1
1
Граф коммитов

1344 Коммитов

Автор SHA1 Сообщение Дата
KAWASHIMA Takahiro
0cbdbe32f7 ompi/request: Support non-PML persistent requests
This commit adds the `req_start` member to the `ompi_request_t` struct.
The `MPI_START` and `MPI_STARTALL` routines call this callback function
instead of `MCA_PML_CALL(start(...))`. So components that return
persistent request must set this member to their request objects.

`mca_pml_base_module_t::pml_start` is not deleted because
`MCA_PML_CALL(start(...))` is still used elsewhere across OMPI.

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
2017-06-02 13:08:17 +09:00
KAWASHIMA Takahiro
c8d38d31c6 Merge pull request #3618 from kawashima-fj/pr/java-doc-man
java: Detect `javadoc` path and improve `mpijavac` man page
2017-06-02 10:24:05 +09:00
William LePera
a7c9c4aef3 MPI_Sendreceive_replace data error with > 2k msg (RTC 155305)
Signed-off-by: William LePera <lepera@us.ibm.com>
2017-06-01 13:08:58 -04:00
KAWASHIMA Takahiro
63f0945dcc java: Detect the path of javadoc in configure
Without this change, the directory of `javadoc` command must be
included in the `PATH` environment variable at `make`-time.
Paths of `javac`, `javah`, and `jar` commands are detected in
`configure`. So the path of `javadoc` also should be detected.

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
2017-05-31 14:26:14 +09:00
Nathan Hjelm
c7e6294f31 Merge pull request #3589 from hjelmn/cxx_glue
mpi/cxx: remove nonexistent function from cxx glue
2017-05-26 11:24:05 -06:00
Nathan Hjelm
ee9093c373 mpi/cxx: remove nonexistent function from cxx glue
This commit removes a nonexistent function that was causing build
problems under certain environments.

Reference #3442

Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
2017-05-26 10:40:19 -06:00
KAWASHIMA Takahiro
c3bbd7dfec man: Remove unnecessary empty lines
All other man pages don't have an empty line after
the "! or the older form: INCLUDE 'mpif.h'" line

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
2017-05-26 11:17:59 +09:00
KAWASHIMA Takahiro
e57ab611cd man: Fix roff markup of variable names
These typos are found by running `grep -r '\\f[^IBRP]' ompi/mpi/man/`.

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
2017-05-26 11:17:23 +09:00
Joshua Hursey
a5e9c3501b ompi/mpi: Fix MPI_UNDEFINED handling in mpi_type_create_f90_(real|complex)
Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
2017-05-24 12:10:49 -04:00
Joshua Hursey
5e302f5279 ompi/mpi: Fix parameter order in mpi_type_create_f90_(real|complex)
Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
2017-05-23 17:54:33 -04:00
Geoff Paulsen
50f9287c03 Merge pull request #2941 from markalle/pr/mpi-info-update2
Finally Merging this in.  MPI_*_get_info/set_info().
Targeting v3.1 release.  @hjelmn were you interested in switching some internal pieces to begin using this?  Should we target v3.1 (or whatever we call the Oct 15th release?)
2017-05-22 09:22:04 -05:00
Mark Allen
482d84b6e5 fixes for Dave's get/set info code
The expected sequence of events for processing info during object creation
is that if there's an incoming info arg, it is opal_info_dup()ed into the obj
at obj->s_info first. Then interested components register callbacks for
keys they want to know about using opal_infosubscribe_infosubscribe().

Inside info_subscribe_subscribe() the specified callback() is called with
whatever matching k/v is in the object's info, or with the default. The
return string from the callback goes into the new k/v stored in info, and
the input k/v is saved as __IN_<key>/<val>. It's saved the same way
whether the input came from info or whether it was a default. A null return
from the callback indicates an ignored key/val, and no k/v is stored for
it, but an __IN_<key>/<val> is still kept so we still have access to the
original.

At MPI_*_set_info() time, opal_infosubscribe_change_info() is used. That
function calls the registered callbacks for each item in the provided info.
If the callback returns non-null, the info is updated with that k/v, or if
the callback returns null, that key is deleted from info. An __IN_<key>/<val>
is saved either way, and overwrites any previously saved value.

