162 lines
3.4 KiB
Groff
162 lines
3.4 KiB
Groff
.TH MPI_Op_create 3 "2/3/2025" " " "MPI"
|
|
.SH NAME
|
|
MPI_Op_create \- Creates a user-defined combination function handle
|
|
.SH SYNOPSIS
|
|
.nf
|
|
.fi
|
|
.nf
|
|
int MPI_Op_create(MPI_User_function *user_fn, int commute, MPI_Op *op)
|
|
.fi
|
|
|
|
.nf
|
|
int MPI_Op_create_c(MPI_User_function_c *user_fn, int commute, MPI_Op *op)
|
|
.fi
|
|
|
|
|
|
.SH INPUT PARAMETERS
|
|
.PD 0
|
|
.TP
|
|
.B user_fn
|
|
- user defined function (function)
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B commute
|
|
- true if commutative; false otherwise. (logical)
|
|
.PD 1
|
|
|
|
.SH OUTPUT PARAMETERS
|
|
.PD 0
|
|
.TP
|
|
.B op
|
|
- operation (handle)
|
|
.PD 1
|
|
|
|
.SH NOTES ON THE USER FUNCTION
|
|
The calling list for the user function type is
|
|
.nf
|
|
typedef void (MPI_User_function) (void * a,
|
|
void * b, int * len, MPI_Datatype *);
|
|
.fi
|
|
|
|
where the operation is
|
|
.I b[i] = a[i] op b[i]
|
|
, for
|
|
.I i=0,...,len-1
|
|
\&.
|
|
A pointer
|
|
to the datatype given to the MPI collective computation routine (i.e.,
|
|
.I MPI_Reduce
|
|
,
|
|
.I MPI_Allreduce
|
|
,
|
|
.I MPI_Scan
|
|
, or
|
|
.I MPI_Reduce_scatter
|
|
) is also
|
|
passed to the user-specified routine.
|
|
|
|
.SH NOTES ON COLLECTIVE OPERATIONS
|
|
|
|
The reduction functions (
|
|
.I MPI_Op
|
|
) do not return an error value. As a result,
|
|
if the functions detect an error, all they can do is either call
|
|
.I MPI_Abort
|
|
or silently skip the problem. Thus, if you change the error handler from
|
|
.I MPI_ERRORS_ARE_FATAL
|
|
to something else, for example,
|
|
.I 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.
|
|
|
|
.SH THREAD AND INTERRUPT SAFETY
|
|
|
|
This routine is thread-safe. This means that this routine may be
|
|
safely used by multiple threads without the need for any user-provided
|
|
thread locks. However, the routine is not interrupt safe. Typically,
|
|
this is due to the use of memory allocation routines such as
|
|
.I malloc
|
|
or other non-MPICH runtime routines that are themselves not interrupt-safe.
|
|
|
|
.SH NOTES FOR FORTRAN
|
|
All MPI routines in Fortran (except for
|
|
.I MPI_WTIME
|
|
and
|
|
.I MPI_WTICK
|
|
) have
|
|
an additional argument
|
|
.I ierr
|
|
at the end of the argument list.
|
|
.I ierr
|
|
is an integer and has the same meaning as the return value of the routine
|
|
in C. In Fortran, MPI routines are subroutines, and are invoked with the
|
|
.I call
|
|
statement.
|
|
|
|
All MPI objects (e.g.,
|
|
.I MPI_Datatype
|
|
,
|
|
.I MPI_Comm
|
|
) are of type
|
|
.I INTEGER
|
|
in Fortran.
|
|
|
|
.SH ERRORS
|
|
|
|
All MPI routines (except
|
|
.I MPI_Wtime
|
|
and
|
|
.I MPI_Wtick
|
|
) return an error value;
|
|
C routines as the value of the function and Fortran routines in the last
|
|
argument. Before the value is returned, the current MPI error handler is
|
|
called. By default, this error handler aborts the MPI job. The error handler
|
|
may be changed with
|
|
.I MPI_Comm_set_errhandler
|
|
(for communicators),
|
|
.I MPI_File_set_errhandler
|
|
(for files), and
|
|
.I MPI_Win_set_errhandler
|
|
(for
|
|
RMA windows). The MPI-1 routine
|
|
.I MPI_Errhandler_set
|
|
may be used but
|
|
its use is deprecated. The predefined error handler
|
|
.I MPI_ERRORS_RETURN
|
|
may be used to cause error values to be returned.
|
|
Note that MPI does
|
|
.B not
|
|
guarantee that an MPI program can continue past
|
|
an error; however, MPI implementations will attempt to continue whenever
|
|
possible.
|
|
|
|
.PD 0
|
|
.TP
|
|
.B MPI_SUCCESS
|
|
- No error; MPI routine completed successfully.
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_ARG
|
|
- Invalid argument. Some argument is invalid and is not
|
|
identified by a specific error class (e.g.,
|
|
.I MPI_ERR_RANK
|
|
).
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_OTHER
|
|
- Other error; use
|
|
.I MPI_Error_string
|
|
to get more information
|
|
about this error code.
|
|
.PD 1
|
|
|
|
.SH SEE ALSO
|
|
MPI_Op_free
|
|
.br
|