MPI_OP_CREATE(3)

💖 MPI_OP_CREATE(3) — Open MPI 💖

🌸 NAME 🌸

MPI_Op_create — Creates a user-defined combination function handle. No cap, this is the glow-up for custom reduction ops. ✨

✨ SYNTAX ✨

🧸 C Syntax 🧸

#include <mpi.h>

int MPI_Op_create(MPI_User_function *function, int commute,
               MPI_Op *op)

🎀 Fortran Syntax 🎀

USE MPI
! or the older form: INCLUDE 'mpif.h'
MPI_OP_CREATE(FUNCTION, COMMUTE, OP, IERROR)
     EXTERNAL        FUNCTION
     LOGICAL COMMUTE
     INTEGER OP, IERROR

🦋 Fortran 2008 Syntax 🦋

USE mpi_f08
MPI_Op_create(user_fn, commute, op, ierror)
     PROCEDURE(MPI_User_function) :: user_fn
     LOGICAL, INTENT(IN) :: commute
     TYPE(MPI_Op), INTENT(OUT) :: op
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror

💖 INPUT PARAMETERS 💖

• function — User-defined function (function). This is your little custom combine machine.
• commute — True if commutative; false otherwise. Order matters or it doesn't — choose wisely, bestie.

🫶 OUTPUT PARAMETERS 🫶

• op — Operation (handle). This is the handle you'll pass around later.
• ierror — Fortran only: Error status (integer). Fortran girlies get the extra status arg.

🌈 DESCRIPTION 🌈

Okay so MPI_Op_create binds a user-defined global operation to an op handle that can subsequently be used in MPI_Reduce, MPI_Allreduce, MPI_Reduce_scatter, and MPI_Scan. It's giving "make your own reduction, main character energy." 💅

The user-defined operation is assumed to be associative. If commute = true, then the operation should be both commutative and associative. If commute = false, then the order of operands is fixed and is defined to be in ascending, process rank order, beginning with process zero. The order of evaluation can be changed, taking advantage of the associativity of the operation. If commute = true then the order of evaluation can be changed, taking advantage of commutativity and associativity. Literally the whole vibe check is "can I reorder this or not?"

function is the user-defined function, which must have the following four arguments: invec, inoutvec, len, and datatype. Four args, no more, no less.

The ANSI-C prototype for the function is the following:

typedef void MPI_User_function(void *invec, void *inoutvec,
                               int *len,
                               MPI_Datatype *datatype);

The Fortran declaration of the user-defined function appears below.

FUNCTION USER_FUNCTION( INVEC(*), INOUTVEC(*), LEN, TYPE)
<type> INVEC(LEN), INOUTVEC(LEN)
 INTEGER LEN, TYPE

The datatype argument is a handle to the data type that was passed into the call to MPI_Reduce. It's the type info, not a mystery box.

The user reduce function should be written such that the following holds: Let u[0], …, u[len-1] be the len elements in the communication buffer described by the arguments invec, len, and datatype when the function is invoked; let v[0], …, v[len-1] be len elements in the communication buffer described by the arguments inoutvec, len, and datatype when the function is invoked; let w[0], …, w[len-1] be len elements in the communication buffer described by the arguments inoutvec, len, and datatype when the function returns; then w[i] = u[i] o v[i], for i=0 ,…, len-1, where o is the reduce operation that the function computes. That's the whole contract, fr fr.

Informally, we can think of invec and inoutvec as arrays of len elements that function is combining. The result of the reduction over-writes values in inoutvec, hence the name. Each invocation of the function results in the pointwise evaluation of the reduce operator on len elements: i.e, the function returns in inoutvec[i] the value invec[i] o inoutvec[i], for i = 0…, count-1, where o is the combining operation computed by the function. Pointwise, bestie. One element at a time.

By internally comparing the value of the datatype argument to known, global handles, it is possible to overload the use of a single user-defined function for several different data types. One function, many types — lowkey iconic.

General datatypes may be passed to the user function. However, use of datatypes that are not contiguous is likely to lead to inefficiencies. Not forbidden, just kinda slow. You've been warned.

Big warning energy: No MPI communication function may be called inside the user function. MPI_Abort may be called inside the function in case of an error. Do not call MPI comms in there, periodt.

🎀 NOTES 🎀

Suppose one defines a library of user-defined reduce functions that are overloaded: The datatype argument is used to select the right execution path at each invocation, according to the types of the operands. The type handle is basically the vibe selector.

The user-defined reduce function cannot “decode” the datatype argument that it is passed, and cannot identify, by itself, the correspondence between the datatype handles and the datatype they represent. This correspondence was established when the datatypes were created. You gotta remember that mapping yourself.

Before the library is used, a library initialization preamble must be executed. This preamble code will define the datatypes that are used by the library and store handles to these datatypes in global, static variables that are shared by the user code and the library code. Setup first, then slay.

Example: Example of user-defined reduce:

Compute the product of an array of complex numbers, in C.

typedef struct {
    double real,imag;
} Complex;

/* the user-defined function
 */
void myProd( Complex *in, Complex *inout, int *len,
             MPI_Datatype *dptr )
{
    int i;
    Complex c;

for (i=0; i< *len; ++i) {
        c.real = inout->real*in->real -
                   inout->imag*in->imag;
        c.imag = inout->real*in->imag +
                   inout->imag*in->real;
        *inout = c;
        in++; inout++;
    }
}

/* and, to call it...
 */
...

/* each process has an array of 100 Complexes
     */
    Complex a[100], answer[100];
    MPI_Op myOp;
    MPI_Datatype ctype;

/* explain to MPI how type Complex is defined
     */
   MPI_Type_contiguous( 2, MPI_DOUBLE, &ctype );
    MPI_Type_commit( &ctype );
    /* create the complex-product user-op
     */
    MPI_Op_create( myProd, True, &myOp );

    MPI_Reduce( a, answer, 100, ctype, myOp, root, comm );

    /* At this point, the answer, which consists of 100 Complexes,
     * resides on process root
     */

The Fortran version of MPI_Reduce will invoke a user-defined reduce function using the Fortran calling conventions and will pass a Fortran-type datatype argument; the C version will use C calling convention and the C representation of a datatype handle. Users who plan to mix languages should define their reduction functions accordingly. Mix languages at your own risk, bestie.

🦋 NOTES ON COLLECTIVE OPERATIONS 🦋

The reduction functions (MPI_Op) do not return an error value. As a result, if the functions detect an error, all they can do is either call MPI_Abort or silently skip the problem. Thus, if you change the error handler from MPI_ERRORS_ARE_FATAL to something else, for example, MPI_ERRORS_RETURN, then no error may be indicated. That's a real "silent treatment" moment, and not the cute kind. 💀

The reason for this is the performance problems in ensuring that all collective routines return the same error value. Performance said "not today," and honestly? Fair.

💜 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. C girlies check the return; Fortran girlies check the last arg.

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. Error-handler lore is real, iykyk.

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

• MPI_ERRORS_ARE_FATAL — Causes the program to abort all connected MPI processes. Everybody out. Immediately.
• 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. Context-dependent abort energy.
• MPI_ERRORS_RETURN — Returns an error code to the application. You get the code back, bestie.

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. No cap, this is serious.

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_Reduce
• MPI_Reduce_scatter
• MPI_Allreduce
• MPI_Scan
• MPI_Op_free

🌟 COPYRIGHT 🌟

2003-2026, The Open MPI Community

---

💌 Sign-off: source/version is Open MPI, date is Sep 11, 2026, and this iconic little manual is MPI_OP_CREATE(3). You ate that, bestie. Periodt. 💌