MPI_GATHERV(3)

📦
version 5.0.10 · 7 versions
, in ubuntu stonking

MPI_Gatherv(3) 💖 — the Open MPI girlies' guide to gathering (varying-flavor edition) ✨

okay so bestie, welcome to MPI_Gatherv 🎀 — that's the Open MPI manual page, section 3, and it's the ✨fanciest✨ sibling of plain old Gather. Grab a snack, we're doing this in parts.

🌸 NAME 🌸

MPI_Gatherv, MPI_Igatherv, MPI_Gatherv_init — the iconique trio that gathers varying amounts of data from all processes to the root process 💅. Varying amounts!! Not everyone has to bring the same number of snacks to the function, and honestly? That's the whole point. periodt.

📜 SYNTAX 📜

🫶 C Syntax

#include <mpi.h>

int MPI_Gatherv(const void *sendbuf, int sendcount, MPI_Datatype sendtype,
    void *recvbuf, const int recvcounts[], const int displs[], MPI_Datatype recvtype,
    int root, MPI_Comm comm)

int MPI_Igatherv(const void *sendbuf, int sendcount, MPI_Datatype sendtype,
    void *recvbuf, const int recvcounts[], const int displs[], MPI_Datatype recvtype,
    int root, MPI_Comm comm, MPI_Request *request)

int MPI_Gatherv_init(const void *sendbuf, int sendcount, MPI_Datatype sendtype,
    void *recvbuf, const int recvcounts[], const int displs[], 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_GATHERV(SENDBUF, SENDCOUNT, SENDTYPE, RECVBUF, RECVCOUNTS,
        DISPLS, RECVTYPE, ROOT, COMM, IERROR)
    <type>  SENDBUF(*), RECVBUF(*)
    INTEGER SENDCOUNT, SENDTYPE, RECVCOUNTS(*), DISPLS(*)
    INTEGER RECVTYPE, ROOT, COMM, IERROR

MPI_IGATHERV(SENDBUF, SENDCOUNT, SENDTYPE, RECVBUF, RECVCOUNTS,
        DISPLS, RECVTYPE, ROOT, COMM, REQUEST, IERROR)
    <type>  SENDBUF(*), RECVBUF(*)
    INTEGER SENDCOUNT, SENDTYPE, RECVCOUNTS(*), DISPLS(*)
    INTEGER RECVTYPE, ROOT, COMM, REQUEST, IERROR

MPI_GATHERV_INIT(SENDBUF, SENDCOUNT, SENDTYPE, RECVBUF, RECVCOUNTS,
        DISPLS, RECVTYPE, ROOT, COMM, INFO, REQUEST, IERROR)
    <type>  SENDBUF(*), RECVBUF(*)
    INTEGER SENDCOUNT, SENDTYPE, RECVCOUNTS(*), DISPLS(*)
    INTEGER RECVTYPE, ROOT, COMM, INFO, REQUEST, IERROR

🦋 Fortran 2008 Syntax

USE mpi_f08

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

MPI_Igatherv(sendbuf, sendcount, sendtype, recvbuf, recvcounts, displs,
        recvtype, root, comm, request, ierror)
    TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
    TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
    INTEGER, INTENT(IN) :: sendcount, root
    INTEGER, INTENT(IN), ASYNCHRONOUS :: recvcounts(*), displs(*)
    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_Gatherv_init(sendbuf, sendcount, sendtype, recvbuf, recvcounts, displs,
        recvtype, root, comm, info, request, ierror)
    TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
    TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
    INTEGER, INTENT(IN) :: sendcount, root
    INTEGER, INTENT(IN), ASYNCHRONOUS :: recvcounts(*), displs(*)
    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 💌

