add support for request_get_status_any/all/some #13279

edgargabriel · 2025-05-26T20:44:51Z

Add support for the new MPI_Request_get_status_any/all/some functions introduced with MPI 4.1

This PR contains the C implementation for the functions as well as the man-pages.
There are however also some things missing:

in the C code generation python scripts, we need to introduce the ability to create const MPI_Request[], (I have currently removed the const from the function definitions in mpi.h.in in order to make the code compile).
Fortran interfaces

hppritcha · 2025-05-26T23:51:34Z

Let me know if you want help with the python binding infrastructure.

edgargabriel · 2025-05-27T13:20:25Z

Let me know if you want help with the python binding infrastructure.

@hppritcha yes, I would appreciate some help on that front (and the same applies for the fortran bindings, even if its just a conversation that I understand what needs to be done).

ompi/mpi/c/request_get_status_all.c.in

hppritcha · 2025-05-27T18:19:36Z

@edgargabriel added new data type to the bindings code to add this new use of const MPI_Request reqs[] in the standard.

hppritcha · 2025-05-27T18:20:02Z

I'll work on the fortran but that will have to wait till later in the week.

hppritcha · 2025-05-27T18:24:29Z

note that mpi4py is probably not testing this since it keys off our MPI_Get_version return values for major/minor.
@edgargabriel have you tested mpi4py with VERSION faked to return 4.1?

edgargabriel · 2025-05-28T13:25:27Z

@hppritcha thank you very much, I will test it later this week. I have not done the mpi4py test that you mentioned, will look into this as well.

edgargabriel · 2025-06-11T22:22:18Z

note that mpi4py is probably not testing this since it keys off our MPI_Get_version return values for major/minor. @edgargabriel have you tested mpi4py with VERSION faked to return 4.1?

faking MPI 4.1. for mpi4py doesn't work unfortunately, we fail the compilation of mpi4py due to other missing function (MPI_Buffer_flush etc.). I will write some tests for the new functions.

hppritcha · 2025-06-19T19:55:26Z

@edgargabriel i pushed the remainder of the fortran related files to the PR - hopefully.

edgargabriel · 2025-06-19T20:28:58Z

@edgargabriel i pushed the remainder of the fortran related files to the PR - hopefully.

@hppritcha thank you! I hope to finish up adding tests to the ibm testsuite for the new function this weekend, and hopefully next week we could merge the PR if all tests pass.

edgargabriel · 2025-06-21T23:07:13Z

I added some tests for request_get_status_any/all/some to the ompi-tests private testsuite, and they pass. This is however only testing the C-interfaces of the function. The tests are also probably not entirely bullet-proof in terms of that they might miss some corner cases, but the base function is shown to be working.

ompi/mpi/bindings/bindings.py

ompi/mpi/c/request_get_status_all.c.in

docs/man-openmpi/man3/MPI_Request_get_status_all.3.rst

ompi/mpi/c/request_get_status_all.c.in

ompi/mpi/fortran/use-mpi-f08/request_get_status_all.c.in

ompi/mpi/fortran/use-mpi-f08/request_get_status_any.c.in

ompi/mpi/fortran/mpif-h/request_get_status_some_f.c

docs/man-openmpi/man3/MPI_Request_get_status_all.3.rst

docs/man-openmpi/man3/MPI_Request_get_status_any.3.rst

docs/man-openmpi/man3/MPI_Request_get_status_some.3.rst

docs/man-openmpi/man3/MPI_Request_get_status_all.3.rst

ompi/mpi/c/request_get_status_all.c.in

ompi/mpi/fortran/mpif-h/request_get_status_some_f.c

ompi/mpi/fortran/use-mpi-f08/request_get_status_all.c.in

ompi/mpi/fortran/use-mpi-f08/request_get_status_any.c.in

hppritcha · 2025-08-13T18:16:30Z

did we add the tests for this to ompi-tests? i'm triaging compile failures for the tests in my mtt runs:


request_get_status_all.c:32:9: error: call to undeclared function 'MPI_Request_get_status_all'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]    32 \|         MPI_Request_get_status_all(1, req, &flag, statuses);       \|         ^ request_get_status_all.c:32:9: note: did you mean 'MPI_Request_get_status'? /home/howardp/mtt/master_scratch/MiddlewareBuild_OMPIMaster/include/mpi.h:2234:20: note: 'MPI_Request_get_status' declared here  2234 \| OMPI_DECLSPEC  int MPI_Request_get_status(MPI_Request request, int *flag,       \|                    ^ 1 error generated. make[1]: Leaving directory '/home/howardp/mtt/master_scratch/TestGet_IBM/ompi-tests/ibm/pt2pt' make[1]: *** [Makefile:1582: request_get_status_all.o] Error 1 make: *** [Makefile:430: all-recursive] Error 1
--
Environment |

