|
« Return to documentation listing
NAME
MPI_Type_match_size - Returns an MPI datatype of a given type and size
SYNTAX
C Syntax
#include <mpi.h>
int MPI_Type_match_size(int typeclass, int size,
MPI_Datatype *type)
Fortran Syntax
INCLUDE 'mpif.h'
MPI_TYPE_MATCH_SIZE(TYPECLASS, SIZE, TYPE, IERROR)
INTEGER TYPECLASS, SIZE, TYPE, IERROR
C++ Syntax
#include <mpi.h>
static MPI::Datatype MPI::Match_size(int typeclass, int size)
INPUT PARAMETERS
typeclass Generic type specifier (integer).
size Size, in bytes, of representation (integer).
OUTPUT PARAMETERS
type Datatype with correct type and size (handle).
IERROR Fortran only: Error status (integer).
DESCRIPTION
The function returns an MPI datatype matching a local variable of type
(typeclass, size). The returned type is a reference (handle) to a pre-
defined named datatype, not a duplicate. This type cannot be freed.
The value of typeclass may be set to one of MPI_TYPECLASS_REAL,
MPI_TYPECLASS_INTEGER, or MPI_TYPECLASS_COMPLEX, corresponding to the
desired datatype.
MPI_type_match_size can be used to obtain a size-specific type that
matches a Fortran numeric intrinsic type: first call MPI_Sizeof to com-
pute the variable size, then call MPI_Type_match_size to find a suit-
able datatype. In C and C++, use the sizeof builtin instead of
MPI_Sizeof.
It is erroneous to specify a size not supported by the compiler.
ERRORS
Almost all MPI routines return an error value; C routines as the value
of the function and Fortran routines in the last argument. C++ func-
tions do not return errors. If the default error handler is set to
MPI::ERRORS_THROW_EXCEPTIONS, then on error the C++ exception mechanism
will be used to throw an MPI:Exception object.
See the MPI man page for a full list of MPI error codes.
SEE ALSO
MPI_Sizeof
MPI_Type_get_extent
1.3.4 Nov 11, 2009 MPI_Type_match_size(3)
« Return to documentation listing
|
