MPI_GATHER(3)

📦

version 5.0.10 · 7 versions

👑 NAME 👑

MPI_Gather, MPI_Igather, MPI_Gather_init — literally gathers up values from a whole group of processes 💖 (this is the Open MPI MPI_GATHER(3) page, bestie, get comfy)

✨ SYNOPSIS ✨

🌸 C Syntax

#include <mpi.h>

int MPI_Gather(const void *sendbuf, int sendcount, MPI_Datatype sendtype,
    void *recvbuf, int recvcount, MPI_Datatype recvtype, int root,
    MPI_Comm comm)

int MPI_Igather(const void *sendbuf, int sendcount, MPI_Datatype sendtype,
    void *recvbuf, int recvcount, MPI_Datatype recvtype, int root,
    MPI_Comm comm, MPI_Request *request)

int MPI_Gather_init(const void *sendbuf, int sendcount, MPI_Datatype sendtype,
    void *recvbuf, int recvcount, MPI_Datatype recvtype, int root,
    MPI_Comm comm, MPI_Info info, MPI_Request *request)

🎀 Fortran Syntax

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

MPI_GATHER(SENDBUF, SENDCOUNT, SENDTYPE, RECVBUF, RECVCOUNT,
        RECVTYPE, ROOT, COMM, IERROR)
    <type>  SENDBUF(*), RECVBUF(*)
    INTEGER SENDCOUNT, SENDTYPE, RECVCOUNT, RECVTYPE, ROOT
    INTEGER COMM, IERROR

MPI_IGATHER(SENDBUF, SENDCOUNT, SENDTYPE, RECVBUF, RECVCOUNT,
        RECVTYPE, ROOT, COMM, REQUEST, IERROR)
    <type>  SENDBUF(*), RECVBUF(*)
    INTEGER SENDCOUNT, SENDTYPE, RECVCOUNT, RECVTYPE, ROOT
    INTEGER COMM, REQUEST, IERROR

MPI_GATHER_INIT(SENDBUF, SENDCOUNT, SENDTYPE, RECVBUF, RECVCOUNT,
        RECVTYPE, ROOT, COMM, INFO, REQUEST, IERROR)
    <type>  SENDBUF(*), RECVBUF(*)
    INTEGER SENDCOUNT, SENDTYPE, RECVCOUNT, RECVTYPE, ROOT
    INTEGER COMM, INFO, REQUEST, IERROR

🦋 Fortran 2008 Syntax

USE mpi_f08

MPI_Gather(sendbuf, sendcount, sendtype, recvbuf, recvcount, recvtype,
        root, comm, ierror)
    TYPE(*), DIMENSION(..), INTENT(IN) :: sendbuf
    TYPE(*), DIMENSION(..) :: recvbuf
    INTEGER, INTENT(IN) :: sendcount, recvcount, root
    TYPE(MPI_Datatype), INTENT(IN) :: sendtype, recvtype
    TYPE(MPI_Comm), INTENT(IN) :: comm
    INTEGER, OPTIONAL, INTENT(OUT) :: ierror

MPI_Igather(sendbuf, sendcount, sendtype, recvbuf, recvcount, recvtype,
        root, comm, request, ierror)
    TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
    TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
    INTEGER, INTENT(IN) :: sendcount, recvcount, root
    TYPE(MPI_Datatype), INTENT(IN) :: sendtype, recvtype
    TYPE(MPI_Comm), INTENT(IN) :: comm
    TYPE(MPI_Request), INTENT(OUT) :: request
    INTEGER, OPTIONAL, INTENT(OUT) :: ierror

MPI_Gather_init(sendbuf, sendcount, sendtype, recvbuf, recvcount, recvtype,
        root, comm, info, request, ierror)
    TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
    TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
    INTEGER, INTENT(IN) :: sendcount, recvcount, root
    TYPE(MPI_Datatype), INTENT(IN) :: sendtype, recvtype
    TYPE(MPI_Comm), INTENT(IN) :: comm
    TYPE(MPI_Info), INTENT(IN) :: info
    TYPE(MPI_Request), INTENT(OUT) :: request
    INTEGER, OPTIONAL, INTENT(OUT) :: ierror

