ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
26 269 коммитов 3 Ветки 0 Теги
Граф коммитов

9342 Коммитов

Автор SHA1 Сообщение Дата
Joshua Hursey
5a8b2f7431 topo/base: Fix module reference in collective call 
Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
 2016-11-14 11:34:54 -06:00
Jeff Squyres
8d2c98e616 Merge pull request #2408 from hppritcha/manpage_typo 
fix minor typo in MPI_Comm_connect man page
 2016-11-14 09:38:38 -07:00
Howard Pritchard
3923bf8151 fix minor type in MPI_Comm_connect man page 
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
 2016-11-14 05:52:45 -07:00
Gilles Gouaillardet
fc776e3fa5 coll: code cleanup 
- instead of coll_base_comm_get_reqs(2) for irecv/isend, use only
   one request allocated in the stack and do a irecv/send

 - instead of ompi_request_wait_all(2), simpy ompi_request_wait

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-11-13 22:35:33 -07:00
Gilles Gouaillardet
99d30353af coll: Don't allocate space for zero requests 
Refs #2402

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-11-13 22:20:58 -07:00
Oscar Vega-Gisbert
891272f556 Update java paper reference. 
Signed-off-by: Oscar Vega-Gisbert
 2016-11-13 22:05:18 +01:00
George Bosilca
725277bc26 Don't allocate space for the requests if the 
underlying topology has no neighbors.

This commit fixes issue #2402.

Signed-off-by: George Bosilca <bosilca@icl.utk.edu>
 2016-11-12 18:01:09 -05:00
Artem Polyakov
06a73da5ea ompi/init: always lazy-wait in ompi_mpi_init 
According to discussion in #2181 we don't need MCA
parameter any more.

Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2016-11-12 07:54:48 +07:00
Gilles Gouaillardet
11dc86f26b cleanup: always #include <pthread.h> 
pthreads are now mandatory, so there is no more need to

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-11-08 13:07:45 +09:00
Gilles Gouaillardet
023d18abae pml/ob1: mca_pml_ob1_recv must have memchecker mark the buffer as defined upon success 
this is generally done in mca_pml_ob1_recv_request_free(), but this is not invoked
in via mca_pml_ob1_recv(), so do it manually

Thanks Yvan Fournier for the report

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-11-07 13:10:15 +09:00
Jeff Squyres
f11b0c7edf Merge pull request #2330 from jjhursey/topic/ibcast-non-uniform-dt-wa 
coll/libnbc: Work around for non-uniform data types in ibcast
 2016-11-05 10:26:04 -04:00
Joshua Hursey
350ef67fe0 coll/libnbc: Work around for non-uniform data types in ibcast 
* If (legal) non-uniform data type signatures are used in ibcast
   then the chosen algorithm may fail on the request, and worst case
   it could produce wrong answers.
 * Add an MCA parameter that, by default, protects the user from this
   scenario. If the user really wants to use it then they have to
   'opt-in' by setting the following parameter to false:
   - `-mca coll_libnbc_ibcast_skip_dt_decision f`
 * Once the following Issues are resolved then this parameter can
   be removed.
   - https://github.com/open-mpi/ompi/issues/2256
   - https://github.com/open-mpi/ompi/issues/1763

Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
 2016-11-01 13:33:23 -05:00
Yossi Itigin
17c8f76411 pml_ucx: fix uninitialized field req_status->_cancelled. 
Signed-off-by: Yossi Itigin <yosefe@mellanox.com>
 2016-11-01 17:02:22 +02:00
Thananon Patinyasakdikul
ea2d38de14 romio: update REFRESH_NOTES to accommodate the random() patch. 
From patch: open-mpi/ompi@23b27c510c
Signed-off-by: Thananon Patinyasakdikul <tpatinya@utk.edu>
 2016-10-31 16:08:08 -04:00
Joshua Ladd
d27b680de2 Merge pull request #2305 from vspetrov/hcoll_fortran_pair_types 
coll/hcoll fortran pair types
 2016-10-28 12:05:00 -04:00
Gilles Gouaillardet
efac15e9a1 ompi: use opal_setenv instead of putenv 
this fixes a memory leak at finalize

