markalle
008ab98946
Merge pull request #6531 from markalle/patcher_additions
...
shmat/shmdt additions for patcher
2019-05-30 12:16:05 -05:00
Nathan Hjelm
8961daae4a
opal/atomic: work around memory barrier bug in older gcc
...
This commit fixes an issue seem with some older versions of gcc
(verified to occur in gcc 6.x) where on x86_64 systems the
acquire memory barrier in C11 atomics acts as a no-op. On these
systems the three memory barriers should all be equivalent.
This is related to the error fixed in open-mpi/ompi@30119ee .
References #6655 .
Signed-off-by: Nathan Hjelm <hjelmn@google.com>
2019-05-30 06:58:28 -07:00
Yossi Itigin
5f37fe654a
Merge pull request #6694 from hoopoepg/topic/pci-flush-on-quiet
...
SPML/UCX: added synchronized flush on quiet
2019-05-29 11:19:59 +03:00
valentin petrov
2469f6ca13
Merge pull request #6708 from vspetrov/master
...
Coll/hcoll: adding scatterv interface
2019-05-27 20:22:00 +03:00
Sergey Oblomov
0b108411f8
SPML/UCX: added synchronized flush on quiet
...
- added synchronized flush operation on quiet call.
- flush is implemented using get operation
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-27 16:07:04 +03:00
Tomislav Janjusic
6ea920e225
Coll/hcoll: adding scatterv interface
...
Signed-off-by: Valentin Petrov valentinp@mellanox.com
2019-05-27 12:27:43 +03:00
Yossi Itigin
88503f0f8d
Merge pull request #6667 from hoopoepg/topic/alloc-with-hint-realloc-inplace
...
ALLOC_WITH_HINT: added inplace realloc
2019-05-26 11:12:55 +03:00
Sergey Oblomov
d6a0912024
OSHMEM: minor optimization of realloc in shadow allocator
...
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-24 09:16:56 +03:00
Edgar Gabriel
01db2585c4
Merge pull request #6702 from edgargabriel/topic/coverty-fixes-external32
...
common/ompio: fix coverty warnings
2019-05-23 15:00:22 -05:00
Edgar Gabriel
8eda9f2ecd
common/ompio: fix coverty warnings
...
this commmit fixes coverty warnings CID 1445198 and CID 1445197
For a reason that is a bit unclear to me, coverty only complained about the read
files, but the write operations had the same issue, so I fixed that within the
same commit as well.
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2019-05-23 13:40:39 -05:00
Yossi Itigin
ad29f70c8a
Merge pull request #6698 from hoopoepg/topic/sshmem-mpi-coll-collect
...
SSHMEM/COLL: added sshmem/mpi implementation for shmem_collect call
2019-05-22 15:40:43 +03:00
Nathan Hjelm
b78066720c
btl/uct: add support for UCX 1.6.x
...
This commit updates the uct btl to support the v1.6.x release of
UCX. This release breaks API.
Signed-off-by: Nathan Hjelm <hjelmn@cs.unm.edu>
2019-05-21 04:31:57 -06:00
Sergey Oblomov
7d8cb75b2e
SSHMEM/COLL: added sshmem/mpi implementation for shmem_collect call
...
- added MPI based implementation of shmem_collect call
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-21 11:42:10 +03:00
Edgar Gabriel
88b3b24101
Merge pull request #6697 from edgargabriel/topic/external32-v2
...
Topic/external32 v2
2019-05-20 19:11:11 -05:00
Edgar Gabriel
27b2ec71a7
common/ompio: add support for read operations and collective I/O
...
external32 data representation is now support by ompio for everything
but non-blocking collective I/O operations. The support can further be improved
in a second step to limit the temporary buffer size (at least for blocking operations),
but it does work now for many scenarios.
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2019-05-20 17:56:16 -05:00
Edgar Gabriel
ab56e6f0db
common/ompio: make individual read operations work.
...
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2019-05-20 17:22:33 -05:00
Edgar Gabriel
f6b3a0af52
common/ompio: individual write of external32 works
...
both blocking and non-blocking. collective write and read operations not yet.
