1
1
Граф коммитов

581 Коммитов

Автор SHA1 Сообщение Дата
Sergey Oblomov
ef7ab9bf96 OSHMEM: added missing API for get/put operations
- added calls for datatypes int/uint/8/16/32/size/ptrdiff
  for shmem_g/get/iget/get_nbi/_p/put/iput/put_nbi

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit cfa9150934)
2019-01-09 11:52:26 +02:00
Yossi Itigin
ad4b33336d oshmem/scoll: fix shmem_collect32/64 for zero-size length
Fixes scoll_basic failures with shmem_verifier, caused by recent changes
in handling of zero-size collectives.

- Check for zero-size length only for fixed size collect (shmem_fcollect),
  but not for variable-size collect (shmem_collect)
- Add 'nlong_type' parameter to internal broadcast function, to indicate
  whether the 'nlong' parameter is valid on non-root PEs, since it's
  used by shmem_collect algorithm. Before this change, some components
  assumed it's true (scoll_mpi) while others assumed it's false
  (scoll_basic).
- In scoll_basic, if nlong_type==false, do not exit if nlong==0, since
  this parameter may not be the same on all PEs.
- In scoll_mpi, fallback to scoll_basic if nlong_type==false, since MPI
  requires the 'count' argument of MPI_Bcast to be valid on all ranks.

(Picked from master 939162e)

Signed-off-by: Yossi Itigin <yosefe@mellanox.com>
2019-01-02 12:15:01 +02:00
Howard Pritchard
552834b9a6
Merge pull request #6110 from hoopoepg/topic/amo-int32-64-datatypes-v4.0
OSHMEM/AMO: added int/uint/32/64 atomics calls - v4.0
2018-12-11 06:43:05 -07:00
Sergey Oblomov
5838760a3a OSHMEM/COLL/BCAST: removed unnecessary bcast call
- removed unnecessary bcast call on zero-length request

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit c93927e27a)
2018-11-27 14:26:56 +02:00
Sergey Oblomov
0a064d8c8d OSHMEM/COLL: optimization on zero-length ops
- removed barrier call on zero-length operations

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit ff2fd0679e)
2018-11-27 14:26:52 +02:00
Sergey Oblomov
dea9cf6b63 OSHMEM: added processing of zero-length collectives
- according spec 1.4, annex C shmem collectives should process
  calls where number of elements is zero independently from pointer
  value
- added zero-count processing - it just call barrier to
  sync ranks

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 9de128afaf)
2018-11-27 14:26:44 +02:00
Sergey Oblomov
63cbe36cab OSHMEM/AMO: added int/uint/32/64 atomics calls
- added int/uint/32/64 atomics calls
- added SHMEM_SYNC_SIZE macro

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 4c071da565)
2018-11-26 09:29:55 +02:00
Geoff Paulsen
6898de01a7
Merge pull request #6012 from hoopoepg/topic/added-missing-amo-datatypes-v4.0
OSHMEM/AMO: added missing C11 macro datatypes - v4.0
2018-11-19 14:20:15 -06:00
Howard Pritchard
3369b0d10f
Merge pull request #6011 from hoopoepg/topic/fixed-oshmem-profile-build-v4.0
OSHMEM/PROFILE: fixed profile build - v4.0
2018-11-19 13:15:09 -07:00
Sergey Oblomov
b416c8afe2 OSHMEM/AMO: code beautify
- added <cr> to split API groups to simplify human processing

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 6e78102089)
2018-11-01 16:52:01 +02:00
Sergey Oblomov
d3f08d010c OSHMEM/AMO: added missing C11 macro datatypes
- added signed datatypes for atomic_add calls
- added unsigned datatypes for atomic put/inc/get/fetch calls
- fixed incorrect SHMEM_CTX_DEFAULT macro, added
  external declaration of oshmem_ctx_default variable

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit f63d6da6d7)
2018-11-01 16:51:56 +02:00
Sergey Oblomov
aaf15a6c17 OSHMEM/PROFILE: fixed profile build
- added missing file to profile makefile
- constants SHMEM_CTX_* are shifted into public header