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-28 09:32:30 +09:00
Gilles Gouaillardet
981dccab8d ompi: cleanup environment at finalize 
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-28 09:32:30 +09:00
Gilles Gouaillardet
af67183e2f pml/v: fix a memory leak 
close the framework if no more component should be used

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-28 09:32:30 +09:00
Jeff Squyres
e9aab634af Merge pull request #2294 from ggouaillardet/topic/fortran_use_mpi_tkr 
fortran/use-mpi-tkr misc fixes
 2016-10-27 13:09:06 -04:00
Valentin Petrov
2b7e362e56 coll/hcoll fortran pair types 
Adds mapping of the MPI Fortran pair types (2INTEGER, 2REAL, 2DBLPREC)
    to the corresponding hcoll dtypes.

Signed-off-by: Valentin Petrov <valentinp@mellanox.com>
 2016-10-27 18:24:07 +03:00
Gilles Gouaillardet
ad7f3f93b0 mpi: support MPI_Dims_create(..., ndims=0, ...) 
this is a bozo case, but it should not fail with MPI_ERR_DIMS

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-27 14:13:51 +09:00
Gilles Gouaillardet
bf789762a7 fortran/use-mpi-tkr: fix MPI_Sizeof handling 
MPI_Sizeof related stuff has been moved to their own files.
Remove MPI_Sizeof from Fortran interfaces when it cannot be built
(e.g. stock gcc 4.8 on CentOS 7)

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-27 08:54:28 +09:00
Gilles Gouaillardet
1a16e68c26 fortran/use-mpi-trk: add PMPI_* interfaces in mpi module 
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-27 08:54:07 +09:00
Gilles Gouaillardet
8e26e78728 fortran/use-mpi-tkr: only build MPI_File support if requested 
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-27 08:54:07 +09:00
Gilles Gouaillardet
5543b19e9a fortran/use-mpi-tkr: rename mpi-f90-cptr-interfaces.F90 into mpi-f90-cptr-interfaces.h 
this file is meant to be included and not compiled, so use a consistent naming

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2016-10-27 08:54:07 +09:00
Edgar Gabriel
2076622924 Merge pull request #2238 from edgargabriel/pr/delete-error-codes 
update the error codes reported by file_delete
 2016-10-25 12:38:03 -05:00
George Bosilca
028e747470 Do not alter ompi_coll_tuned_use_dynamic_rules. 
This is set globally as an MCA parameter and should be never
altered based on a single communicator setting.
 2016-10-25 12:17:25 -04:00
George Bosilca
253eb80e26 Code cleaning of the tuned module. 2016-10-25 12:17:25 -04:00
Edgar Gabriel
74441b960b update the error codes reported by file_delete 2016-10-25 10:15:14 -05:00
Gilles Gouaillardet
8e788b5aee pml/ob1: refactor append_recv_req_to_queue() to improve readability 
and fix a typo in a comment

Thanks George for the patch
 2016-10-25 10:50:40 +09:00
Gilles Gouaillardet
4a886ac4cc pml/ob1: correctly reset receive request type before init 
recvreq->req_recv.req_base.req_type should always be set before invoking
MCA_PML_OB1_RECV_REQUEST_INIT(recvreq, ...) otherwise, the previous type
might be set, and you could end up with MPC_PML_REQUEST_IMPROBE when
MCA_PML_REQUEST_RECV is expected.

Thanks Chris Pattison for the report and test case.