When MPI_*_get_info() is called, opal_info_dup_mpistandard() is used, which
allows relatively easy changes in interpretation of the standard, by looking
at both the <key>/<val> and __IN_<key>/<val> in info. Right now it does
  1. includes system extras, eg k/v defaults not expliclty set by the user
  2. omits ignored keys
  3. shows input values, not callback modifications, eg not the internal values

Currently the callbacks are doing things like
    return some_condition ? "true" : "false"
that is, returning static strings that are not to be freed. If the return
strings start becoming more dynamic in the future I don't see how unallocated
strings could support that, so I'd propose a change for the future that
the callback()s registered with info_subscribe_subscribe() do a strdup on
their return, and we change the callers of callback() to free the strings
it returns (there are only two callers).

Rough outline of the smaller changes spread over the less central files:
  comm.c
    initialize comm->super.s_info to NULL
    copy into comm->super.s_info in comm creation calls that provide info
    OBJ_RELEASE comm->super.s_info at free time
  comm_init.c
    initialize comm->super.s_info to NULL
  file.c
    copy into file->super.s_info if file creation provides info
    OBJ_RELEASE file->super.s_info at free time
  win.c
    copy into win->super.s_info if win creation provides info
    OBJ_RELEASE win->super.s_info at free time

  comm_get_info.c
  file_get_info.c
  win_get_info.c
    change_info() if there's no info attached (shouldn't happen if callbacks
      are registered)
    copy the info for the user

The other category of change is generally addressing compiler warnings where
ompi_info_t and opal_info_t were being used a little too interchangably. An
ompi_info_t* contains an opal_info_t*, at &(ompi_info->super)

Also this commit updates the copyrights.

Signed-off-by: Mark Allen <markalle@us.ibm.com>
2017-05-17 01:12:49 -04:00
Gilles Gouaillardet
384387bb53 Merge pull request #3411 from ggouaillardet/topic/mpi_f08_interfaces_callbacks
f08: make procedure(MPI_User_function) type available from mpi_f08
2017-05-17 09:02:26 +09:00
Jeff Squyres
39fa1d5c05 Merge pull request #3500 from bosilca/topic/any_source
Allow MPI_ANY_SOURCE in MPI_Sendrecv_replace.
2017-05-16 16:36:00 -04:00
David Solt
50aa143ab6 Major structural changes to data types: .super infosubscriber
ompi_communicator_t, ompi_win_t, ompi_file_t all have a super class of type opal_infosubscriber_t instead of a base/super type of opal_object_t (in previous code comm used c_base, but file used super).  It may be a bit bold to say that being a subscriber of MPI_Info is the foundational piece that ties these three things together, but if you object, then I would prefer to turn infosubscriber into a more general name that encompasses other common features rather than create a different super class.  The key here is that we want to be able to pass comm, win and file objects as if they were opal_infosubscriber_t, so that one routine can heandle all 3 types of objects being passed to it.

MPI_INFO_NULL is still an ompi_predefined_info_t type since an MPI_Info is part of ompi but the internal details of the underlying information concept is part of opal.

An ompi_info_t type still exists for exposure to the user, but it is simply a wrapper for the opal object.

Routines such as ompi_info_dup, etc have all been moved to opal_info_dup and related to the opal directory.

Fortran to C translation tables are only used for MPI_Info that is exposed to the application and are therefore part of the ompi_info_t and not the opal_info_t

The data structure changes are primarily in the following files:

    communicator/communicator.h
    ompi/info/info.h
    ompi/win/win.h
    ompi/file/file.h

The following new files were created:

    opal/util/info.h
    opal/util/info.c
    opal/util/info_subscriber.h
    opal/util/info_subscriber.c

This infosubscriber concept is that communicators, files and windows can have subscribers that subscribe to any changes in the info associated with the comm/file/window.  When xxx_set_info is called, the new info is presented to each subscriber who can modify the info in any way they want.  The new value is presented to the next subscriber and so on until all subscribers have had a chance to modify the value.  Therefore, the order of subscribers can make a difference but we hope that there is generally only one subscriber that cares or modifies any given key/value pair.  The final info is then stored and returned by a call to xxx_get_info.

