MPI\_BUFFER\_ATTACH(3) Open MPI MPI\_BUFFER\_ATTACH(3)

MPI\_Buffer\_attach — Attaches a user-defined buffer for sending.

# [SYNTAX](#SYNTAX)

## [C Syntax](#C_Syntax)

```
#include <mpi.h>
int MPI_Buffer_attach(void *buf, int size)
```

## [Fortran Syntax](#Fortran_Syntax)

```
USE MPI
! or the older form: INCLUDE 'mpif.h'
MPI_BUFFER_ATTACH(BUF, SIZE, IERROR)


    <type>  BUF(*)


    INTEGER SIZE, IERROR
```

## [Fortran 2008 Syntax](#Fortran_2008_Syntax)

```
USE mpi_f08
MPI_Buffer_attach(buffer, size, ierror)


    TYPE(*), DIMENSION(..), ASYNCHRONOUS :: buffer


    INTEGER, INTENT(IN) :: size


    INTEGER, OPTIONAL, INTENT(OUT) :: ierror
```

# [INPUT PARAMETERS](#INPUT_PARAMETERS)

- **buf** : Initial buffer address (choice).
- **size** : Buffer size, in bytes (integer).

# [OUTPUT PARAMETER](#OUTPUT_PARAMETER)

•

**ierror** : Fortran only: Error status (integer).

# [DESCRIPTION](#DESCRIPTION)

Provides to MPI a buffer in the user’s memory to be used for buffering outgoing messages. The buffer is used only by messages sent in buffered mode. Only one buffer can be attached to a process at a time.

# [NOTES](#NOTES)

The size given should be the sum of the sizes of all outstanding Bsends that you intend to have, plus MPI\_BSEND\_OVERHEAD bytes for each Bsend that you do. For the purposes of calculating size, you should use MPI\_Pack\_size &lt;#mpi-pack-size&gt;. In other words, in the code

```
MPI_Buffer_attach( buf, size )
MPI_Bsend( ..., count=20, datatype=type1, ... );
MPI_Bsend( ..., count=40, datatype=type2, ... );
```

the value of size in the MPI\_Buffer\_attach call should be greater than the value computed by

```
MPI_Pack_size( 20, type1, comm, &s1 );
MPI_Pack_size( 40, type2, comm, &s2 );
size = s1 + s2 + 2 * MPI_BSEND_OVERHEAD;
```

MPI\_BSEND\_OVERHEAD gives the maximum amount of buffer space that may be used by the Bsend routines. This value is in mpi.h for C and mpif.h for Fortran.

# [ERRORS](#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 &lt;#mpi-init&gt;/MPI\_Init\_thread &lt;#mpi-init-thread&gt;, after MPI\_Finalize &lt;#mpi-finalize&gt;, 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 &lt;#mpi-comm-set-errhandler&gt; 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 &lt;#mpi-comm-spawn&gt;/MPI\_Comm\_spawn\_multiple &lt;#mpi-comm-spawn-multiple&gt;. 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.
- **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 &lt;#mpi-abort&gt; was called on that communicator. If called on a window or file, acts as if MPI\_Abort &lt;#mpi-abort&gt; 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.
- **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 &lt;#mpi-comm-create-errhandler&gt; then MPI\_Comm\_set\_errhandler &lt;#mpi-comm-set-errhandler&gt;
- MPI\_File\_create\_errhandler &lt;#mpi-file-create-errhandler&gt; then MPI\_File\_set\_errhandler &lt;#mpi-file-set-errhandler&gt;
- MPI\_Session\_create\_errhandler &lt;#mpi-session-create-errhandler&gt; then MPI\_Session\_set\_errhandler &lt;#mpi-session-set-errhandler&gt; or at MPI\_Session\_init &lt;#mpi-session-init&gt;
- MPI\_Win\_create\_errhandler &lt;#mpi-win-create-errhandler&gt; then MPI\_Win\_set\_errhandler &lt;#mpi-win-set-errhandler&gt;

Note that MPI does not guarantee that an MPI program can continue past an error.

See the MPI man page &lt;#open-mpi&gt; for a full list of MPI error codes &lt;#open-mpi-errors&gt;.

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

**See also:**

•

MPI\_Buffer\_detach &lt;#mpi-buffer-detach&gt;

# [Copyright](#Copyright)

2003-2026, The Open MPI Community

October 9, 2026

---

Document: MPI_Buffer_attach(3) from openmpi-cuda-13.2 5.0.11-r1 (Chainguard OS)
Source: https://github.com/open-mpi/ompi