Fixes open-mpi/ompi#2275
 2016-10-24 16:50:23 +09:00
Gilles Gouaillardet
055df6f7c6 fortran: correctly defines MPI_DISPLACEMENT_CURRENT with KIND=MPI_OFFSET_KIND 
and remove unused ompi/include/mpif-mpi-io.h
 2016-10-24 09:53:53 +09:00
Gilles Gouaillardet
e2769e4343 fortran/use-mpi-ignore-tkr: fix typo in MPI_File_write_at_all_begin interface 2016-10-24 09:53:52 +09:00
Gilles Gouaillardet
e02dc1e637 fortran/use-mpi-ignore-trk: fix typo in MPI_File_read_ordered_begin interface 2016-10-24 09:53:52 +09:00
Gilles Gouaillardet
6714f6aee7 coll/libnbc: fix MPI_Ialltoallv with MPI_IN_PLACE and without MPI param check 2016-10-24 09:29:06 +09:00
Gilles Gouaillardet
98f62690f1 man: fix typos in MPI_Info_get_{nkeys,nthkey} 
Thanks Nicolas Joly for the patch
 2016-10-24 09:04:29 +09:00
Josh Hursey
d1ecc83e14 Merge pull request #2245 from jjhursey/topic/libnbc-error-path 
coll/libnbc: Fix error path on internal error
 2016-10-21 13:27:17 -05:00
Joshua Hursey
8748e54c11 coll/libnbc: Fix error path on internal error 
* If an error is detected internal to libnbc (e.g., PML truncation error)
   this patch makes sure that the request is completed and the `MPI_ERROR`
   field is set approprately.
 * Make an attempt to cleanup outstanding requests before returning.
   - This is a "best attempt" since not all PMLs support canceling requests.
 2016-10-21 11:41:08 -04:00
Gilles Gouaillardet
45336d0bea libnbc: fix iallgather[v] 
In order to optimize for MPI_IN_PLACE, data is sent from the receive buffer.
consequently, it should be sent with the receive type and count.

Thanks Josh Hursey for the report and test case

Refs open-mpi/ompi#2256
 2016-10-21 10:24:25 +09:00
Gilles Gouaillardet
e78fcc4db9 coll/base: fix ompi_coll_base_{gather,scatter}_intra_binomial 
receive type is only relevant for root with gather,
send type is only relevant for root with scatter,
so do not access these types on a non root task
 2016-10-19 14:05:22 +09:00
Gilles Gouaillardet
cb76d93b4e ompi_wrapper_script: fix $extra_ldflags 
use @OMPI_PKG_CONFIG_LDFLAGS@ instead of @OMPI_WRAPPER_EXTRA_LDFLAGS@
so @{libdir} is substitued with ${libdir}

Thanks Manesh Nanavalla for the report
 2016-10-19 09:57:55 +09:00
Ralph Castain
7910aa23eb Set lazy_wait_in_init "on" by default for test in master 2016-10-18 08:47:04 -07:00
Gilles Gouaillardet
1e3191115b Merge pull request #2172 from ggouaillardet/topic/ialltoall_in_place 
support MPI_IN_PLACE in MPI_Ialltoall*
 2016-10-17 17:00:47 +09:00
Gilles Gouaillardet
c530b0a07c mpi/cxx: remove duplicate and now useless typedef 2016-10-15 14:30:00 +09:00
Joshua Ladd
64a15188bd Merge pull request #2199 from vspetrov/coll_hcoll_ialltoallv 
coll/hcoll: ialltoallv interface
 2016-10-14 07:59:23 -06:00
Gilles Gouaillardet
9389de4199 topo/treematch: fix displacements in mca_topo_treematch_dist_graph_create() 2016-10-14 17:16:49 +09:00
Joshua Ladd
b661307e6f Merge pull request #2218 from yosefe/topic/ucx-pml-spml-update 
ucx: adapt pml_ucx and spml_ucx to new UCX APIs
 2016-10-13 09:23:37 -04:00
Gilles Gouaillardet
958e29f929 osc/rdma: silence a warning 
declare a local variable volatile and silence CID 1372692
 2016-10-13 16:10:07 +09:00
Yossi Itigin
05ca466c6b ucx: adapt pml_ucx and spml_ucx to new UCX APIs 
- pass field_mask to ucp_init().
- use non-blocking disconnect.
- recv() with pre-allocated request.
- call opal_progress() from iprobe() and improbe().
- use shift pattern in connect/disconnect.
 2016-10-12 23:45:45 +03:00
Nathan Hjelm
1b01b6db4f Merge pull request #2213 from hjelmn/osc_rdma 
osc/rdma: fix warnings
 2016-10-12 13:13:27 -06:00