  • sendbuf — starting address of send buffer (choice). yes bestie, it's a choice, so it can be whatever type your heart desires 🫶.
  • sendcount — number of elements in send buffer (integer).
  • sendtype — datatype of send buffer elements (handle).
  • recvcounts — integer array (of length group size) containing the number of elements that are received from each process (significant only at root). so like. only the root is even looking at this bad boy 👀.
  • displs — integer array (of length group size). Entry i specifies the displacement relative to recvbuf at which to place the incoming data from process i (significant only at root). it's giving ✨custom seating chart✨ for everyone's data.
  • recvtype — datatype of recv buffer elements (significant only at root) (handle).
  • root — rank of receiving process (integer). the main character of this whole operation 👑.
  • 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).
🌈 reminder that we're only part 1 here — the rest is coming, don't go anywhere bestie 💜

💖 DESCRIPTION 💖

okay bestie, so MPI_Gatherv is literally MPI_Gather <#mpi-gather> but with ✨main character energy✨. It levels up the whole game by letting each process send a different amount of data, because recvcounts is now an array instead of one sad little number. And it also gives you way more say in where stuff lands on the root, thanks to the new argument displs. Obsessed. 🎀

The whole vibe is basically as if every process — root included — sends a message to the root:

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

and then the root does n receives:

MPI_Recv(recvbuf + disp[i] * extent(recvtype), recvcounts[i],
         recvtype, i, ...);

Messages land in the root's receive buffer in rank order, periodt. So the data from process j goes into the jth portion of the receive buffer recvbuf on process root. And that jth portion of recvbuf starts at offset displs[j] elements (counted in terms of recvtype) into recvbuf. Cute, right? 💅

The receive buffer is ignored for all nonroot processes. Not their business, honestly.

The type signature implied by sendcount, sendtype on process i must be equal to the type signature implied by recvcounts[i], recvtype at the root. Which means the amount of data sent has to equal the amount of data received, pairwise, between each process and the root. Distinct type maps between sender and receiver are still allowed tho — Example 2 below is giving exactly that ✨

All arguments to the function are significant on process root. On every other process, only sendbuf, sendcount, sendtype, root, comm matter. And the arguments root and comm must have identical values on all processes, no cap.

🚨 Technical caveat, bestie: the specification of counts, types, and displacements should not cause any location on the root to be written more than once. Such a call is erroneous. Like, that's UB territory, we do not go there. 🙈

Example 1: Now have each process send 100 ints to root, but place each set (of 100) stride ints apart at the receiving end. Use MPI_Gatherv and the displs argument to achieve this effect. Assume stride >= 100.

MPI_Comm comm;
int gsize, sendarray[100];
int root, *rbuf, stride;
int *displs, i, rcounts;
...

MPI_Comm_size(comm, &gsize);
rbuf = (int)malloc(gsize * stride * sizeof(int));
displs = (int)malloc(gsize * sizeof(int));
rcounts = (int )malloc(gsize * sizeof(int));

for (i=0; i<gsize; ++i) {
  displs[i] = i * stride;
  rcounts[i] = 100;
}
MPI_Gatherv(sendarray, 100, MPI_INT, rbuf, rcounts, displs, MPI_INT,
            root, comm);
Note that the program is erroneous if stride < 100. Just saying. 😭

Example 2: Same as Example 1 on the receiving side, but send the 100 ints from the 0th column of a 100 150 int array, in C.

MPI_Comm comm;
int gsize, sendarray[100][150];
int root, *rbuf, stride;
MPI_Datatype stype;
int displs,i, rcounts;
...

MPI_Comm_size(comm, &gsize);
rbuf = (int )malloc(gsize * stride * sizeof(int));
displs = (int)malloc(gsize * sizeof(int));
rcounts = (int )malloc(gsize * sizeof(int));

for (i=0; i<gsize; ++i) {
  displs[i] = i * stride;
  rcounts[i] = 100;
}

// Create datatype for 1 column of array
MPI_Type_vector(100, 1, 150, MPI_INT, &stype);
MPI_Type_commit( &stype );
MPI_Gatherv(sendarray, 1, stype, rbuf, rcounts, displs, MPI_INT,
            root, comm);

Example 3: Process i sends (100-i) ints from the ith column of a 100 x 150 int array, in C. It is received into a buffer with stride, as in the previous two examples.

