Files
cpp-thirdparty/macx64/mpi/openmpi/share/man/man3/MPI_Allreduce.3
Bassem Girgis d29ef955f5 Upgrade macos
2025-03-19 08:52:56 -05:00

306 lines
9.5 KiB
Groff

.\" Man page generated from reStructuredText.
.
.TH "MPI_ALLREDUCE" "3" "Feb 14, 2025" "" "Open MPI"
.
.nr rst2man-indent-level 0
.
.de1 rstReportMargin
\\$1 \\n[an-margin]
level \\n[rst2man-indent-level]
level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]
-
\\n[rst2man-indent0]
\\n[rst2man-indent1]
\\n[rst2man-indent2]
..
.de1 INDENT
.\" .rstReportMargin pre:
. RS \\$1
. nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]
. nr rst2man-indent-level +1
.\" .rstReportMargin post:
..
.de UNINDENT
. RE
.\" indent \\n[an-margin]
.\" old: \\n[rst2man-indent\\n[rst2man-indent-level]]
.nr rst2man-indent-level -1
.\" new: \\n[rst2man-indent\\n[rst2man-indent-level]]
.in \\n[rst2man-indent\\n[rst2man-indent-level]]u
..
.sp
\fI\%MPI_Allreduce\fP, \fI\%MPI_Iallreduce\fP, \fI\%MPI_Allreduce_init\fP \- Combines values
from all processes and distributes the result back to all processes.
.SH SYNTAX
.SS C Syntax
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
#include <mpi.h>
int MPI_Allreduce(const void *sendbuf, void *recvbuf, int count,
MPI_Datatype datatype, MPI_Op op, MPI_Comm comm)
int MPI_Iallreduce(const void *sendbuf, void *recvbuf, int count,
MPI_Datatype datatype, MPI_Op op, MPI_Comm comm,
MPI_Request *request)
int MPI_Allreduce_init(const void *sendbuf, void *recvbuf, int count,
MPI_Datatype datatype, MPI_Op op, MPI_Comm comm,
MPI_Info info, MPI_Request *request)
.ft P
.fi
.UNINDENT
.UNINDENT
.SS Fortran Syntax
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
USE MPI
! or the older form: INCLUDE \(aqmpif.h\(aq
MPI_ALLREDUCE(SENDBUF, RECVBUF, COUNT, DATATYPE, OP, COMM, IERROR)
<type> SENDBUF(*), RECVBUF(*)
INTEGER COUNT, DATATYPE, OP, COMM, IERROR
MPI_IALLREDUCE(SENDBUF, RECVBUF, COUNT, DATATYPE, OP, COMM, REQUEST, IERROR)
<type> SENDBUF(*), RECVBUF(*)
INTEGER COUNT, DATATYPE, OP, COMM, REQUEST, IERROR
MPI_ALLREDUCE_INIT(SENDBUF, RECVBUF, COUNT, DATATYPE, OP, COMM, INFO, REQUEST, IERROR)
<type> SENDBUF(*), RECVBUF(*)
INTEGER COUNT, DATATYPE, OP, COMM, INFO, REQUEST, IERROR
.ft P
.fi
.UNINDENT
.UNINDENT
.SS Fortran 2008 Syntax
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
USE mpi_f08
MPI_Allreduce(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_Iallreduce(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_Allreduce_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
.ft P
.fi
.UNINDENT
.UNINDENT
.SH INPUT PARAMETERS
.INDENT 0.0
.IP \(bu 2
\fBsendbuf\fP: Starting address of send buffer (choice).
.IP \(bu 2
\fBcount\fP: Number of elements in send buffer (integer).
.IP \(bu 2
\fBdatatype\fP: Datatype of elements of send buffer (handle).
.IP \(bu 2
\fBop\fP: Operation (handle).
.IP \(bu 2
\fBcomm\fP: Communicator (handle).
.IP \(bu 2
\fBinfo\fP: Info (handle, persistent only).
.UNINDENT
.SH OUTPUT PARAMETERS
.INDENT 0.0
.IP \(bu 2
\fBrecvbuf\fP: Starting address of receive buffer (choice).
.IP \(bu 2
\fBrequest\fP: Request (handle, non\-blocking only).
.IP \(bu 2
\fBierror\fP: Fortran only: Error status (integer).
.UNINDENT
.SH DESCRIPTION
.sp
Same as \fI\%MPI_Reduce\fP except that the result appears in the receive buffer
of all the group members.
.sp
\fBExample 1:\fP A routine that computes the product of a vector and an
array that are distributed across a group of processes and returns the
answer at all nodes (compare with Example 2, with \fI\%MPI_Reduce\fP, below).