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2019-05-20 16:26:14 -05:00
Edgar Gabriel
d955753cb8
common/ompio: abstraction for different convertor types
...
introduce separate convertors for memory vs. file representation. Adjust the interfaces for decode_datatype to provide the convertor to be used for that.
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2019-05-20 13:35:38 -05:00
Edgar Gabriel
35be18b266
common/ompio: rename ompio_cuda* to ompio_buffer*
...
the infrastructure put in place to manage cuda buffers is actually
a lot more generic than just for cuda buffers. Specifically, we ca
reuse much of the code to implement the external32 data representation.
This commit converts the code from common_ompio_cuda* to
common_ompio_buffer*. There are just very few places where we actually need to keep the OPAL_CUDA_SUPPORT ifdef in place.
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2019-05-20 12:50:04 -05:00
Edgar Gabriel
a96efb7620
common/ompio: add comm_ompio_read_all/write_all functions
...
in preparation for adding support for the external32 data
representation.
Signed-off-by: Edgar Gabriel <egabriel@central.uh.edu>
2019-05-20 12:49:36 -05:00
Yossi Itigin
d65fae11bd
Merge pull request #6693 from hoopoepg/topic/fixed-compilation-warnings
...
SPML/UCX: fixed few compilation warnings
2019-05-20 15:54:42 +03:00
Sergey Oblomov
421a7fd47d
SPML/UCX: fixed few compilation warnings
...
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-20 14:40:24 +03:00
valentin petrov
5e0e1b63f3
Merge pull request #6690 from vspetrov/master
...
Coll/hcoll: don't init opal memhooks unless explicitely requested
2019-05-20 12:27:13 +03:00
Valentin Petrov
f19f6f432a
Coll/hcoll: don't init opal memhooks unless explicitely requested by user
...
If user sets HCOLL_EXTERNAL_UCM_EVENTS=1 then we try init opal
memory framework and register a mem release cb. Otherwise, rely on ucx.
Signed-off-by: Valentin Petrov <valentinp@mellanox.com>
2019-05-20 11:17:44 +03:00
Yossi Itigin
0c1da0fcab
Merge pull request #6687 from yosefe/topic/osc-ucx-fix-ud-self-deadlock
...
OSC/UCX: Fix deadlock with atomic lock
2019-05-20 09:50:20 +03:00
Yossi Itigin
9d1994b906
OSC/UCX: Fix deadlock with atomic lock
...
Atomic lock must progress local worker while obtaining the remote lock,
otherwise an active message which actually releases the lock might not
be processed while polling on local memory location.
Signed-off-by: Yossi Itigin <yosefe@mellanox.com>
2019-05-19 20:10:09 +03:00
Yossi Itigin
61adcd9fc2
Merge pull request #6680 from hoopoepg/topic/suppressed-pml-ucx-mt-warning
...
PML/UCX: disable PML UCX if MT is requested but not supported
2019-05-19 10:21:46 +03:00
Sergey Oblomov
a3578d9ece
PML/UCX: disable PML UCX if MT is requested but not supported
...
- in case if multithreading requested but not supported
disable PML UCX
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-17 11:25:23 +03:00
Gilles Gouaillardet
5cfa1cf666
Merge pull request #6676 from ggouaillardet/topic/oshmem_no_orte
...
oshmem: remove useless reference to orte header
2019-05-17 16:35:37 +09:00
Gilles Gouaillardet
5c14f8439a
oshmem: remove useless reference to orte header
...
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
2019-05-17 15:38:31 +09:00
Yossi Itigin
84ae05c7bc
Merge pull request #6675 from hoopoepg/topic/ucx-common-init-patcher-on-hooks-used-only
...
COMMON/UCX: init memhooks infra on external hooks only
2019-05-16 22:35:32 +03:00
Sergey Oblomov
ebc457baf5
COMMON/UCX: removed ucs stuff
...
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-16 20:56:30 +03:00
Sergey Oblomov
a0a9306066
COMMON/UCX: init memhooks infra on external hooks only
...