🌈 INPUT PARAMETERS 🌈

Everything you gotta hand over, no cap:

sendbuf — Starting address of send buffer (choice).
sendcount — Number of elements in send buffer (integer).
sendtype — Datatype of send buffer elements (handle).
recvcount — Number of elements for any single receive (integer, and it's significant only at root, bestie, meaning it only counts for the root).
recvtype — Datatype of recvbuffer elements (handle, significant only at root).
root — Rank of receiving process (integer). 👑 the main character fr.
comm — Communicator (handle).
info — Info (handle, persistent only).

💅 OUTPUT PARAMETERS 💅

recvbuf — Address of receive buffer (choice, significant only at root).
request — Request (handle, non-blocking only).
ierror — Fortran only: Error status (integer).

🧚 DESCRIPTION 🧚

okay so the vibe: every process, and yes that includes the root process, sends the contents of its send buffer to the root process. Then the root process receives all those messages and stores them in rank order. Periodt. 💖

The outcome is as if each of the n processes in the group (root process included, she's not exempt) had executed a call to:

MPI_Send(sendbuf, sendcount, sendtype, root, ...)

and the root had executed n calls to:

MPI_Recv(recfbuf + i * recvcount * extent(recvtype), recvcount,
         recvtype, i, ...)

where extent(recvtype) is the type extent obtained from a call to MPI_Type_extent.

An alternative description — and honestly it's giving the same energy — is that the n messages sent by the processes in the group are concatenated in rank order, and the resulting message is received by the root as if by a call to MPI_Recv(recvbuf, recvcount * n, recvtype, ... ).

The receive buffer is ignored for all nonroot processes. like, she's not even looking at it bestie 🙈

General, derived datatypes are allowed for both sendtype and recvtype. The type signature of sendcount, sendtype on process i must be equal to the type signature of recvcount, recvtype at the root. This implies that the amount of data sent must be equal to the amount of data received, pairwise between each process and the root. Distinct type maps between sender and receiver are still allowed though, so you've got options ✨

All arguments to the function are significant on process root, while on other processes, only arguments sendbuf, sendcount, sendtype, root, comm are significant. The arguments root and comm must have identical values on all processes — everybody has to agree on who the root is, or it's chaos 💀

The specification of counts and types should not cause any location on the root to be written more than once. Such a call is erroneous. And heads up: the recvcount argument at the root indicates the number of items it receives from each process, not the total number of items it receives. Read that again, it's a classic trap fr fr.

🍓 Example 1: Gather 100 ints from every process in group to root.

MPI_Comm comm;
int gsize, sendarray[100];
int root, *rbuf;
...

MPI_Comm_size( comm, &gsize);
rbuf = (int*)malloc(gsize* 100*sizeof(int));

MPI_Gather( sendarray, 100, MPI_INT, rbuf, 100, MPI_INT, root, comm);

🌸 Example 2: Previous example modified — only the root allocates memory for the receive buffer.

MPI_Comm comm;
int gsize, sendarray[100];
int root, myrank, *rbuf;
...

MPI_Comm_rank( comm, myrank);
if ( myrank == root) {
  MPI_Comm_size( comm, &gsize);
  rbuf = (int *)malloc(gsize * 100*sizeof(int));
}
MPI_Gather( sendarray, 100, MPI_INT, rbuf, 100, MPI_INT, root, comm);

💜 Example 3: Do the same as the previous example, but use a derived datatype.

Note that the type cannot be the entire set of gsize * 100 ints since type matching is defined pairwise between the root and each process in the gather. iykyk.

MPI_Comm comm;
int gsize, sendarray[100];
int root, *rbuf;
MPI_Datatype rtype;
...

