1
1
Граф коммитов

10159 Коммитов

Автор SHA1 Сообщение Дата
KAWASHIMA Takahiro
b9316d3136 fortran/use-mpi-f08: Correct f08 routine signatures
Following the commit f750c6932c, I compared
`ompi/mpi/fortran/use-mpi-f08/*.F90` and
`ompi/mpi/fortran/use-mpi-f08/profile/p*.F90`, and
`ompi/mpi/fortran/use-mpi-f08/mod/mpi-f08-interfaces.F90` and
`ompi/mpi/fortran/use-mpi-f08/mod/pmpi-f08-interfaces.F90`.

There are many differences. Some are bugs of `MPI_*`, some are
bugs of `PMPI_*`. I'm not sure how these bugs affect applications.

To make it easy to compare these files future, I also removed
editorial differences.

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
(cherry picked from commit cf6d28cb66)
2018-10-05 09:04:17 +09:00
Geoff Paulsen
c0796664b1
Merge pull request #5780 from jsquyres/pr/v4.0.x/moar-fortran-fixes
v4.0.x: Fortran 08 bindings fixes
2018-10-04 16:08:30 -05:00
Geoff Paulsen
5cae0ec25b
Merge pull request #5794 from bwbarrett/v4.0.x-ofi-mtl-selection
mtl ofi: Change from opt-in to opt-out provider selection
2018-10-03 08:31:07 -05:00
Jeff Squyres
46dd266e45 mpi.h: remove MPI_UB/MPI_LB when not enabling MPI-1 compat
When --enable-mpi1-compatibility was specified, the ompi_mpi_ub/lb
symbols were #if'ed out of mpi.h.  But the #defines for MPI_UB/LB
still remained.  This commit also #if's out the MPI_UB/LB macros when
--enable-mpi1-compatibility is specified.

Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
(cherry picked from commit 7223334d4d)
2018-09-28 10:01:48 -07:00
Brian Barrett
10d0a430c4 mtl ofi: Change from opt-in to opt-out provider selection
Change default provider selection logic for the OFI MTL.  The
old logic was whitelist-only, so any new HPC NIC provider would
have to ask users to do extra work or wait for an OMPI release
to be whitelisted.  The reason for the logic was to avoid
selecting a "generic" provider like sockets or shm that would
frequently have worse performance than the optimized BTL options
Open MPI supports.

With the change, we blacklist the (small, relatively static) list
of providers that duplicate internal capabilities.  Users can use
one of thse blacklisted providers in two ways: first, they can
explicitly request the provider in the include list (which will
override the default exclude list) and second, the can set a new
empty exclude list.

Since most HPC networks require special libraries and therefore
an explicit build of libfabric, it is highly unlikely that this
change will cause users to use libfabric when they didn't want to
do so.  It does, however, solve the whitelisting problem.

Signed-off-by: Brian Barrett <bbarrett@amazon.com>
(cherry picked from commit c5eaa38491)
2018-09-27 18:41:47 +00:00
Gilles Gouaillardet
ce5959ba6c fortran/use-mpi-f08: Corrections to PMPI signatures of collectives
Corrected the signatures of the collectives used by the Fortran 2008
interface to state correct intent for inout arguments and use the
ASYNCHRONOUS attribute in non-blocking collective calls.

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
(cherry picked from commit f750c6932c)
2018-09-26 12:34:46 -07:00
Philipp Otte
e98eae3da6 fortran/use-mpi-f08: Corrections to Fortran08 signatures of collectives
Corrected the signatures of the collectives used by the Fortran 2008
interface to state correct intent for inout arguments and use the
ASYNCHRONOUS attribute in non-blocking collective calls. Also corrected
the C-bindings in Fortran accordingly

Signed-off-by: Philipp Otte <philipp.j.otte@googlemail.com>
(cherry picked from commit e98d794e8b)
2018-09-26 12:34:46 -07:00
Geoff Paulsen
9d9ae9286c
Merge pull request #5753 from gpaulsen/man-page-script-abstraction-break
Fix script abstraction break: mv make_manpage.pl to config
2018-09-23 09:01:19 -05:00
Jeff Squyres
c83b30755a Fix script abstraction break: mv make_manpage.pl to config
Having the "make_manpage.pl" script in the ompi/ tree broke
"./autogen.pl --no-ompi" (specifically: "make distcheck" of --no-ompi
builds would break).

