MPI_FETCH_AND_OP(3)

📦
version 5.0.11 · 16 versions
, in arch rolling

💅 MPI_FETCH_AND_OP(3) — Open MPI, bestie edition 🎀

Okay so this is the Open MPI version of the MPI_Fetch_and_op man page, and honestly? It's giving "atomic queen." Let's get into it ✨

🌸 NAME 🌸

MPI_Fetch_and_op — combines the contents of the origin buffer with that of a target buffer and returns the target buffer value. No cap, that's literally the whole vibe 🫶

✨ SYNTAX ✨

🍓 C Syntax

#include <mpi.h>

int MPI_Fetch_and_op(const void *origin_addr, void *result_addr,
     MPI_Datatype datatype, int target_rank, MPI_Aint target_disp,
     MPI_Op op, MPI_Win win)

🦋 Fortran Syntax

USE MPI
! or the older form: INCLUDE 'mpif.h'
MPI_FETCH_AND_OP(ORIGIN_ADDR, RESULT_ADDR, DATATYPE, TARGET_RANK,
                 TARGET_DISP, OP, WIN, IERROR)
     <type> ORIGIN_ADDR, RESULT_ADDR(*)
     INTEGER(KIND=MPI_ADDRESS_KIND) TARGET_DISP
     INTEGER DATATYPE, TARGET_RANK, OP, WIN, IERROR

🌈 Fortran 2008 Syntax

USE mpi_f08
MPI_Fetch_and_op(origin_addr, result_addr, datatype, target_rank,
             target_disp, op, win, ierror)
     TYPE(*), DIMENSION(..), INTENT(IN) :: origin_addr
     TYPE(*), DIMENSION(..) :: result_addr
     TYPE(MPI_Datatype), INTENT(IN) :: datatype
     INTEGER, INTENT(IN) :: target_rank
     INTEGER(KIND=MPI_ADDRESS_KIND), INTENT(IN) :: target_disp
     TYPE(MPI_Op), INTENET(IN) :: op
     TYPE(MPI_Win), INTENT(IN) :: win
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror
(Yes, INTENET(IN) is in here exactly like that — copy it verbatim, don't "fix" it, that's the assignment 😌)

💖 INPUT PARAMETERS 💖

  • origin_addr — initial address of buffer (choice). This is where your value starts its little journey 💫
  • result_addr — initial address of result buffer (choice). The old target value lands here, bestie 🎁
  • datatype — data type of the entry in origin, result, and target buffers (handle). One type to rule all three 👑
  • target_rank — rank of target (nonnegative integer). Gotta be nonnegative, no negativity allowed 🙅
  • target_disp — displacement from start of window to beginning of target buffer (nonnegative integer). Also has to behave itself and be nonnegative 🌸
  • op — reduce operation (handle). The personality of the whole operation, lowkey 💅
  • win — window object (handle). The whole neighborhood this is happening in 🏡

🎀 OUTPUT PARAMETER 🎀

  • ierror — Fortran only: error status (integer). For the C girlies, the error comes back as the return value instead 🫶

🔥 DESCRIPTION 🔥

So what it does: it accumulates one element of type datatype from the origin buffer (origin_addr) over to the buffer at offset target_disp, in the target window specified by target_rank and win, using the operation op — and then it drops the contents of the target buffer, from before the accumulation, into the result buffer result_addr. Literally "here's what you had before I touched it" energy 😭💖

The origin and result buffers (origin_addr and result_addr) must be disjoint. Not optional, not negotiable, they cannot overlap. Any of the predefined operations for MPI_Rreduce, as well as MPI_NO_OP or MPI_REPLACE, can be specified as op; user-defined functions cannot be used. The datatype argument must be a predefined datatype. And the whole operation is executed atomically — it's an all-at-once main character moment, no messy in-between states ✨

A new predefined operation, MPI_REPLACE, is defined. It corresponds to the associative function f(a, b) =b; that is, the current value in the target memory is replaced by the value supplied by the origin. Out with the old, in with the new, periodt 💅

A new predefined operation, MPI_NO_OP, is defined. It corresponds to the associative function f(a, b) = a; that is the current value in the target memory is returned in the result buffer at the origin and no operation is performed on the target buffer. It's giving "I'm just here to observe, not to participate" 🙈

🌟 NOTES 🌟

Real talk: it is the user's responsibility to guarantee that, when using the accumulate functions, the target displacement argument is such that accesses to the window are properly aligned according to the data type arguments in the call to the MPI_Fetch_and_op function. Misaligned = you did that, not us 😬

💀 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 — collect them all 🎀:

  • MPI_ERRORS_ARE_FATAL — causes the program to abort all connected MPI processes. Girl, everybody's going down together 💀
  • 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. Selective destruction, we love a targeted queen 🔥
  • MPI_ERRORS_RETURN — returns an error code to the application. Chill, hands you the receipt and moves on 🧾

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, it might just be over. Fr fr 😭

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_Get_accumulate
  • MPI_Reduce

2003-2026, The Open MPI Community

Okay that's the whole page, you ate that 💅✨ This was the Open MPI edition of MPI_FETCH_AND_OP(3), dated Sep 11, 2026 — the footer said so and I would never lie to you 🫶 Go forth and fetch-and-op responsibly, bestie 🎀🌈

📦 where this page comes from