- initialize memory hooks infrastructure only in case
if external memory hooks are requested
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-16 20:13:16 +03:00
Jeff Squyres
aaa0b57f50
Merge pull request #6654 from jdhayes/master
...
Validate slurm params function.
2019-05-16 12:12:21 -04:00
Sergey Oblomov
a51badd627
SHADOW ALLOCATOR: minor code optimization
...
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-16 09:38:01 +03:00
Jordan Hayes
7dad74032e
plm_slurm_module: adjust for new SLURM CLI options
...
SLURM 19 discontinued the use of --cpu_bind (and changed it to
--cpu-bind). There's no easy way to test at run time which one is
accepted, so set the environment variable SLURM_CPU_BIND to "none",
which should do the same thing as the srun CLI parameter.
Signed-off-by: Jordan Hayes <jhayes@ucr.edu>
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2019-05-15 14:52:33 -07:00
Nathan Hjelm
3e1dd36241
btl/uct: check for support before disabling UCX memory hooks
...
Signed-off-by: Nathan Hjelm <hjelmn@me.com>
2019-05-15 13:49:10 -06:00
Sergey Oblomov
277c2a9e5c
ALLOC_WITH_HINT: added implace realloc
...
- in some cases realloc operation may be completed without
allocation of new buffer (and without additional data copy)
- added logic to reallocate buffer inplace if possible
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-15 19:37:38 +03:00
Yossi Itigin
7fe5c5431f
Merge pull request #6662 from yosefe/topic/oshmem-sshmem-mmap-sysv-hint-no-impl
...
OSHMEM/MMAP/SYSV: Return ERR_NOT_IMPLEMENTED if segment hint != 0
2019-05-15 17:09:49 +03:00
Jeff Squyres
4a420bb1e2
Merge pull request #6659 from jsquyres/pr/openmpi-specfile-minor-fix
...
openmpi.spec: make sure grep failure doesn't abort
2019-05-15 09:53:28 -04:00
Yossi Itigin
f7086746e9
OSHMEM/MMAP/SYSV: Return ERR_NOT_IMPLEMENTED if segment hint != 0
...
Signed-off-by: Yossi Itigin <yosefe@mellanox.com>
2019-05-15 16:12:19 +03:00
Yossi Itigin
fe5ad67127
Merge pull request #6657 from brminich/topic/fix_cov_errors
...
SPML/UCX: Fix coverity error
2019-05-15 12:29:35 +03:00
Jeff Squyres
013f5b03f5
openmpi.spec: make sure grep failure doesn't abort
...
Thanks to Daniel Letai for bringing this to our attention.
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2019-05-14 16:28:53 -07:00
Jeff Squyres
db0775974d
Merge pull request #6658 from jsquyres/pr/usnic-fix-coverity-cid-1445095
...
usnic: fix Coverity false positives
2019-05-14 18:22:29 -04:00
bosilca
6089608858
Merge pull request #6647 from bosilca/fix/length_0
...
Fix/length 0
2019-05-14 17:59:15 -04:00
Jeff Squyres
df5f7afb14
usnic: fix Coverity false positives
...
Add some Coverity inline notation to tell Coverity that these
functions never return.
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2019-05-14 13:53:25 -07:00
Mikhail Brinskii
d81dc533f6
SPML/UCX: Fix coverity error
...
Signed-off-by: Mikhail Brinskii <mikhailb@mellanox.com>
2019-05-14 22:34:01 +03:00
Jeff Squyres
9442989e2c
Merge pull request #6382 from jsquyres/pr/ofi-mtl-gitignore
...
mtl/ofi: add a .gitignore
2019-05-13 12:00:41 -04:00
Yossi Itigin
4e356cd788
Merge pull request #6653 from hoopoepg/topic/suppressed-coverity-issue
...
OSHMEM/free: suppressed coverity issue
2019-05-13 15:06:30 +03:00
Sergey Oblomov
4df8c1b3e3
OSHMEM/free: suppressed coverity issue
...
- removed dead code
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2019-05-13 11:59:02 +03:00