NAME

MPI_Type_hindexed - Construct a new type using multiple contiguous blocks of another type using byte offsets

SYNOPSIS

#include <mpi.h> 
int MPI_Type_hindexed(int count , int *b_len , MPI_Aint *disp , MPI_Datatype oldtype ,
	 MPI_Datatype *newtype ); 
int MPI_Type_create_hindexed(int count , int *b_len , MPI_Aint *disp , MPI_Datatype oldtype ,
	 MPI_Datatype *newtype ); 
#include <pmpi.h> 
int PMPI_Type_hindexed(int count , int *b_len , MPI_Aint *disp , MPI_Datatype oldtype ,
	 MPI_Datatype *newtype ); 
int PMPI_Type_create_hindexed(int count , int *b_len , MPI_Aint *disp , MPI_Datatype oldtype ,
	 MPI_Datatype *newtype ); 

INPUT PARAMETERS

count - Number of contiguous segments (integer)

b_len - array of lengths of blocks of component type (array of integers)

disp - array of offsets in bytes of blocks of component type (array of integers)

oldtype - component type (handle)

OUTPUT PARAMETER

newtype - newly constructed type (handle)

DESCRIPTION

The MPI_Type_hindexed() or MPI_Type_create_hindexed() functions are used to create a new type that describes count different blocks of a size described by the b_len array, at offsets described by the disp array, of the type oldtype . The offsets are in units of bytes.

Note that MPI_Type_hindexed() and MPI_Type_create_hindexed() are aliases to each other. This is due to the MPI FORTRAN ABI incorrectly specifying the displacements as integer sized rather than MPI_Aint for MPI_Type_hindexed(). Since this version of MPI currently does not support FORTRAN, the two functions are identical. MPI_Type_hindexed() has been marked as depreciated by the MPI committee.

The type newtype created by this function should be commited with MPI_Type_commit() if it is to be used with message passing functions. The type should be eventually freed with the MPI_Type_free() function.

PMPI_Type_hindexed() and PMPIT_Type_create_hindexed() are the profiling versions of this function.

ERRORS

All MPI routines except for MPI_Wtime and MPI_Wtick return an error value. The the current MPI error handler is invoked if this return value is not MPI_SUCCESS. The default error handler aborts, but this may be changed with by using the MPI_Errhandler_set() function. The predefined error handler MPI_ERRORS_RETURN may be used to cause error values to be returned instead. Note that MPI does not guarentee that an MPI program can continue past an error. In this implementation, all errors except MPI_ERR_INTERN or MPI_ERR_OTHER should always be recoverable.

MPI_SUCCESS - No error;

MPI_ERR_COUNT - Invalid count;

MPI_ERR_ARG - Invalid pointer;

MPI_ERR_TYPE - Invalid type;

MPI_ERR_INTERN - Out of Memory.

SEE ALSO

MPI_Type_free (3) MPI_Type_struct (3) MPI_Type_create_struct (3) MPI_Type_contiguous (3) MPI_Type_indexed (3) MPI_Type_create_hindexed (3) MPI_Type_vector (3) MPI_Type_hvector (3) MPI_Type_create_hvector (3)

• Lockless
• MPI Documentation
• MPI_Type_hindexed