MPI_EXSCAN(3) Open MPI MPI_EXSCAN(3)

MPI_Exscan, MPI_Iexscan - Computes an exclusive scan (partial reduction)

#include <mpi.h>
int MPI_Exscan(const void *sendbuf, void *recvbuf, int count,
     MPI_Datatype datatype, MPI_Op op, MPI_Comm comm)
int MPI_Iexscan(const void *sendbuf, void *recvbuf, int count,
     MPI_Datatype datatype, MPI_Op op, MPI_Comm comm,
     MPI_Request *request)
int MPI_Exscan_init(const void *sendbuf, void *recvbuf, int count,
     MPI_Datatype datatype, MPI_Op op, MPI_Comm comm,
     MPI_Info info, MPI_Request *request)

USE MPI
! or the older form: INCLUDE 'mpif.h'
MPI_EXSCAN(SENDBUF, RECVBUF, COUNT, DATATYPE, OP, COMM, IERROR)
     <type>  SENDBUF(*), RECVBUF(*)
     INTEGER COUNT, DATATYPE, OP, COMM, IERROR
MPI_IEXSCAN(SENDBUF, RECVBUF, COUNT, DATATYPE, OP, COMM, REQUEST, IERROR)
     <type>  SENDBUF(*), RECVBUF(*)
     INTEGER COUNT, DATATYPE, OP, COMM, REQUEST, IERROR
MPI_EXSCAN_INIT(SENDBUF, RECVBUF, COUNT, DATATYPE, OP, COMM, INFO, REQUEST, IERROR)
     <type>  SENDBUF(*), RECVBUF(*)
     INTEGER COUNT, DATATYPE, OP, COMM, INFO, REQUEST, IERROR

USE mpi_f08
MPI_Exscan(sendbuf, recvbuf, count, datatype, op, comm, ierror)
     TYPE(*), DIMENSION(..), INTENT(IN) :: sendbuf
     TYPE(*), DIMENSION(..) :: recvbuf
     INTEGER, INTENT(IN) :: count
     TYPE(MPI_Datatype), INTENT(IN) :: datatype
     TYPE(MPI_Op), INTENT(IN) :: op
     TYPE(MPI_Comm), INTENT(IN) :: comm
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror
MPI_Iexscan(sendbuf, recvbuf, count, datatype, op, comm, request, ierror)
     TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
     TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
     INTEGER, INTENT(IN) :: count
     TYPE(MPI_Datatype), INTENT(IN) :: datatype
     TYPE(MPI_Op), INTENT(IN) :: op
     TYPE(MPI_Comm), INTENT(IN) :: comm
     TYPE(MPI_Request), INTENT(OUT) :: request
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror
MPI_Exscan_init(sendbuf, recvbuf, count, datatype, op, comm, info, request, ierror)
     TYPE(*), DIMENSION(..), INTENT(IN), ASYNCHRONOUS :: sendbuf
     TYPE(*), DIMENSION(..), ASYNCHRONOUS :: recvbuf
     INTEGER, INTENT(IN) :: count
     TYPE(MPI_Datatype), INTENT(IN) :: datatype
     TYPE(MPI_Op), INTENT(IN) :: op
     TYPE(MPI_Comm), INTENT(IN) :: comm
     TYPE(MPI_Info), INTENT(IN) :: info
     TYPE(MPI_Request), INTENT(OUT) :: request
     INTEGER, OPTIONAL, INTENT(OUT) :: ierror

  • sendbuf: Send buffer (choice).
  • count: Number of elements in input buffer (integer).
  • datatype: Data type of elements of input buffer (handle).
  • op: Operation (handle).
  • comm: Communicator (handle).

  • recvbuf: Receive buffer (choice).
  • request: Request (handle, non-blocking only).
  • ierror: Fortran only: Error status (integer).

MPI_Exscan is used to perform an exclusive prefix reduction on data distributed across the calling processes. The operation returns, in the recvbuf of the process with rank i, the reduction (calculated according to the function op) of the values in the sendbufs of processes with ranks 0, …, i-1. Compare this with the functionality of MPI_Scan, which calculates over the range 0, …, i (inclusive). The type of operations supported, their semantics, and the constraints on send and receive buffers are as for MPI_Reduce.

The value in recvbuf on process 0 is undefined and unreliable as recvbuf is not significant for process 0. The value of recvbuf on process 1 is always the value in sendbuf on process 0.

The `in place’ option for intracommunicators is specified by passing MPI_IN_PLACE in the sendbuf argument. In this case, the input data is taken from the receive buffer, and replaced by the output data.

Note that MPI_IN_PLACE is a special kind of value; it has the same restrictions on its use as MPI_BOTTOM.

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.

MPI does not specify which process computes which operation. In particular, both processes 0 and 1 may participate in the computation even though the results for both processes’ recvbuf are degenerate. Therefore, all processes, including 0 and 1, must provide the same op.

It can be argued, from a mathematical perspective, that the definition of MPI_Exscan is unsatisfactory because the output at process 0 is undefined. The “mathematically correct” output for process 0 would be the unit element of the reduction operation. However, such a definition of an exclusive scan would not work with user-defined op functions as there is no way for MPI to “know” the unit value for these custom operations.

The reduction functions of type 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 the error handler is changed from MPI_ERRORS_ARE_FATAL to something else (e.g., MPI_ERRORS_RETURN), then no error may be indicated.

The reason for this is the performance problems in ensuring that all collective routines return the same error value.

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.
  • 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.
  • 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.

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_Op_create
  • MPI_Reduce
  • MPI_Scan

2003-2024, The Open MPI Community

February 6, 2024