edgargabriel · 2025-08-13T21:06:38Z

did we add the tests for this to ompi-tests? i'm triaging compile failures for the tests in my mtt runs:


request_get_status_all.c:32:9: error: call to undeclared function 'MPI_Request_get_status_all'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]    32 \|         MPI_Request_get_status_all(1, req, &flag, statuses);       \|         ^ request_get_status_all.c:32:9: note: did you mean 'MPI_Request_get_status'? /home/howardp/mtt/master_scratch/MiddlewareBuild_OMPIMaster/include/mpi.h:2234:20: note: 'MPI_Request_get_status' declared here  2234 \| OMPI_DECLSPEC  int MPI_Request_get_status(MPI_Request request, int *flag,       \|                    ^ 1 error generated. make[1]: Leaving directory '/home/howardp/mtt/master_scratch/TestGet_IBM/ompi-tests/ibm/pt2pt' make[1]: *** [Makefile:1582: request_get_status_all.o] Error 1 make: *** [Makefile:430: all-recursive] Error 1
--
Environment |

@hppritcha I added these tests to the ibm testsuite https://github.com/open-mpi/ompi-tests/pull/189

edgargabriel · 2025-08-13T21:07:14Z

It was probably too early to merge it, should have waited until we merge the actual code. Sorry, I didn't think it through :-(

hppritcha · 2025-08-14T13:47:16Z

related to #13279

We only support named types with this first pass. related to open-mpi#12076 Fortran interfaces will be added once Fortran infrastructure additions in PR open-mpi#13279 are merged in to main. Signed-off-by: Howard Pritchard <[email protected]>

jsquyres

Great! Can we squash these down (don't have to squash to 1 commit -- just get rid of the "fixup" commits)? Then let's merge.

bosilca

I think there are some major issues with this PR. Please check my comments.

ompi/include/mpi.h.in

ompi/mpi/c/request_get_status_all.c.in

bosilca · 2025-08-15T17:59:29Z

ompi/mpi/c/request_get_status_all.c.in

+            ** MPI functions invoking this functionality does not have the const
+            ** argument
+            */
+            if(!ompi_request_check_same_instance((MPI_Request *)requests, count) ) {


Changing ompi_request_check_same_instance to use const make sense as part of this PR because it is the first time it is useful to have const in the API instead of casting everywhere.

@bosilca just to clarify: If I would change the ompi_request_check_same_instance function to take const MPI_Request * as an argument, I would have to add typecasts to MPI_Waitall/Waitany/Waitsome/Testall/Testany/Testsome since they are not const MPI_Request*. Is that what you are suggesting?

My line of thinking was that even if we decide to make that change (which I don't think I am technically in favor), I would prefer to do that in a separate PR, since I didn't want to touch the Waitall/Testall and friends functions in this one.

I am not sure I understand why you would have to make changes anywhere else? Passing a non-const to a const function argument does not require casting (unlike passing a const to a non-const).

My concern is that delayed things have a tendency to remain delayed and then forgotten because there is always something more important. This is a general statement, I'm not pointing fingers.

I don't think that is correct. I made change that you suggested, and now I get a lot of warnings from the files that I mentioned:

testall_generated.c: In function 'PMPI_Testall': testall_generated.c:64:50: warning: passing argument 1 of 'ompi_request_check_same_instance' from incompatible pointer type [-Wincompatible-pointer-types] 64 | if(!ompi_request_check_same_instance(requests, count) ) { | ^~~~~~~~ | | | struct ompi_request_t ** In file included from ../../../ompi/communicator/comm_request.h:18, from ../../../ompi/communicator/communicator.h:45, from testall_generated.c:33: ../../../ompi/request/request.h:575:62: note: expected 'const ompi_request_t **' but argument is of type 'struct ompi_request_t **' 575 | bool ompi_request_check_same_instance(const ompi_request_t** requests, | ~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~

@bosilca, I incorporated all of your change requests except for this const thing, can you please re-check and let me know how you would like to proceed.

I'm puzzled by the error message as I don't see why we cannot pass a non-const argument to a const function. Anyway, as is this PR is good to go.

ompi/mpi/c/request_get_status_all.c.in

ompi/mpi/c/request_get_status_any.c.in

ompi/mpi/fortran/mpif-h/request_get_status_all_f.c

ompi/mpi/fortran/mpif-h/request_get_status_any_f.c

ompi/mpi/fortran/mpif-h/request_get_status_some_f.c

- add the man pages for the newly implemented MPI_Request_get_status_all/any/some functions. - c-bindings: add support for const request args Three new functions were added to the MPI API as part of the 4.1 standard. These used an array of const MPI_Request s which the bindings code didn't support. This commit also fixes back the mpi.h prototypes to include the constants and required changes to the new template files. - request_get_status variants: add f08 interfaces also switch MPI_Request_get_status to use new method for generating f08 bindings. - Update fortran bindings interfaces generation code. - f90/f77 interfaces will be added as another commit. - use-mpi-ignore: start using binding infrastructure - request_get_status_mult: add f77 functions Signed-off-by: Edgar Gabriel <[email protected]> Signed-off-by: Howard Pritchard <[email protected]>

bosilca · 2025-08-25T15:39:02Z

ompi/mpi/c/request_get_status_any.c.in

+                OMPI_COPY_STATUS(status, requests[i]->req_status, false);
+            }
+            return MPI_SUCCESS;
+        } else {