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
SUBROUTINE PAR_BLAS2(m, n, a, b, c, comm)
REAL a(m), b(m,n) ! local slice of array
REAL c(n) ! result
REAL sum(n)
INTEGER n, comm, i, j, ierr
! local sum
DO j= 1, n
sum(j) = 0.0
DO i = 1, m
sum(j) = sum(j) + a(i)*b(i,j)
END DO
END DO
! global sum
CALL MPI_ALLREDUCE(sum, c, n, MPI_REAL, MPI_SUM, comm, ierr)
! return result at all nodes
RETURN
.ft P
.fi
.UNINDENT
.UNINDENT
.sp
\fBExample 2:\fP A routine that computes the product of a vector and an
array that are distributed across a group of processes and returns the
answer at node zero.
.INDENT 0.0
.INDENT 3.5
.sp
.nf
.ft C
SUBROUTINE PAR_BLAS2(m, n, a, b, c, comm)
REAL a(m), b(m,n) ! local slice of array
REAL c(n) ! result
REAL sum(n)
INTEGER n, comm, i, j, ierr
! local sum
DO j= 1, n
sum(j) = 0.0
DO i = 1, m
sum(j) = sum(j) + a(i)*b(i,j)
END DO
END DO
! global sum
CALL MPI_REDUCE(sum, c, n, MPI_REAL, MPI_SUM, 0, comm, ierr)
! return result at node zero (and garbage at the other nodes)
RETURN
.ft P
.fi
.UNINDENT
.UNINDENT
.SH USE OF IN-PLACE OPTION
.sp
When the communicator is an intracommunicator, you can perform an
all\-reduce operation in\-place (the output buffer is used as the input
buffer). Use the variable MPI_IN_PLACE as the value of \fIsendbuf\fP at all
processes.
.sp
Note that MPI_IN_PLACE is a special kind of value; it has the same
restrictions on its use as MPI_BOTTOM.
.sp
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.
.SH WHEN COMMUNICATOR IS AN INTER-COMMUNICATOR
.sp
When the communicator is an inter\-communicator, the reduce operation
occurs in two phases. The data is reduced from all the members of the
first group and received by all the members of the second group. Then
the data is reduced from all the members of the second group and
received by all the members of the first. The operation exhibits a
symmetric, full\-duplex behavior.
.sp
When the communicator is an intra\-communicator, these groups are the
same, and the operation occurs in a single phase.
.SH NOTES ON COLLECTIVE OPERATIONS
.sp
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
\fI\%MPI_Abort\fP 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.
.SH ERRORS
.sp
Almost all MPI routines return an error value; C routines as the return result
of the function and Fortran routines in the last argument.
.sp
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
\fI\%MPI_Init\fP/\fI\%MPI_Init_thread\fP, after \fI\%MPI_Finalize\fP, or when using the Sessions
Model exclusively) the error raises the initial error handler. The initial
error handler can be changed by calling \fI\%MPI_Comm_set_errhandler\fP on
MPI_COMM_SELF when using the World model, or the mpi_initial_errhandler CLI
argument to mpiexec or info key to \fI\%MPI_Comm_spawn\fP/\fI\%MPI_Comm_spawn_multiple\fP\&.
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.
.sp
Open MPI includes three predefined error handlers that can be used:
.INDENT 0.0
.IP \(bu 2
\fBMPI_ERRORS_ARE_FATAL\fP
Causes the program to abort all connected MPI processes.
.IP \(bu 2
\fBMPI_ERRORS_ABORT\fP
An error handler that can be invoked on a communicator,
window, file, or session. When called on a communicator, it
acts as if \fI\%MPI_Abort\fP was called on that communicator. If
called on a window or file, acts as if \fI\%MPI_Abort\fP 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.
.IP \(bu 2
\fBMPI_ERRORS_RETURN\fP
Returns an error code to the application.
.UNINDENT
.sp
MPI applications can also implement their own error handlers by calling:
.INDENT 0.0
.IP \(bu 2
\fI\%MPI_Comm_create_errhandler\fP then \fI\%MPI_Comm_set_errhandler\fP
.IP \(bu 2
\fI\%MPI_File_create_errhandler\fP then \fI\%MPI_File_set_errhandler\fP
.IP \(bu 2
\fI\%MPI_Session_create_errhandler\fP then \fI\%MPI_Session_set_errhandler\fP or at \fI\%MPI_Session_init\fP
.IP \(bu 2
\fI\%MPI_Win_create_errhandler\fP then \fI\%MPI_Win_set_errhandler\fP
.UNINDENT
.sp
Note that MPI does not guarantee that an MPI program can continue past
an error.
.sp
See the \fI\%MPI man page\fP for a full list of \fI\%MPI error codes\fP\&.
.sp
See the Error Handling section of the MPI\-3.1 standard for
more information.
.SH COPYRIGHT
2003-2025, The Open MPI Community
.\" Generated by docutils manpage writer.
.