MPI_Comm comm;
int gsize, sendarray[100][150], *sptr;
int root, *rbuf, stride, myrank;
MPI_Datatype stype;
int displs, i, rcounts;
...

MPI_Comm_size(comm, &gsize);
MPI_Comm_rank( comm, &myrank );
rbuf = (int)malloc(gsize * stride * sizeof(int));
displs = (int)malloc(gsize * sizeof(int));
rcounts = (int )malloc(gsize * sizeof(int));

for (i=0; i<gsize; ++i) {
  displs[i] = i * stride;
  rcounts[i] = 100-i; // note change from previous example
}

// Create datatype for the column we are sending
MPI_Type_vector(100-myrank, 1, 150, MPI_INT, &stype);
MPI_Type_commit( &stype );
// sptr is the address of start of "myrank" column
sptr = &sendarray[0][myrank];
MPI_Gatherv(sptr, 1, stype, rbuf, rcounts, displs, MPI_INT,
            root, comm);
Note that a different amount of data is received from each process. 👑

Example 4: Same as Example 3, but done in a different way at the sending end. We create a datatype that causes the correct striding at the sending end so that we read a column of a C array.

MPI_Comm comm;
int gsize, sendarray[100][150], *sptr;
int root, *rbuf, stride, myrank, disp[2], blocklen[2];
MPI_Datatype stype, type[2];
int displs, i, rcounts;
...

MPI_Comm_size(comm, &gsize);
MPI_Comm_rank(comm, &myrank );
rbuf = (int )alloc(gsize * stride * sizeof(int));
displs = (int )malloc(gsize * sizeof(int));
rcounts = (int)malloc(gsize * sizeof(int));

for (i=0; i<gsize; ++i) {
  displs[i] = i* stride;
  rcounts[i] = 100-i;
}
// Create datatype for one int, with extent of entire row
disp[0] = 0;
disp[1] = 150 * sizeof(int);
type[0] = MPI_INT;
type[1] = MPI_UB;
blocklen[0] = 1;
blocklen[1] = 1;

MPI_Type_struct( 2, blocklen, disp, type, &stype );
MPI_Type_commit(&stype );
sptr = &sendarray[0][myrank];
MPI_Gatherv(sptr, 100-myrank, stype, rbuf, rcounts, displs, MPI_INT,
            root, comm);

Example 5: Same as Example 3 at sending side, but at receiving side we make the stride between received blocks vary from block to block.

MPI_Comm comm;
int gsize, sendarray[100][150], *sptr;
int root, *rbuf, *stride, myrank, bufsize;
MPI_Datatype stype;
int *displs, i, *rcounts, offset;
...

MPI_Comm_size( comm, &gsize);
MPI_Comm_rank( comm, &myrank );
de = (int )malloc(gsize * sizeof(int));
...
// stride[i] for i = 0 to gsize-1 is set somehow

// set up displs and rcounts vectors first
displs = (int)malloc(gsize * sizeof(int));
rcounts = (int )malloc(gsize * sizeof(int));
offset = 0;

for (i=0; i<gsize; ++i) {
  displs[i] = offset;
  offset += stride[i];
  rcounts[i] = 100-i;
}

// the required buffer size for rbuf is now easily obtained
bufsize = displs[gsize-1]+rcounts[gsize-1];
rbuf = (int )malloc(bufsize * sizeof(int));
// Create datatype for the column we are sending
MPI_Type_vector(100-myrank, 1, 150, MPI_INT, &stype);
MPI_Type_commit( &stype );
sptr = &sendarray[0][myrank];
MPI_Gatherv(sptr, 1, stype, rbuf, rcounts, displs, MPI_INT,
            root, comm);

Example 6: Process i sends num ints from the ith column of a 100 x 150 int array, in C. The complicating factor is that the various values of num are not known to root, so a separate gather must first be run to find these out. The data is placed contiguously at the receiving end.

MPI_Comm comm;
int gsize, sendarray[100][150], *sptr;
int root, *rbuf, stride, myrank, disp[2], blocklen[2];
MPI_Datatype stype,types[2];
int *displs, i, *rcounts, num;
...