(cherry picked from commit 89773c41)
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2018-09-22 15:11:06 -05:00
Geoff Paulsen
3d4164e1e1
Merge pull request #5752 from gpaulsen/misc-warnings-fixes
Miscellaneous compiler warning stomps.
2018-09-22 15:01:53 -05:00
Geoff Paulsen
bc798b6135
Merge pull request #5755 from gpaulsen/osc_rdma_cleanup
osc/rdma: clean out stale aggregation code
2018-09-22 15:00:21 -05:00
Nathan Hjelm
72fc8acb50 osc/rdma: quiet warning
gcc complains about ret possibly being used uninitialized. That will
never happen but we should still quiet the warning. This commit sets
ret to a valid value.

Fixes #5513

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2018-09-21 14:44:56 -05:00
Nathan Hjelm
56e31f8206 osc/rdma: clean out stale aggregation code
The aggregation code in osc/rdma is currently broken and will likely
not be reused. This commit cleans it out.

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2018-09-21 14:42:45 -05:00
Jeff Squyres
2e37f97a38 Miscellaneous compiler warning stomps.
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
(cherry picked from commit fe0852bcb4)
2018-09-21 14:35:51 -05:00
Geoff Paulsen
4688da0631
Merge pull request #5736 from hoopoepg/topic/topic/common-del-procs-v4.0
MCA/COMMON/UCX: del_procs calls are unified to common module - v4.0
2018-09-20 18:12:25 -05:00
Geoff Paulsen
1a65b0ab66
Merge pull request #5741 from ggouaillardet/topic/v4.0.x/use_mpi_f08_bindings
v4.0.x: fortran/use-mpi-f08: clean [p]ompi_FOO_f bindings
2018-09-20 18:10:11 -05:00
Gilles Gouaillardet
d0a0fe818f fortran/use-mpi-f08: use bindings from ompi_mpifh_bindings
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@c4ce01d104)
2018-09-20 10:37:33 +09:00
Gilles Gouaillardet
afb66d222b fortran/use-mpi-f08: fix [p]ompi_FOO_f symbols handling
- do not generate bindings for pompi_FOO_f symbols
   (they are simply not used anywhere)

 - move ompi_FOO_f bindings out of mpi_f08.mod into
   ompi_mpifh_bindings.mod that is only used at build time

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@c6070fd2e0)
2018-09-20 10:37:01 +09:00
Gilles Gouaillardet
03d994c9cf configury: do not define "dummy" empty targets any more.
We previously needed to have empty targets because AM couldn't handle
having an AM_CONDITIONAL was targets in the "if" statement but not in the
"else".  :-(

That now appears as an old automake bug that has been fixed,
so cleanup some Makefile.am

Thanks Jeff for the pointer.

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@6e04b2a66a)
2018-09-20 10:36:41 +09:00
Gilles Gouaillardet
98156b7ace use-mpi-f08: fix a typo in [P]MPI_Dist_graph_create_adjacent bindings
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@d2393251f7)
2018-09-20 10:36:01 +09:00
Sergey Oblomov
3cace87749 MCA/COMMON/UCX: del_procs calls are unified to common module
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 920cc2e0d9)
2018-09-19 10:47:27 +03:00
George Bosilca
8d892f9917 Be conservative with the array_of_indices
We were assuming that the array_of_indices has the same size as the
number of requests (incount), instead of the numberr of actually
active requests. While the patch is trivial, the question of the
size of the array_of_indices should be clarified in the MPI Forum.