The new model can be seen in the following files:

    ompi/mpi/c/comm_get_info.c
    ompi/mpi/c/comm_set_info.c
    ompi/mpi/c/file_get_info.c
    ompi/mpi/c/file_set_info.c
    ompi/mpi/c/win_get_info.c
    ompi/mpi/c/win_set_info.c

The current subscribers where changed as follows:

    mca/io/ompio/io_ompio_file_open.c
    mca/io/ompio/io_ompio_module.c
    mca/osc/rmda/osc_rdma_component.c (This one actually subscribes to "no_locks")
    mca/osc/sm/osc_sm_component.c (This one actually subscribes to "blocking_fence" and "alloc_shared_contig")

Signed-off-by: Mark Allen <markalle@us.ibm.com>

Conflicts:
	AUTHORS
	ompi/communicator/comm.c
	ompi/debuggers/ompi_mpihandles_dll.c
	ompi/file/file.c
	ompi/file/file.h
	ompi/info/info.c
	ompi/mca/io/ompio/io_ompio.h
	ompi/mca/io/ompio/io_ompio_file_open.c
	ompi/mca/io/ompio/io_ompio_file_set_view.c
	ompi/mca/osc/pt2pt/osc_pt2pt.h
	ompi/mca/sharedfp/addproc/sharedfp_addproc.h
	ompi/mca/sharedfp/addproc/sharedfp_addproc_file_open.c
	ompi/mca/topo/treematch/topo_treematch_dist_graph_create.c
	ompi/mpi/c/lookup_name.c
	ompi/mpi/c/publish_name.c
	ompi/mpi/c/unpublish_name.c
	opal/mca/mpool/base/mpool_base_alloc.c
	opal/util/Makefile.am
2017-05-12 14:41:05 -04:00
KAWASHIMA Takahiro
0650d4141f Merge pull request #3401 from kawashima-fj/pr/fortran-argv-null
fortran: Fix `MPI_ARGV(S)_NULL` compilation error
2017-05-11 11:23:12 +09:00
George Bosilca
86a7b317a5
Allow MPI_ANY_SOURCE in MPI_Sendrecv_replace.
Signed-off-by: George Bosilca <bosilca@icl.utk.edu>
2017-05-09 16:57:15 -04:00
Gilles Gouaillardet
96b00b0fcf f08: make procedure(MPI_User_function) type available from mpi_f08
Refs. open-mpi/ompi#3409

Thanks Nathan T. Weeks for the report

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
2017-04-25 13:33:00 +09:00
KAWASHIMA Takahiro
3699ce1f75 mpi/java: Set the given error handler to Win
Probably setting `MPI_ERRORS_RETURN` is unintentional. Probably...

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
2017-04-24 16:55:13 +09:00
KAWASHIMA Takahiro
8558185c85 mpi/java: Add missing Java binding methods
This commit add the following methods.

| Language-indep. notation | Java binding            |
| ------------------------ | ----------------------- |
| MPI_WIN_GET_ERRHANDLER   | mpi.Win.getErrhandler   |
| MPI_FILE_SET_ERRHANDLER  | mpi.File.setErrhandler  |
| MPI_FILE_GET_ERRHANDLER  | mpi.File.getErrhandler  |
| MPI_COMM_CALL_ERRHANDLER | mpi.Comm.callErrhandler |
| MPI_FILE_CALL_ERRHANDLER | mpi.File.callErrhandler |
| MPI_FILE_IREAD_AT_ALL    | mpi.File.iReadAtAll     |
| MPI_FILE_IWRITE_AT_ALL   | mpi.File.iWriteAtAll    |
| MPI_FILE_IREAD_ALL       | mpi.File.iReadAll       |
| MPI_FILE_IWRITE_ALL      | mpi.File.iWriteAll      |
| MPI_FILE_GET_ATOMICITY   | mpi.File.getAtomicity   |

`MPI_FILE_I{READ,WRITE}(_AT)_ALL` routines are added in MPI-3.1.
I don't know why other methods were missing.

