MPI_GROUP_EXCL(3)

💅 MPI_Group_excl — group glow-up: take your existing group, drop the listed faves, keep everyone else

okay bestie so in Open MPI land there's this little icon MPI_Group_excl, and what it does is produce a group by reordering an existing group and taking only unlisted members. Yes that's the official vibe. Let me walk you through it 🫶

---

✨ SYNTAX ✨

🌸 C Syntax

#include <mpi.h>

int MPI_Group_excl(MPI_Group group, int n, const int ranks[],
    MPI_Group *newgroup)

🎀 Fortran Syntax

USE MPI
! or the older form: INCLUDE 'mpif.h'

MPI_GROUP_EXCL(GROUP, N, RANKS, NEWGROUP, IERROR)
    INTEGER GROUP, N, RANKS(*), NEWGROUP, IERROR

🦋 Fortran 2008 Syntax

USE mpi_f08

MPI_Group_excl(group, n, ranks, newgroup, ierror)
    TYPE(MPI_Group), INTENT(IN) :: group
    INTEGER, INTENT(IN) :: n, ranks(n)
    TYPE(MPI_Group), INTENT(OUT) :: newgroup
    INTEGER, OPTIONAL, INTENT(OUT) :: ierror

---

💖 INPUT PARAMETERS 💖

• group — the group handle you're starting from ✨
• n — how many elements are chilling in the ranks array (an integer, no cap)
• ranks — an array of integer ranks in group that you do not want showing up in newgroup. literally the un-invite list 💅

---

🔥 OUTPUT PARAMETERS 🔥

• newgroup — the brand new group derived from the above, and it preserves the order defined by group. main character energy only, same order as before 👑
• ierror — Fortran only: error status (integer). classic Fortran, keeping it in the last arg 🙈

---

🌈 DESCRIPTION 🌈

So MPI_Group_excl creates a group of processes called newgroup, and it does that by deleting from group those processes with ranks ranks[0], … ranks[n-1]. That's it. That's the whole trick. 🎀

The ordering of processes in newgroup is identical to the ordering in group — no reshuffling, no glow-up reorder, just a straight subtraction, okay?

Each of the n elements of ranks must be a valid rank in group, and all the elements must be distinct — otherwise the call is erroneous. Not "oops small problem" erroneous. Erroneous erroneous. 💀

And the cute little edge case: if n = 0, then newgroup is identical to group. Nothing excluded, nothing lost, we simply vibe. ✨

---

⭐ NOTE ⭐

Currently, each of the ranks to exclude must be a valid rank in the group and all elements must be distinct or the function is erroneous. This restriction is per the draft — so yes, it's a real rule, ngl, don't test it 🫶

---

💀 ERRORS 💀

Almost all MPI routines return an error value — C routines as the return result of the function, and Fortran routines in the last argument. (Yep, "last argument" is doing a lot of work in Fortran, love that for them.)

Before the error value is returned, the current MPI error handler associated with the communication object (e.g., communicator, window, file) is called. If no communication object is associated with the MPI call, then the call is considered attached to MPI_COMM_SELF and will call the associated MPI error handler. When MPI_COMM_SELF is not initialized (i.e., before MPI_Init/MPI_Init_thread, after MPI_Finalize, or when using the Sessions Model exclusively) the error raises the initial error handler. The initial error handler can be changed by calling MPI_Comm_set_errhandler on MPI_COMM_SELF when using the World model, or the mpi_initial_errhandler CLI argument to mpiexec or info key to MPI_Comm_spawn/MPI_Comm_spawn_multiple. If no other appropriate error handler has been set, then the MPI_ERRORS_RETURN error handler is called for MPI I/O functions and the MPI_ERRORS_ABORT error handler is called for all other MPI functions.

Open MPI includes three predefined error handlers that can be used:

• MPI_ERRORS_ARE_FATAL — Causes the program to abort all connected MPI processes. dramatic but effective 💅
• MPI_ERRORS_ABORT — An error handler that can be invoked on a communicator, window, file, or session. When called on a communicator, it acts as if MPI_Abort was called on that communicator. If called on a window or file, acts as if MPI_Abort was called on a communicator containing the group of processes in the corresponding window or file. If called on a session, aborts only the local process. so… context-aware chaos 🔥
• MPI_ERRORS_RETURN — Returns an error code to the application. the "just hand me the tea" option 🍓

MPI applications can also implement their own error handlers by calling:

• MPI_Comm_create_errhandler then MPI_Comm_set_errhandler
• MPI_File_create_errhandler then MPI_File_set_errhandler
• MPI_Session_create_errhandler then MPI_Session_set_errhandler or at MPI_Session_init
• MPI_Win_create_errhandler then MPI_Win_set_errhandler

Note that MPI does not guarantee that an MPI program can continue past an error. like, it might just be over. no cap 😭

See the MPI man page for a full list of MPI error codes.

See the Error Handling section of the MPI-3.1 standard for more information.

---

🦋 SEE ALSO 🦋

• MPI_Group_range_excl — the other excl, go look at it too bestie ✨

---

🎀 COPYRIGHT 🎀

2003-2026, The Open MPI Community

---

and that's the whole page, babes 💖 this was Open MPI's MPI_GROUP_EXCL(3), dated Sep 11, 2026 — go forth and exclude those ranks, periodt 🌸🫶