммитов

Автор SHA1 Сообщение Дата
Igor Ivanov
50d68cc02e oshmem: Align OSHMEM API with spec v1.2 (fortran api) 2015-11-24 18:21:08 +02:00
Igor Ivanov
9942dfdabf oshmem: Align OSHMEM API with spec v1.2 (modify existing functions)
Several functions are moved from to shmem-compat.h to shmem.h and
back.
2015-11-24 18:21:07 +02:00
Nathan Hjelm
8498e26c4e Merge pull request #1147 from hjelmn/exp_verbs
btl/openib: add support for mlx5 atomic operations
2015-11-24 09:04:27 -07:00
Nathan Hjelm
02a6c6856d btl/openib: add support for mlx5 atomic operations
This commit adds support for fetch-and-add and compare-and-swap when
using the mlx5 driver. The support is only enabled if the expanded
verbs interface is detected. This is required because mlx5 HCAs return
the atomic result in network byte order. This support may need to be
tweaked if Mellanox commits their changes into upstream verbs.

Closes open-mpi/ompi#1077

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-11-23 16:07:12 -07:00
Jeff Squyres
a549db8ce2 create_tarball.sh: use "autogen.pl --force" 2015-11-20 22:42:01 -05:00
Jeff Squyres
acf94eef7e create_tarball: cleanup whitespace errors
No code / logic changes.
2015-11-20 22:40:23 -05:00
Ryan Grant
219581e87e Merge pull request #1090 from tkordenbrock/topic/check.for.invalid.handles.in.finalize
mtl-portals4: test for valid handle before releasing resources
2015-11-20 07:54:44 -06:00
Ryan Grant
4272f92a9c Merge pull request #1139 from francois-wellenreiter/btl_portals4_mdbind
BTL portals4: remove useless PtlMDBind PtlMDRelease calls for RMDA ex…
2015-11-20 07:53:40 -06:00
Mike Dubman
c544620a7c Merge pull request #1138 from igor-ivanov/pr/yalla-valgrind
yalla: fix valgrind error due to uninitialized status field.
2015-11-20 07:19:11 -05:00
Gilles Gouaillardet
002c7b8b3a fcoll/two_phase: use PMPI_* insted of MPI_* 2015-11-20 13:46:19 +09:00
Gilles Gouaillardet
561e7f6647 vprotocol/pessimist: use internal ompi_* insted of MPI_* 2015-11-20 13:46:19 +09:00
Gilles Gouaillardet
025fd8a9fc osc: use PMPI_* insted of MPI_* 2015-11-20 13:46:19 +09:00
Gilles Gouaillardet
d816d1c194 coll/libnbc: use PMPI_* and internal ompi_* insted of MPI_* 2015-11-20 13:46:19 +09:00
Gilles Gouaillardet
c61ef30980 autogen.pl: aborts if autogen.pl is invoked from an Open MPI tarball and without the --force option
Thanks Jeff for the wording and review
2015-11-20 13:00:55 +09:00
Francois WELLENREITER
251009e0aa BTL portals4: remove useless PtlMDBind PtlMDRelease calls for RMDA 2015-11-19 14:51:00 +01:00
yosefe
3bb1270715 yalla: fix valgrind error due to uninitialized status field. 2015-11-19 10:59:31 +02:00
Edgar Gabriel
9e5ade4e8b argh, a debugging sleep statement got into the source code. 2015-11-16 13:26:57 -06:00
Edgar Gabriel
9828389dd7 Merge pull request #1135 from edgargabriel/pr/aggregatorlogic
add a simplified version of the aggregator selection logic which reduces communication costs
2015-11-16 08:58:32 -06:00
Edgar Gabriel
dbfbcdecd5 make adjustments for the default settings of grouping parameters and the default contiguous group size option.
minor bug fix in the simple grouping strategy.
2015-11-16 08:17:27 -06:00
Edgar Gabriel
27628774c7 add a new option for a simple aggregator selection which has zero communication costs. 2015-11-16 08:17:26 -06:00
Edgar Gabriel
66c1ea5fcb change the default value of the grouping option. Also add new grouping option which skips the refinement step in the aggregator selection. 2015-11-16 08:17:23 -06:00
Edgar Gabriel
e8e117503d reduce the communication volume during MPI_File_set_view 2015-11-16 08:17:22 -06:00
Mike Dubman
3e93ef49da Merge pull request #1134 from alex-mikheev/topic/ikrit_err_fix_fix
SPML/IKRIT: opal_progress and ud_only fixes
2015-11-15 19:20:55 -06:00
Mike Dubman
b5f83d9ec6 Merge pull request #1133 from miked-mellanox/topic/master_vg_fix
OSHMEM/ikrit: fix valgrind error
2015-11-15 18:45:22 -06:00
Mike Dubman
a7128af8c4 OSHMEM/ikrit: fix valgrind error 2015-11-15 14:51:41 +02:00
Alex Mikheev
0755a59091 SPML/IKRIT: opal_progress and ud_only fixes
Some MXM tls such as self, shm can comlete requests immediately.
Make sure that opal_progress() is called before before request
is completed.