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
2017-04-24 16:55:03 +09:00
KAWASHIMA Takahiro
0fcd96486a fortran: Fix MPI_ARGV(S)_NULL compilation error
Fortran constants `MPI_ARGV_NULL` and `MPI_ARGVS_NULL` are defined
in MPI-3.1 p.680 as below.

> `MPI_ARGVS_NULL`
>   2-dim. array of `CHARACTER*(*)`
> `MPI_ARGV_NULL`
>   array of `CHARACTER*(*)`

`MPI_ARGV_NULL` and `MPI_ARGVS_NULL` are used as an argument of
`MPI_COMM_SPAWN` and `MPI_COMM_SPAWN_MULTIPLE` respectively and
their argument `argv` and `array_of_argv` are defined as below
for `USE mpi_f08` binding in MPI-3.1.

```
CHARACTER(LEN=*), INTENT(IN) :: argv(*)
CHARACTER(LEN=*), INTENT(IN) :: array_of_argv(count, *)
```

Defining them as `INTEGER` in `mpi_f08` module will cause
a compilation error of user programs like
"There is no specific subroutine for the generic 'mpi_comm_spawn'".

Signed-off-by: KAWASHIMA Takahiro <t-kawashima@jp.fujitsu.com>
2017-04-24 13:53:12 +09:00
Gilles Gouaillardet
ebe6125750 mpi/c: MPI_PROC_NULL is not a valid rank in MPI_Win_{lock,unlock}
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
2017-04-22 11:13:13 +09:00
bosilca
872cf44c28 Improve the opal_pointer_array & more (#3369)
* Complete rewrite of opal_pointer_array
Instead of a cache oblivious linear search use a bits array
to speed up the management of the free space. As a result we
slightly increase the memory used by the structure, but we get a
significant boost in performance.

Signed-off-by: George Bosilca <bosilca@icl.utk.edu>

* Do not register datatypes in the f2c translation table.
The registration is now done up into the Fortran layer, by
forcing a call to MPI_Type_c2f.

Signed-off-by: George Bosilca <bosilca@icl.utk.edu>
2017-04-18 21:41:26 -04:00
Gilles Gouaillardet
23dad50d51 mpi/c: allow MPI_PROC_NULL in MPI_Win_shared_query()
This fixes a regression introduced in open-mpi/ompi@b3a20100d3

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
2017-04-19 10:06:41 +09:00
Howard Pritchard
b9331527f5 timer: hack use of clock_gettime
better solution needed later
 workaround for #3003

Signed-off-by: Howard Pritchard <howardp@lanl.gov>
2017-03-18 15:08:59 -05:00
Joshua Hursey
48d13aa8ef mpi/c: Force wtick/wtime to use gettimeofday
* See https://github.com/open-mpi/ompi/issues/3003 for a discussion about
   this patch. Once we get a better version in place we can revert this
   change.

Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
2017-03-15 21:24:37 -05:00
Omri Mor
20ab37a297 Add missing MPI_T_PVAR_SESSION_NULL to mpi.h
MPI_T_pvar_session_free() should reject null sessions and set *session to MPI_T_PVAR_SESSION_NULL

Signed-off-by: Omri Mor <omri50@gmail.com>
2017-03-05 09:03:30 -06:00
Jeff Squyres
dc53cd5f74 MPI_Wtick: may return a higher resolution than 10e-6 these days
Thanks to Mark Dixon (@ccaamad) for reporting the error.

Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2017-03-02 10:39:28 -05:00
Gilles Gouaillardet
880f2d5431 mpi/c: revamp error handling in MPI_{Pack,Unpack}[_external]
Thanks Alex and the folks at Mellanox for the help.

