MPI_TYPE_CREATE_HVECTOR(3)MPI_TYPE_CREATE_HVECTOR(3)NAME
MPI_Type_create_hvector - Creates a vector (strided) data type with
offset in bytes
SYNOPSIS
C:
#include <mpi.h>
int MPI_Type_create_hvector( count, blocklen, stride,
old_type,
newtype )
int count;
int blocklen;
MPI_Aint stride;
MPI_Datatype old_type;
MPI_Datatype *newtype;
C++:
#include <mpi.h>
Datatype Datatype::Create_hvector(
int count,
int blocklength,
Aint stride) const
Fortran:
INCLUDE "mpif.h" (or USE MPI)
INTEGER count, blocklength, oldtype, newtype,
ierror
INTEGER(KIND=MPI_ADDRESS_KIND) stride
CALL MPI_TYPE_CREATE_HVECTOR( count, blocklength, stride,
oldtype, newtype, ierror)
DESCRIPTION
The MPI_Type_create_hvector routine creates a vector (strided) data type
with offset in bytes. The MPI_Type_create_hvector routine is an MPI-2
implementation replacing the MPI-1 MPI_Type_hvector routine which has
been deprecated. This routine differs from the MPI-1 routine in that in
the Fortran implementation the stride argument is of type
MPI_ADDRESS_KIND, which makes it more suitable for ABI 64. Currently,
the Fortran version of this function is implemented only for ABI 64.
This routine accepts the following parameters:
Page 1
MPI_TYPE_CREATE_HVECTOR(3)MPI_TYPE_CREATE_HVECTOR(3)
count Specifies the number of blocks (nonnegative integer)
blocklen Specifies the number of elements in each block
(nonnegative integer)
stride Specifies the number of bytes between the start of each
block (integer)
old_type Specifies the old data type (handle)
newtype Returns the new data type (handle)
ierror Specifies the return code value for successful completion,
which is in MPI_SUCCESS. MPI_SUCCESS is defined in the
mpif.h file.
Page 2