fix ud_only logic when hw rdma channel is using ud and main
transport is rc or dc.
2015-11-15 12:13:24 +02:00
rhc54
5b75af5182 Merge pull request #1130 from edgargabriel/pr/oldlustreconfigurelogic
add a verification step looking for the structures that we use in the…
2015-11-14 12:45:58 -08:00
yohann
005400a937 mtl/ofi: Make sure the resources are managed by the provider. 2015-11-13 16:16:58 -08:00
Howard Pritchard
60be91b321 Merge pull request #1105 from marksantcroos/fix/alpsinfov3
Support ALPS_APPINFO_VERSION 3.
2015-11-13 14:57:45 -07:00
Nathan Hjelm
1a0882ffb2 Merge pull request #1131 from hjelmn/osc_fixes
osc/rdma: fix some threading bugs
2015-11-13 08:46:44 -07:00
Mark Santcroos
3119bc14b2 Merge branch 'master' into fix/alpsinfov3 2015-11-13 08:53:06 -05:00
Nathan Hjelm
9ef0821856 osc/rdma: fix some threading bugs
There were two bugs in osc/rdma when using threads:

 - Deadlock is ompi_osc_rdma_start_atomic. This occurs because
   ompi_osc_rdma_frag_alloc is called with the module lock. To fix the
   issue the module lock is now recursive. In the future I will add a
   new lock to protect just the current rdma fragment.

 - Do not drop the lock in ompi_osc_rdma_frag_alloc when calling
   ompi_osc_rdma_frag_complete. Not only is it not needed but dropping
   the lock at this point can cause a competing thread to mess up the
   state.

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2015-11-12 20:25:57 -07:00
Ralph Castain
84eb21d6bf Update the script to properly run on the Cray. Add rawout option to retain the raw timing output in case the formats don't match 2015-11-12 12:11:17 -08:00
Edgar Gabriel
497bd6f355 add a verification step looking for the structures that we use in the lustre component. Disable the ccomponent if not found. 2015-11-12 10:35:11 -06:00
Yossi
b750b72a81 Merge pull request #1127 from yosefe/topic/pml-ucx-implement-cancel
pml_ucx: implement cancel, and add small optimizations.
2015-11-12 10:50:48 +02:00
yosefe
7becc54d67 pml_ucx: fix typo. 2015-11-12 09:57:41 +02:00
Gilles Gouaillardet
6ab3289582 rpm: fix openmpi.spec not to include the /usr directory
/usr cannot be included on RHEL7 like distros
2015-11-12 16:21:40 +09:00
rhc54
0d175bfca1 Merge pull request #1128 from rhc54/topic/warning
If an executable isn't found, it's possible for the state machine to…
2015-11-11 17:50:49 -08:00
Ralph Castain
986a8c1d48 If an executable isn't found, it's possible for the state machine to hit the grpcomm with a zero-node map before we actually terminate with error. Silence the annoying malloc warning about zero-byte requests.
In a novm operation that only has the HNP, ensure the #nodes gets set

Clean up the error reporting
2015-11-11 14:24:13 -08:00
Matias Cabral
45c27843e1 Merge pull request #1129 from matcabral/HFI1_openib_params
Default values for Intel HFI1 (OmniPath gen1 device) in openib btl
2015-11-11 14:04:24 -08:00
Ralph Castain
1607daeb10 Update the scaling script to output data into a CSV file for easy import into Excel 2015-11-11 13:29:37 -08:00
Ralph Castain
efbea40a8b Minor typo for slurm scaling test support, add aprun for use on Cray 2015-11-11 13:29:37 -08:00
Matias A Cabral
254a05dbbb Default values for Intel HFI1 (OmniPath gen1 device) in openib btl 2015-11-11 12:35:35 -08:00
Mike Dubman
8ec5c99412 Merge pull request #1126 from alex-mikheev/topic/ikrit_err_fix
Topic/ikrit err fix
2015-11-11 15:31:06 +02:00
Mike Dubman
93847e4ca9 Merge pull request #1125 from igor-ivanov/pr/oshmem_new_mca_vars
oshmem: Add new mca variables oshmem_abort_delay and oshmem_abort_pri…
2015-11-11 14:34:12 +02:00
Mike Dubman
ae6b6ba05b Merge pull request #1124 from igor-ivanov/pr/oshmem_error_output
oshmem: Enable force output for error messages
2015-11-11 14:33:40 +02:00
Alex Mikheev
cd8ea438d3 OSHMEM/SPML/ikrit: memcheck support 2015-11-11 13:46:20 +02:00
Alex Mikheev
2a8de45b43 OSHMEM/SPML/IKRIT: check return of mxm_req_send correctly
do not force memory registration if main and additional comm
channels are both ud
2015-11-11 13:34:26 +02:00
Igor Ivanov
f288cd7254 oshmem: Add new mca variables oshmem_abort_delay and oshmem_abort_print_stack
This commit allows to control output during abnormal oshmem application
termination.
2015-11-11 13:33:28 +02:00
Igor Ivanov
c0518c0417 oshmem: Enable force output for error messages
This change fixes issue when oshmem related error messages are not
visible for an user.
2015-11-11 13:26:10 +02:00