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
2017-03-01 10:03:31 +09:00
Josh Hursey
0006f0d7c5 Merge pull request #2773 from jjhursey/topic/hook-fwk
Add a 'hook' framework
2017-02-28 12:29:50 -06:00
George Bosilca
366d64b7e5 Move the collective structure outside the communicator.
As we changed the ABI (forcing a major release), we can limit
the size of the predefined communicators by moving the collective
structure outside the communicator. This might have a minimal,
but unnoticeable, impact on performance. This approach has been
discussed during the January 2017 devel meeting.

Signed-off-by: George Bosilca <bosilca@icl.utk.edu>
Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
2017-02-27 11:54:17 -06:00
Joshua Hursey
c10bbfded6 ompi/hook: Add the hook/license framework
* Include a 'demo' component that shows some of the features.
 * Currently has hooks for:
   - MPI_Initialized
     - top, bottom
   - MPI_Init_thread
     - top, bottom
   - MPI_Finalized
     - top, bottom
   - MPI_Init
     - top (pre-opal_init), top (post-opal_init), error, bottom
   - MPI_Finalize
     - top, bottom
 * Other places in ompi can 'register' to hook into any one of these places
   by passing back a component structure filled with function pointers.
 * Add a `MCA_BASE_COMPONENT_FLAG_REQUIRED` flag to the MCA structure that
   is checked by the `hook` framework. If a required, static component has
   been excluded then the `hook` framework will fail to initialize.
   - See note in `opal/mca/mca.h` as to why this is checked in the `hook`
     framework and not in `opal/mca/base/mca_base_component_find.c`

Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
2017-02-27 12:05:53 -05:00
Joshua Hursey
78006f93a4 coll: Move reduce_local into the coll framework
* Since we are adding a new function to `mca_coll_base_module_2_1_0_t`
   we need to increase the version of the module structure to `2_2_0`.
 * Add a comment just above the PREDEFINED_COMMUNICATOR_PAD describing
   it's purpose and when it should change. To help future developers
   trying to answer the question noted in the comment.

Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
2017-02-14 08:56:07 -06:00
Joshua Hursey
383330a50d coll/basic: Expand check for negative input values
* Negative values are parameter errors for neighborhood collectives
   - Add checks to the mpi/c interface `MPI_PARAM_CHECK`
 * Fix a success check for neighbor_alltoallw with dist_graph

Signed-off-by: Joshua Hursey <jhursey@us.ibm.com>
2017-02-08 14:26:32 -06:00
Gilles Gouaillardet
6f2ca5809b man: fix a typo in MPI_Win_get_name()
Thanks Nicolas Joly for the report

Fixes open-mpi/ompi#2782

Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
2017-01-24 09:08:13 +09:00
Nysal Jan K.A
25ba507ada mpit: Fix MPI_T_pvar_get_index
MPI_T_pvar_get_index was returning an incorrect index. The index
was never set correctly while registering the performance variables.
Additionally fix a missing case in the mca_base_var_type_t to MPI
datatype conversion. This type is currently used for control variables
registered by mxm, fca and hcoll components.

Signed-off-by: Nysal Jan K.A <jnysal@in.ibm.com>
2016-12-22 12:30:21 +05:30
Ralph Castain
585540bcee Reduce the flood of warnings due to uninitialized variables, mismatched types, and unused things to a more bearable trickle
Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-12-14 16:33:50 -08:00
Gilles Gouaillardet
43ee08b20e ompi/c: remove unused variable in [i]gatherv
Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>
2016-12-01 13:59:25 +09:00
Ralph Castain
1e2019ce2a Revert "Update to sync with OMPI master and cleanup to build"
This reverts commit cb55c88a8b.
2016-11-22 15:03:20 -08:00
Ralph Castain
cb55c88a8b Update to sync with OMPI master and cleanup to build
Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-11-22 14:24:54 -08:00
Howard Pritchard
fb5ccd3618 Merge pull request #2404 from osvegis/topic/java_paper
Update java paper reference.
2016-11-14 11:35:45 -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
Oscar Vega-Gisbert
891272f556 Update java paper reference.
Signed-off-by: Oscar Vega-Gisbert
2016-11-13 22:05:18 +01:00
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
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
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