MPI_ALLTOALLW(3)

📦

version 5.0.11 · 16 versions

💫 MPI_ALLTOALLW(3) 💫

okay so this one's from the Open MPI manual, bestie — it's the big all-to-all. Sit down, hydrate, we're doing this. 🍓

MPI_Alltoallw, MPI_Ialltoallw, MPI_Alltoallw_init — every process sends data of different types to, and receives data of different types from, all processes. yes literally every single one. main character collective behavior fr fr 👑

✨ SYNTAX ✨

🌸 C Syntax

#include <mpi.h>

int MPI_Alltoallw(const void *sendbuf, const int sendcounts[],
     const int sdispls[], const MPI_Datatype sendtypes[],
     void *recvbuf, const int recvcounts[], const int rdispls[],
     const MPI_Datatype recvtypes[], MPI_Comm comm)

int MPI_Ialltoallw(const void *sendbuf, const int sendcounts[],
     const int sdispls[], const MPI_Datatype sendtypes[],
     void *recvbuf, const int recvcounts[], const int rdispls[],
     const MPI_Datatype recvtypes[], MPI_Comm comm,
     MPI_Request *request)

int MPI_Alltoallw_init(const void *sendbuf, const int sendcounts[],
     const int sdispls[], const MPI_Datatype sendtypes[],
     void *recvbuf, const int recvcounts[], const int rdispls[],
     const MPI_Datatype recvtypes[], MPI_Comm comm, MPI_Info info,
     MPI_Request *request)

🌸 Fortran Syntax

USE MPI
! or the older form: INCLUDE 'mpif.h'
MPI_ALLTOALLW(SENDBUF, SENDCOUNTS, SDISPLS, SENDTYPES,
     RECVBUF, RECVCOUNTS, RDISPLS, RECVTYPES, COMM, IERROR)

     <type>  SENDBUF(*), RECVBUF(*)
     INTEGER SENDCOUNTS(*), SDISPLS(*), SENDTYPES(*)
     INTEGER RECVCOUNTS(*), RDISPLS(*), RECVTYPES(*)
     INTEGER COMM, IERROR

MPI_IALLTOALLW(SENDBUF, SENDCOUNTS, SDISPLS, SENDTYPES,
     RECVBUF, RECVCOUNTS, RDISPLS, RECVTYPES, COMM, REQUEST, IERROR)

     <type>  SENDBUF(*), RECVBUF(*)
     INTEGER SENDCOUNTS(*), SDISPLS(*), SENDTYPES(*)
     INTEGER RECVCOUNTS(*), RDISPLS(*), RECVTYPES(*)
     INTEGER COMM, REQUEST, IERROR

MPI_ALLTOALLW_INIT(SENDBUF, SENDCOUNTS, SDISPLS, SENDTYPES,
     RECVBUF, RECVCOUNTS, RDISPLS, RECVTYPES, COMM, INFO, REQUEST, IERROR)

     <type>  SENDBUF(*), RECVBUF(*)
     INTEGER SENDCOUNTS(*), SDISPLS(*), SENDTYPES(*)
     INTEGER RECVCOUNTS(*), RDISPLS(*), RECVTYPES(*)
     INTEGER COMM, INFO, REQUEST, IERROR

🌸 Fortran 2008 Syntax

USE mpi_f08
MPI_Alltoallw(sendbuf, sendcounts, sdispls, sendtypes, recvbuf, recvcounts,
             rdispls, recvtypes, comm, ierror)

     TYPE(*), DIMENSION(..), INTENT(IN) :: sendbuf
     TYPE(*), DIMENSION(..) :: recvbuf
     INTEGER, INTENT(IN) :: sendcounts(*), sdispls(*), recvcounts(*),
     rdispls(*)
     TYPE(MPI_Datatype), INTENT(IN) :: sendtypes(*)
     TYPE(MPI_Datatype), INTENT(IN) :: recvtypes(*)
     TYPE(MPI_Comm), INTENT(IN) :: comm
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror

MPI_Ialltoallw(sendbuf, sendcounts, sdispls, sendtypes, recvbuf,
             recvcounts, rdispls, recvtypes, comm, request, ierror)

     TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
     TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
     INTEGER, INTENT(IN), ASYNCHRONOUS :: sendcounts(*), sdispls(*),
     recvcounts(*), rdispls(*)
     TYPE(MPI_Datatype), INTENT(IN), ASYNCHRONOUS :: sendtypes(*),
     recvtypes(*)
     TYPE(MPI_Comm), INTENT(IN) :: comm
     TYPE(MPI_Request), INTENT(OUT) :: request
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror

MPI_Alltoallw_init(sendbuf, sendcounts, sdispls, sendtypes, recvbuf,
             recvcounts, rdispls, recvtypes, comm, fIinfo, request, ierror)

     TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
     TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
     INTEGER, INTENT(IN), ASYNCHRONOUS :: sendcounts(*), sdispls(*),
     recvcounts(*), rdispls(*)
     TYPE(MPI_Datatype), INTENT(IN), ASYNCHRONOUS :: sendtypes(*),
     recvtypes(*)
     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 the send buffer. the vibes start here ✨
sendcounts — integer array where entry i says how many elements you're sending to rank i.
sdispls — integer array where entry i gives the displacement (in bytes, offset from sendbuf) from which you send data to rank i. bytes!! not elements!! remember this, it matters later 😭
sendtypes — datatype array where entry i is the datatype used when sending to rank i.
recvcounts — integer array where entry j says how many elements you're receiving from rank j.
rdispls — integer array where entry j gives the displacement (in bytes, offset from recvbuf) where data from rank j gets written.
recvtypes — datatype array where entry j is the datatype used when receiving from rank j.
comm — the communicator the data gets exchanged over. the group chat itself 🫶
info — Info (handle, persistent only).

🦋 OUTPUT PARAMETERS 🦋

recvbuf — address of the receive buffer. where the good stuff lands 💖
request — Request (handle, non-blocking only).
ierror — Fortran only: error status.

🌈 DESCRIPTION 🌈

MPI_Alltoallw is the generalized collective — every process sends data to and receives data from literally every other process. The way it levels up from MPI_Alltoallv is that you can specify the datatype of individual data blocks, on top of displacement and element count. highkey the final boss of all-to-all 😤

Think of it like this, where each process does 2n independent point-to-point communications (n being the number of processes in communicator comm), including talking to itself (yes, self-care counts as communication 💅):

MPI_Comm_size(comm, &n);
for (i = 0, i < n; i++)
    MPI_Send(sendbuf + sdispls[i], sendcounts[i],
        sendtypes[i], i, ..., comm);
for (i = 0, i < n; i++)
    MPI_Recv(recvbuf + rdispls[i], recvcounts[i],
        recvtypes[i], i, ..., comm);

Process j sends the k-th block of its local sendbuf to process k, and process k places that data in the j-th block of its local recvbuf. it's giving perfectly choreographed group dance 🧚

When two processes exchange data, each one can pass different element count and datatype arguments — the only rule is that the sender specifies the same amount of data to send in bytes as the receiver expects to receive. match the byte count and you're golden ✨

Also notice: process i can send a different amount of data to process j than it receives back from process j. And a process can send completely different amounts and types of data to different processes in the same communicator. no cap, full freedom.

💀 WHEN COMMUNICATOR IS AN INTER-COMMUNICATOR

When the communicator is an inter-communicator, the gather operation happens in two phases. Data is gathered from all the members of the first group and received by all the members of the second group. Then data is gathered from all the members of the second group and received by all the members of the first. The whole thing exhibits a symmetric, full-duplex behavior. it's giving twin flame energy 🔥

The first group defines the root process.
The root process uses MPI_ROOT as the value of root.
All other processes in the first group use MPI_PROC_NULL as the value of root.
All processes in the second group use the rank of the root process in the first group as the value of root.

When the communicator is an intra-communicator, these groups are the same and the operation occurs in a single phase. slay, one and done 💅

🎀 USE OF IN-PLACE OPTION 🎀

When the communicator is an intracommunicator you can do an all-to-all operation in-place — meaning the output buffer is used as the input buffer. Just pass the variable MPI_IN_PLACE as the value of sendbuf.

When you do that: sendcounts, sdispls, and sendtypes are ignored. The input data of each process is assumed to be sitting in the area where that process would receive its own contribution to the receive buffer. recycling era ♻️✨

⭐ NOTES ⭐

The specification of counts, types, and displacements should not cause any location to be written more than once. fr fr, don't do that 🙈
All arguments on all processes are significant. The comm argument in particular must describe the same communicator on all processes. everybody on the same page, always 🫶
The offsets of sdispls and rdispls are measured in bytes. Compare this to MPI_Alltoallv, where these offsets are measured in units of sendtype and recvtype, respectively. this is the glow-up difference, memorize 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.

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. goodbye everyone 💀
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.

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, no promises bestie 😬

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_Alltoall
MPI_Alltoallv

👑 COPYRIGHT 👑

2003-2026, The Open MPI Community

and that's the whole thing, bestie — go forth and exchange your differently-typed data with every single process 💖✨ This gorgeous page dropped on Sep 11, 2026 (the MPI_ALLTOALLW(3) one, you know the one), brought to you by your fave, the Open MPI girlies. mwah 🫶🎀🌷

📦 where this page comes from

arch rolling: openmpi 5.0.11-1 · BSD-3-Clause AND LicenseRef-MPICH
💖 girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on 2026-11-06: a language model's rewrite of the original, under its terms