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 4a3e83780c)
2018-11-01 16:37:49 +02:00
Yossi Itigin
8a329a797c SCOLL/BASIC: Fix invalid pSync pointer passed to barrier func
mca_scoll_basic_alltoall() passed (pSync + 1) to barrier function, but
the value of _SHMEM_ALLTOALL_SYNC_SIZE is 1, which made the barrier
function use an invalid memory location. In particular, this location
was not initialized to _SHMEM_SYNC_VALUE, which broke the barrier
algorithm and it did not complete: One PE could read 0 from its peer and
assume the peer already started the barrier, and then write 1 to the
peer. Then, the peer entered the barrier and overwrote the 1 with 0, and
then it waited forever to see '1' in its pSync.

Found with shmem_verifier test suite.

(picked from master 6754bf1)

Signed-off-by: Yossi Itigin <yosefe@mellanox.com>
2018-10-31 12:22:19 +02:00
Yossi Itigin
cda310733f shmem/lock: progress communications while waiting for shmem_lock
(cherry picked from commit 4101150)

Signed-off-by: Yossi Itigin <yosefe@mellanox.com>
2018-09-27 11:42:34 +03:00
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
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
Sergey Oblomov
6f9da0c3d5 OSHMEM: removed incorrect pshmem_wait_until macro redefinition
- fixes https://github.com/open-mpi/ompi/issues/5585

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 7a5ff6a076)
2018-09-02 08:32:33 +03:00
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
00f417706c OSHMEM/API/C11: fixed API macro
- updated compilation of C11 compiler for API macro

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit be0ea1d764)
2018-08-23 09:36:52 +03:00
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
Sergey Oblomov
b64502977a PML/SPML/UCX: init global objects using C99 style
- to avoid value mix used C99 style of object initializations

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 2806504290)
2018-07-28 16:47:43 +03:00
Sergey Oblomov
58b7786b70 MCA/ATOMIC: atomic_init renamed to atomic_startup
- there is C11 naming conflict - atomic_init is C macro
  which cause building issue

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
(cherry picked from commit 3295b23800)
2018-07-24 17:23:42 +03:00
Joshua Ladd
7bfcd4545d OSHMEM Specification version: Bump to v1.4
Signed-off-by: Joshua Ladd <jladd.mlnx@gmail.com>
2018-07-18 00:23:24 +03:00
Sergey Oblomov
36cc69d47a ATOMIC: fixed build issues (incorrect function proto)
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-17 10:32:15 +03:00
Xin Zhao
c429900cd9 OMPI/OSHMEM: add new functionality of OpenSHMEM v1.4.
Signed-off-by: Xin Zhao <xinz@mellanox.com>
2018-07-16 12:55:25 -07:00
Yossi Itigin
9d0b3a42aa
Merge pull request #5423 from hoopoepg/topic/bitwise-atomics-renaming
ATOMICS: renamed atomic calls to unsigned datatypes
2018-07-16 19:08:02 +03:00
Sergey Oblomov
da1afcaaaf ATOMIC/UCX: fixed typo in datatype macro
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-16 14:49:06 +03:00
Sergey Oblomov
bd84165277 ATOMICS: renamed atomic calls to unsigned datatypes
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-13 15:32:16 +03:00
Sergey Oblomov
d51426ff0a ATOMIC/MXM: fixed abstraction violation
- applied workaround for incorrect dynamic module dependency

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-13 14:30:12 +03:00
Joshua Ladd
f92daa6494
Merge pull request #5392 from hoopoepg/topic/bitwise-atomics-c
OSHMEM/ATOMICS: added C implementation of and/or/xor ops
2018-07-10 09:13:05 -04:00
Sergey Oblomov
0212410187 OSHMEM/ATOMICS: fixed comments errors
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-10 10:13:40 +03:00
Sergey Oblomov
64212a9ff1 OSHMEM/ATOMICS: added C implementation of and/or/xor ops
- added implementation and/or/xor operations for post and
  fetch-op notations
- implemented basic and UCX transports, mxm added
  NON-IMPLEMENTED wrapper
- updated C interfaces only (fortran will be added later)
- existing API is not updated to spec v1.4

