ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
29 690 коммитов 3 Ветки 0 Теги 130 MiB
cd1b5641be
Граф коммитов

29690 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Ralph Castain
cd1b5641be Update slurm pmi configury to account for pmix 
When Slurm is built against PMIx, some installations place a copy of the
PMIx library that Slurm is linking against in the Slurm PMI location.
Current configury ignores that location. The desired behavior is to look
for a PMIx lib in that location when --with-pmi is given. If the user
also specifies --with-pmix and gives a different location, then override
anything previously found and look for it where the user directed.

Signed-off-by: Ralph Castain <rhc@pmix.org>
 2019-02-21 11:33:35 -08:00
Ralph Castain
d2f8737f5a
Merge pull request #6415 from rhc54/topic/sing 
Remove stale singularity/schizo component
 2019-02-20 18:47:57 -08:00
Ralph Castain
2f15379171 Remove stale singularity/schizo component 
Signed-off-by: Ralph Castain <rhc@pmix.org>
 2019-02-20 17:38:24 -08:00
Artem Polyakov
13a8e42108
Merge pull request #6163 from artpol84/osc/mt_submission 
Refactoring of osc/ucx component for MT
 2019-02-20 09:41:27 -08:00
Jeff Squyres
170d5d119e
Merge pull request #6409 from dmitrygladkov/topic/btl/tcp 
btl/tcp: Fix copy-paste misprint
 2019-02-20 12:12:18 -05:00
Dmitry Gladkov
9920da4992 btl/tcp: Fix copy-paste misprint 
Signed-off-by: Dmitry Gladkov <dmitrygla@mellanox.com>
 2019-02-20 11:18:02 +02:00
Gilles Gouaillardet
8d12bb25c2
Merge pull request #6408 from ggouaillardet/topic/orte_cleanup 
Misc ORTE related cleanups
 2019-02-20 17:00:13 +09:00
Gilles Gouaillardet
ad114be28c configury: automatically select rte/pmix runtime if ORTE project is not built 
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2019-02-20 13:55:55 +09:00
Gilles Gouaillardet
69d136ae5e ompi/pmix: fix misc OPAL function calls 
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2019-02-20 13:55:55 +09:00
Gilles Gouaillardet
e0e924c4ed oshmem/wrappers: only install ORTE based wrappers if ORTE is built 
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2019-02-20 13:55:55 +09:00
Gilles Gouaillardet
10cb9f6f9e oshmem: remove unnecessary dependencies to ORTE 
either use OPAL or OMPI layers, since ORTE layer
is not present when PMIx RTE is used

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2019-02-20 13:55:55 +09:00
Gilles Gouaillardet
18f679efac
Merge pull request #6401 from ggouaillardet/topic/osc_rdma_self 
osc/rdma: correctly handle communications to self
 2019-02-20 11:43:22 +09:00
KAWASHIMA Takahiro
19cbd00db0
Merge pull request #6403 from kawashima-fj/pr/man-typo-win-attach 
man: fix more typos in MPI_Win_attach man page
 2019-02-20 11:27:38 +09:00
KAWASHIMA Takahiro
7095ad10a5 man: fix more typos in MPI_Win_attach man page 
Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
 2019-02-20 11:22:38 +09:00
Gilles Gouaillardet
7694ecc13f
Merge pull request #6402 from ggouaillardet/topic/man_win_attach_detach 
man: fix typos in MPI_Win_{attach,detach} man pages
 2019-02-20 11:11:09 +09:00
Gilles Gouaillardet
7c0596819b man: fix typos in MPI_Win_{attach,detach} man pages 
no code change

[skip ci]
bot:notest

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2019-02-20 11:09:45 +09:00
Gilles Gouaillardet
fe05fcc11a osc/rdma: correctly handle communications to self 
mark the "self" peer OMPI_OSC_RDMA_PEER_LOCAL_BASE when
the window is dynamically created and use_cpu_atomics is set
in order to correctly handle communications to self.

Thanks Bart Janssens for reporting this issue.

Refs. open-mpi/ompi#6394

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
 2019-02-20 09:52:17 +09:00
Artem Polyakov
91d6115d99 opal/common/ucx: Adjust the threasholds for periodical flushes 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
3aadc2b5e1 opal/common/ucx: Fix periodical flush in the worker pool 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
84dfe1277c opal/common/ucx: Rename wpool recv_worker to dflt_worker 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
8a990c2b64 opal/common/ucx: Add comments clarifying data structures 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
19e2ae2efb opal/common/ucx: Switch to opal/tsd 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
7984d7d997 opal/common/ucx: Remove unused debugging macro 
Will be reintroduced later if needed and after adaptation to the OMPI
infrastructure.

Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
43f16d8796 opal/common/ucx: Remove common_ucx_int.h 
Place the content of common_ucx_int.h back to the common_ucx.h and
include common_ucx_wpool.h explicitly.

Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
c6de09940f ompi/osc/ucx: Switch osc/ucx code to use Worker Pool. 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
bb7d360621 opal/common/ucx: add refcnt in tlocal_ctx_tbl entry to keep track of usage 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
101036651b opal/common/ucx: Fix the bug in wpool's periodical flush 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
bcb52ecade opal/common/ucx: add winfo ptr into req 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
33517428a1 opal/common/ucx: add periodical flush and counter to opal directory. 
Signed-off-by: Xin Zhao <xinz@mellanox.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
1fa7054041 opal/common/ucx: use trylock in opal_common_progress 
Signed-off-by: Xin Zhao <xinz@mellanox.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
2d3cffe1a3 opal/common/ucx: replace opal_mutex_t with opal_recursive_mutex_t 
Signed-off-by: Xin Zhao <xinz@mellanox.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
aa26a724ed opal/common/ucx: introduce internal UCX request in wpool. 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
07cb4134be opal/common/ucx: Set of bug fixes in wpool 
Signed-off-by: Xin Zhao <xinz@mellanox.com>
 2019-02-19 14:22:07 -08:00
Xin Zhao
344bb641a1 opal/common/ucx: Minor changes in wpool 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
9fb9cfbe8e opal/common/ucx: Simplify Worker Pool TLS structure 
Get rid of unneeded context and memory region identifiers

Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:07 -08:00
Artem Polyakov
1e7bf7085d opal/common/ucx: Improve/fix debug output macro's 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:06 -08:00
Artem Polyakov
fd98ee14eb opal/common/ucx: Code cleanup 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:06 -08:00
Artem Polyakov
f38c9f3e5f opal/common/ucx: Simplify Worker Pool memory handler 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:06 -08:00
Artem Polyakov
6b7acdf21f opal/common/ucx: Somplify Worker Pool context management 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:06 -08:00
Xin Zhao
8b7fa927ba opal/common/ucx: Add fetch primitives to wpool 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:06 -08:00
Xin Zhao
bfbf818fe1 opal/common/ucx: Complete initialization of the Worker Pool 
Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:06 -08:00
Artem Polyakov
e28fadb048 opal/common/ucx: Introduce Worker Pool (wpool) functionality 
Worker Pool is an object containing/managing a set of UCX workers
and providing access to those workers through a smal interface
to allow Multi-Threaded applicatoins to access multiple HW contexts.

Signed-off-by: Artem Polyakov <artpol84@gmail.com>
 2019-02-19 14:22:06 -08:00
Ralph Castain
c9d0393158
Merge pull request #6397 from rhc54/topic/oops 
Restore orted hnp_uri cmd line option
 2019-02-18 15:13:18 -08:00
Ralph Castain
2da5651869 Restore orted hnp_uri cmd line option 
Signed-off-by: Ralph Castain <rhc@pmix.org>
 2019-02-18 13:24:03 -08:00
KAWASHIMA Takahiro
60b6626955
Merge pull request #6392 from kawashima-fj/pr/remove-have-long-long 
config: Remove remaining HAVE_LONG_LONG
 2019-02-18 14:14:27 +09:00
KAWASHIMA Takahiro
1b0fa56261 config: Remove remaining HAVE_LONG_LONG 
In the commit cacd6f389c, I removed `#if HAVE_[TYPE]` lines for types
which are always available in C99 compilers. But I forgot to remove
this line. The `HAVE_LONG_LONG` macro is still defined in `confdefs.h`.
So this is not a bug but code cleanup.

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
 2019-02-18 11:54:53 +09:00
Yossi Itigin
91d05f91e2
Merge pull request #6384 from brminich/topic/ucx_worker_net_address 
PML/UCX: Use net worker address for remote peers
 2019-02-17 12:21:00 +02:00
Matias Cabral
e3f213772d
Merge pull request #6385 from matcabral/ofi_mtl_non_blocking_cancel 
MTL_OFI: Changed Recv cancel to be non-blocking
 2019-02-15 08:44:00 -08:00
Matias A Cabral
25bdd118ac MTL_OFI: Changed Recv cancel to be non-blocking 
Updated the OFI MTL's Recv cancel to be a non-blocking call to match
the MPI spec. Given fi_cancel succeeded, then it is expected that the
user will wait on the request to read the result of if the cancel has
completed.

Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com
 2019-02-14 17:07:20 -05:00
Mikhail Brinskii
751d88192d PML/UCX: Use net worker address for remote peers 
For remote node peers pack smaller worker address, which contains
network device addresses only. This would reduce amount of OOB traffic
during startup.

Signed-off-by: Mikhail Brinskii <mikhailb@mellanox.com>
 2019-02-14 18:06:36 +02:00