MPI_Comm_size( comm, &gsize);
MPI_Type_contiguous( 100, MPI_INT, &rtype);
MPI_Type_commit( &rtype );
rbuf = (int*)malloc(gsize* 100*sizeof(int));
MPI_Gather( sendarray, 100, MPI_INT, rbuf, 1, rtype, root, comm);

🫶 USE OF IN-PLACE OPTION 🫶

When the communicator is an intracommunicator, you can perform a gather operation in-place — that's where the output buffer is used as the input buffer. Iconic, honestly. 👑

Use the variable MPI_IN_PLACE as the value of the root process sendbuf. In this case, sendcount and sendtype are ignored, and the contribution of the root process to the gathered vector is assumed to already be in the correct place in the receive buffer.

Note that MPI_IN_PLACE is a special kind of value; it has the same restrictions on its use as MPI_BOTTOM. ⚠️

Because the in-place option converts the receive buffer into a send-and-receive buffer, a Fortran binding that includes INTENT must mark these as INOUT, not OUT. Don't skip that, bestie, it matters 💖

🌈 WHEN COMMUNICATOR IS AN INTER-COMMUNICATOR 🌈

When the communicator is an inter-communicator, the root process in the first group gathers data from all the processes in the second group.

The first group defines the root process.
That process uses MPI_ROOT as the value of its root argument.
The remaining processes use MPI_PROC_NULL as the value of their root argument.
All processes in the second group use the rank of that root process in the first group as the value of their root argument.

And the send buffer argument of the processes in the first group must be consistent with the receive buffer argument of the root process in the second group. Match them up, no cap 💅

💀 ERRORS 💀

okay bestie, gather round because this part is giving "safety briefing before the rollercoaster" 🎢

Basically almost every MPI routine returns an error value. For C routines it's the return result of the function, and for Fortran routines it's the last argument. So yeah, check it. Fr fr.

But before that error value even comes back to you, the current MPI error handler associated with the communication object (think: communicator, window, file) gets called. And if literally no communication object is tied to the MPI call? Then that call is considered attached to MPI_COMM_SELF and it'll call the associated MPI error handler. Okay okay.

And here's the twist 👀 — when MPI_COMM_SELF is not initialized (meaning: before MPI_Init/MPI_Init_thread, after MPI_Finalize, or when you're using the Sessions Model exclusively), the error raises the initial error handler. That 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
an info key to MPI_Comm_spawn/MPI_Comm_spawn_multiple.

And if no other appropriate error handler has been set? Then MPI_ERRORS_RETURN gets called for MPI I/O functions, and MPI_ERRORS_ABORT gets called for all other MPI functions. That's the default vibe. 😭

Open MPI ships with three predefined error handlers you can use:

MPI_ERRORS_ARE_FATAL — Causes the program to abort all connected MPI processes. (yes, everyone. the whole group chat is getting deleted 💀)
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, it 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, it aborts only the local process. (squad-scoped drama, we love to see it ✨)
MPI_ERRORS_RETURN — Returns an error code to the application. (the "we'll handle it ourselves" icon 💅)

MPI applications can also implement their own error handlers, glow-up style, 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

🚨 heads up bestie: note that MPI does not guarantee that an MPI program can continue past an error. No promises, no safety net. Periodt.

See the MPI man page for a full list of MPI error codes 👑 (it's giving encyclopedia energy, but it's there).

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

✨ See also ✨

MPI_Gatherv

🎀 Copyright 🎀

2003-2026, The Open MPI Community

and that's a wrap on the whole page, bestie 🫶 this was MPI_GATHER(3) from Sep 10, 2026, brought to you by The Open MPI Community — go forth and gather your little hearts out 💖🌸✨

📦 where this page comes from

ubuntu stonking: openmpi-doc 5.0.10-6 · other
💖 girlified by deepseek-ai/DeepSeek-V4.1-Flash on 2026-11-03: a language model's rewrite of the original, under its terms