The else itself is unnecessary, it can be assumed from the rest of the checks. That's how it is done in the some function.

bosilca · 2025-08-25T15:54:16Z

ompi/mpi/c/request_get_status_all.c.in

+            ** MPI functions invoking this functionality does not have the const
+            ** argument
+            */
+            if(!ompi_request_check_same_instance((MPI_Request *)requests, count) ) {


I'm puzzled by the error message as I don't see why we cannot pass a non-const argument to a const function. Anyway, as is this PR is good to go.

We only support named types with this first pass. related to open-mpi#12076 Fortran interfaces will be added once Fortran infrastructure additions in PR open-mpi#13279 are merged in to main. Signed-off-by: Howard Pritchard <[email protected]>

edgargabriel added the ⚠️ WIP-DNM! label May 26, 2025

github-actions bot added the Target: main label May 26, 2025

edgargabriel force-pushed the topic/request-status-mult branch from d233c73 to 723b84e Compare May 26, 2025 20:46

jsquyres added this to MPI 4.1 compliance May 26, 2025

jsquyres moved this to In Progress in MPI 4.1 compliance May 26, 2025

jsquyres marked this pull request as draft May 26, 2025 20:47

jsquyres added this to the v6.0.0 milestone May 27, 2025

jsquyres reviewed May 27, 2025

View reviewed changes

ompi/mpi/c/request_get_status_all.c.in Outdated Show resolved Hide resolved

edgargabriel force-pushed the topic/request-status-mult branch 2 times, most recently from efd9cf5 to f21dff7 Compare May 27, 2025 13:32

edgargabriel force-pushed the topic/request-status-mult branch from a2aa8f9 to 81e3492 Compare June 11, 2025 21:30

edgargabriel removed the ⚠️ WIP-DNM! label Jun 22, 2025

edgargabriel marked this pull request as ready for review June 22, 2025 18:48

jsquyres reviewed Jul 7, 2025

View reviewed changes

edgargabriel force-pushed the topic/request-status-mult branch from 360c797 to 47fbc39 Compare July 17, 2025 14:54

jsquyres reviewed Jul 21, 2025

View reviewed changes

hppritcha mentioned this pull request Jul 23, 2025

support for mpi_comm_attach_buffer and friends #13338

Draft

edgargabriel force-pushed the topic/request-status-mult branch from 2963f48 to f326157 Compare July 28, 2025 17:38

hppritcha mentioned this pull request Aug 14, 2025

basic implementation of MPI_TYPE_GET_VALUE_INDEX #13364

Open

jsquyres previously approved these changes Aug 15, 2025

View reviewed changes

bosilca requested changes Aug 15, 2025

View reviewed changes

hppritcha dismissed jsquyres’s stale review via 88d7f08 August 18, 2025 15:21

edgargabriel force-pushed the topic/request-status-mult branch from 88d7f08 to b057513 Compare August 25, 2025 15:08

bosilca approved these changes Aug 25, 2025

View reviewed changes

bosilca merged commit 59191a7 into open-mpi:main Aug 25, 2025
16 checks passed

add support for request_get_status_any/all/some #13279

add support for request_get_status_any/all/some #13279

Conversation

edgargabriel commented May 26, 2025

Uh oh!

hppritcha commented May 26, 2025

Uh oh!

edgargabriel commented May 27, 2025

Uh oh!

Uh oh!

hppritcha commented May 27, 2025

Uh oh!

hppritcha commented May 27, 2025

Uh oh!

hppritcha commented May 27, 2025

Uh oh!

edgargabriel commented May 28, 2025

Uh oh!

edgargabriel commented Jun 11, 2025

Uh oh!

hppritcha commented Jun 19, 2025

Uh oh!

edgargabriel commented Jun 19, 2025

Uh oh!

edgargabriel commented Jun 21, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

hppritcha commented Aug 13, 2025

Uh oh!

edgargabriel commented Aug 13, 2025

Uh oh!

edgargabriel commented Aug 13, 2025

Uh oh!

hppritcha commented Aug 14, 2025

Uh oh!

jsquyres left a comment

Choose a reason for hiding this comment

Uh oh!

bosilca left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

edgargabriel commented Jun 21, 2025 •

edited

Loading