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-09 16:18:47 +03:00
Sergey Oblomov
f2a24a008c OSHMEM: fixed compilation warning
- suppressed warning like: warning: no previous prototype for
  'shmemx_XXXXX_OP' [-Wmissing-prototypes]

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-09 10:44:35 +03:00
Sergey Oblomov
240670152e MCA/COMMON/UCX: code beautify - alignment
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-06 19:40:58 +03:00
Sergey Oblomov
bef47b792c MCA/COMMON/UCX: unified logging across all UCX modules
- added common logging infrastructure for all
  UCX modules
- all UCX modules are switched to new infra

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-05 16:25:39 +03:00
Sergey Oblomov
8080283b3d MCA/COMMON/UCX: changed return type for wait_request
- for now wait_request returns OMPI status
- updated callers

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-04 23:29:38 +03:00
Sergey Oblomov
586c16be70 ATOMIC/UCX: renamed ATOMIC_PTR_2_INT to OSHMEM_ATOMIC_PTR_2_INT
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-04 15:07:39 +03:00
Sergey Oblomov
54d97efa84 ATOMIC/UCX: fixed atomic swap/cswap issues
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-04 14:41:48 +03:00
Sergey Oblomov
5eb8c99cd7 ATOMIC/UCX: optimization for cswap
- used uint64_t output datatype to avoid branches in
  implementations

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-04 14:41:46 +03:00
Sergey Oblomov
f574c14e3a ATOMICS/UCX: redefine atomic module API
- now it accepts integer values directily instead of
  pointers

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-04 14:41:45 +03:00
Sergey Oblomov
a0ea368464 ATOMIC/UCX: minor optimization and code cleaning
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-04 14:41:43 +03:00
Sergey Oblomov
eb0abfcf92 SHMEM/ATOMIC: refactoring of module API
- removed atomic-basic-specific operand from module API
- added own calls for add and swap operations
- minor optimization for UCX atomics

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-04 14:40:14 +03:00
Sergey Oblomov
13331ba4d8 MCA/COMMON/UCX: code beautify + build fix
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-02 16:37:03 +03:00
Sergey Oblomov
8a793bb279 MCA/COMMON/UCX: fixed build issues
- fixed fuild issues when used older UCX
- added non-blocking call of ucp_put call

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-02 15:58:08 +03:00
Sergey Oblomov
c2bd6af9f2 MCA/COMMON/UCX: minor unification of del_proces calls
- some common functionality of del_procs calls is moved into
  mca_common module
- blocking ucp_put call is replaced by non-blocking routine

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-02 15:10:53 +03:00
Sergey Oblomov
952fa8ade7 PML/UCX: method mca_spml_ucx_get_mkey_slow is renamed to get_mkey_slow
Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-01 20:44:19 +03:00
Sergey Oblomov
c55db78e93 SPML/UCX: get mkey call refactoring
- method mca_spml_ucx_get_mkey_slow is moved into .c module,
  added pointer to this method into mca_spml_ucx_t structure

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-07-01 18:58:14 +03:00
Sergey Oblomov
910e08f5ef MCA/ATOMICS/UCX: workaround for abstraction violation
- some spml calls are marked as inline to exclude cross-module
  dependency
- updated get-key call to get link to local module

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-06-29 16:32:04 +03:00
Sergey Oblomov
502d04bf12 UCX/PML/SPML: fixed few coverity issues
- fixed incorrect pointer manipulation/free
- cleaned dead code
- minor optimization on process delete routine
- fixed error handling - free pointers
- added debug output for woker flush failure

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-06-26 18:52:39 +03:00
Sergey Oblomov
63e7ba6843 MCA/COMMON/UCX: added parameter for UCX/opal progress
- added parameter to set UCX/opal progresses
- minor refactoring of request wait routines

Signed-off-by: Sergey Oblomov <sergeyo@mellanox.com>
2018-06-25 11:00:12 +03:00