Signed-off-by: George Bosilca <bosilca@icl.utk.edu>
(cherry picked from commit a5fbfa476a)
2018-09-18 12:05:51 -07:00
Howard Pritchard
3a584fee53
Merge pull request #5723 from ggouaillardet/topic/v4.0.x/libnbc_error_path
coll/libnbc: fix various error paths
2018-09-18 09:29:45 -06:00
KAWASHIMA Takahiro
e83e118ae7 mpiext/pcollreq: fix more typos
Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
(cherry picked from commit 4a0a2598f6)
2018-09-18 15:43:06 +09:00
Gilles Gouaillardet
ece18aed45 coll/libnbc: fix various error paths
The parameter passed to NBC_Return_handle() was incorrectly casted
and not dereferenced.

Thanks Yossi for the bug report.

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@8b51862fb2)
2018-09-18 15:29:33 +09:00
Gilles Gouaillardet
73f531a8f2 mpiext/pcollreq: fix misc typos
Thanks Jeff for the report

Fixes open-mpi/ompi#5712

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@8dc6985a5a)
2018-09-18 12:47:04 +09:00
Geoff Paulsen
de0c595ca5
Merge pull request #5650 from matcabral/remove_psm2_shadow_env_40x
v4.0.x: MTL PSM2: Remove shadow variables from v4.0.x
2018-09-17 14:40:59 -05:00
Geoff Paulsen
17aab5ea5b
Merge pull request #5659 from ggouaillardet/topic/v4.0.x/misc_finalize_leaks
Plug misc leaks on MPI_Finalize()
2018-09-10 14:06:31 -05:00
KAWASHIMA Takahiro
6858028596 mpiext/pcollreq: Fix zero-count reduction
We need to return a persistent request.
`ompi_request_empty` is not a persistent request.

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>

(cherry picked from commit 69901a5156)
2018-09-10 13:11:59 +09:00
Gilles Gouaillardet
ff8600f2e4 ompi/hook: plug a misc memory leak
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@b79b37465c)
2018-09-10 09:21:49 +09:00
Gilles Gouaillardet
4bd5c538a2 pml/ob1: plug a memory leak in mca_pml_ob1_component_fini()
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(back-ported from commit open-mpi/ompi@fed33c1530)
2018-09-10 09:21:12 +09:00
Gilles Gouaillardet
c767c63a3b ompi/info: plug memory leaks in ompi_mpiinfo_finalize()
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@d0d399c9a9)
2018-09-10 09:18:15 +09:00
Gilles Gouaillardet
080e20fa02 mtl/psm2: fix a misc memory leak
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>

(cherry picked from commit open-mpi/ompi@316e4e38f4)
2018-09-10 09:17:54 +09:00
matcabral
8fa172e60b MTL PSM2: Remove shadow variables from v4.0.x
As agreed on #4574, where removed in past release branches
to avoid perfomance impacts in the default values for
some paramters.

Signed-off-by: Matias Cabral <matias.a.cabral@intel.com>
2018-09-05 18:44:40 -04:00
Howard Pritchard
7e10bc0833
Merge pull request #5607 from edgargabriel/pr/sharedfp-naming-conflict-v4.0
sharedfp/sm and lockedfile: fix naming bug
2018-09-02 16:03:14 -04:00
Geoff Paulsen
3282c61048
Merge pull request #5625 from hoopoepg/topic/optimize-blocked-calls-v4.0
PML/UCX: blocked calls optimizations - v4.0
2018-08-31 14:11:11 -05:00
Geoff Paulsen
334748753c
Merge pull request #5626 from hoopoepg/topic/opal-mem-hooks-syno-v4.0
MCA/COMMON/UCX: added synonim to opal_mem_hook variable - v4.0
2018-08-31 14:09:14 -05:00
Geoff Paulsen
51e685ff40
Merge pull request #5622 from aravindksg/ofi_race_fix_40x
MTL OFI: Fix race condition due to global progress entries array
2018-08-31 14:07:42 -05:00
Sergey Oblomov
028bcb8a73 MCA/COMMON/UCX: added synonim to opal_mem_hook variable
- added synonim to common ucx variables to allow
  to print it in opal_info -a

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit e00f7a68ba)
2018-08-29 15:17:00 +03:00
Sergey Oblomov
9215eb9a3b PML/UCX: blocked calls optimizations
- refactoring of opal/UCX progress calls
- added UCX progress priority

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit b0f87f2235)
2018-08-29 14:38:22 +03:00
Aravind Gopalakrishnan
37d1a202be MTL OFI: Fix race condition due to global progress entries array
Since progress entries array is globally allocated, it is susceptible
to race conditions when using multi-threaded applications. Allocating it
on the stack resolves any potential races as it is thread local by default.

Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@intel.com>
(cherry picked from commit ed2343034d)
2018-08-28 14:23:56 -07:00
Edgar Gabriel
2e3cf6fb12 io/base: fixes to file_delete selection logic
file_delete triggers underneath the hood the full component selection
logic, since we do not have a file handle, just a file name.

As part of the selection logic, we have to however initiate the
framework-open of the fs component in case of ompio, since ompio
will call the delete function of the selected fs componentn, which
is based on the file system where the file is located.

This was not handled correctly so far. The problem however only
shows up if the first I/O operatin to be executed is a file_delete,
other wise the file_open will lead to the correct opening and initialization
of the fs framework. This commit ensures that we do the right thing
even if file_delete is the first file I/O operation in the application.

Fixes issue #5611

Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2018-08-28 08:18:59 -05:00
Edgar Gabriel
a489a6fc9d sharedfp/sm and lockedfile: fix naming bug
If an application opens a file for reading from multiple processes
using MPI_COMM_SELF (or another communicator that has distinct
process groups but the same comm-id, as can happen as the result
of comm_split), the naming chosen for the lockedfile or the mmapped
file used by the sharedfp/sm component would collide. This patch
ensures that the filename is different by integrating the process id
of rank 0 for each sub-communicator.

This fixes one aspect of the problem reported in github issue 5593

Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2018-08-27 14:11:03 -05:00
Howard Pritchard
37440aca90
Merge pull request #5497 from markalle/apply_romio314_patch_to_v40x
v4.0.x: apply romio314 patch to romio321
2018-08-25 11:12:08 -04:00
Howard Pritchard
b926c35df0
Merge pull request #5562 from edgargabriel/pr/file_open_sharedfp_ordering_v4.0x
common/ompio: fix an ordering problem during file_open
2018-08-21 22:17:45 -04:00
Howard Pritchard
4c8852c2c8
Merge pull request #5555 from karasevb/v4.0.x_pmix_fence_status
v4.0.x/pmix: added check for pmix fence status
2018-08-21 09:28:17 -06:00
Edgar Gabriel
2da601a350 common/ompio: fix an ordering problem during file_open
the sharedfp component has to be selected and opened before
we set the default file view during file_open. Otherwise
there is a sperious error message from the sharefp_file_seek
operation that is called during the file_set_view.

Fixes Issue #5560

Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2018-08-20 10:23:32 -05:00
Boris Karasev
8873d901e8 pmix: added check for pmix fence status
Signed-off-by: Boris Karasev <karasev.b@gmail.com>
(cherry picked from commit 57683366ca)

Conflicts:
	opal/mca/common/ucx/common_ucx.c
	opal/mca/common/ucx/common_ucx.h

Modified:
	ompi/mca/pml/ucx/pml_ucx.c
	oshmem/mca/spml/ucx/spml_ucx.c
2018-08-17 21:33:50 +06:00
Jeff Squyres
7f443a159a fortran/use TKR: remove excess declaration for PMPI_Type_extent
This declaration was accidentally left behind in 89da9651bb.

Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
(cherry picked from commit 8a0b5454ae)
2018-08-16 13:13:14 -07:00
Howard Pritchard
cdc315c1ac
Merge pull request #5523 from tkordenbrock/topic/v4.0.x/fix.PtlMEUnlink.in.use
v4.0.x: coll-portals4: retry PtlMEUnlink() if PTL_IN_USE
2018-08-13 14:19:10 -06:00