MPI_Comm_size( comm, &gsize);
MPI_Comm_rank( comm, &myrank );

// First, gather nums to root
rcounts = (int )malloc(gsize * sizeof(int));
MPI_Gather( &num, 1, MPI_INT, rcounts, 1, MPI_INT, root, comm);
// root now has correct rcounts, using these we set
// displs[] so that data is placed contiguously (or concatenated) at receive end

displs = (int)malloc(gsize * sizeof(int));
displs[0] = 0;
for (i=1; i<gsize; ++i) {
  displs[i] = displs[i-1]+rcounts[i-1];
}

// And, create receive buffer
rbuf = (int *)malloc(gsize * (displs[gsize-1]+rcounts[gsize-1]) * sizeof(int));
// Create datatype for one int, with extent of entire row
disp[0] = 0;
disp[1] = 150 * sizeof(int);
type[0] = MPI_INT;
type[1] = MPI_UB;
blocklen[0] = 1;
blocklen[1] = 1;
MPI_Type_struct(2, blocklen, disp, type, &stype );
MPI_Type_commit( &stype );
sptr = &sendarray[0][myrank];
MPI_Gatherv(sptr, num, stype, rbuf, rcounts, displs, MPI_INT, root, comm);

✨ USE OF IN-PLACE OPTION ✨

okay so the in-place option works exactly the same way it does for MPI_Gather <#mpi-gather>. 🫶 When the communicator is an intracommunicator, you can do a gather operation in-place — meaning the output buffer is used as the input buffer too. The way you do it: use the variable MPI_IN_PLACE as the value of the root process sendbuf. When you do that, sendcount and sendtype are ignored, and the root process's contribution to the gathered vector is just assumed to already be sitting in the correct place in the receive buffer. iconic, honestly 😌

Lowkey important: MPI_IN_PLACE is a special kind of value — it has the same restrictions on its use as MPI_BOTTOM. Don't get cute with it. 💀

And here's the tea 🍓: 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. fr fr.

🦋 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.

Also, 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. No vibes-based mismatches, bestie. 💅

✨ ERRORS ✨

okay so bestie, here's the tea on errors 🫖 — literally almost all MPI routines hand back an error value. In C it comes back as the return result of the function, and in Fortran it shows up in the last argument. classic, right?

So before that error value gets returned, the current MPI error handler associated with the communication object (think: communicator, window, file — the whole squad) gets called. And if there's no communication object attached to the MPI call at all? Then the call is considered attached to MPI_COMM_SELF and it'll call the associated MPI error handler instead. no cap.

Now here's the part that's giving ✨ special case ✨ realness: 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. And you can change that initial error handler — by calling MPI_Comm_set_errhandler on MPI_COMM_SELF when you're using the World model, or via the mpi_initial_errhandler CLI argument to mpiexec, or the info key to MPI_Comm_spawn/MPI_Comm_spawn_multiple. the way that's so much flexibility, we love options 💅

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. periodt.

Open MPI comes with three predefined error handlers you can just... use ✨:

  • MPI_ERRORS_ARE_FATAL — Causes the program to abort all connected MPI processes. 💀 yeah. all of them. everyone. gone.
  • 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.
  • MPI_ERRORS_RETURN — Returns an error code to the application. so polite, so demure 🎀

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

build your own, be the main character of your own error handling 😌

⚠️ Note that MPI does not guarantee that an MPI program can continue past an error. like, it might just Not. don't count on it bestie 🙈

See the MPI man page for a full list of MPI error codes. And see the Error Handling section of the MPI-3.1 standard for more information.

See also:

  • MPI_Gather

2003-2026, The Open MPI Community

so this whole thing is © The Open MPI Community, all the way from 2003 through 2026 — that's legacy, that's longevity, that's iconic 👑

andas for the vibes check on sourcing 🧚 — this installment of MPI_GATHERV(3) is dated Sep 10, 2026, straight from the official source. take care of yourself out there, don't let the error handlers catch you slippin', and remember: gatherv responsibly 💜✨

📦 where this page comes from