Lockless Inc

NAME

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

SYNOPSIS

#include <mpi.h> 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_create_hindexed(int count , int *b_len , MPI_Aint *disp , MPI_Datatype oldtype , MPI_Datatype *newtype );

#include <mpi.h> MPI::Datatype MPI::Datatype::Create_hindexed(int count , const int *b_len , const MPI::Aint *stride ) const;

INCLUDE 'mpif.h' MPI_TYPE_CREATE_HINDEXED(count , b_len , disp , oldtype , newtype , ierr ) INTEGER count , b_len (*), oldtype , newtype , ierr INTEGER(KIND=MPI_ADDRESS_KIND) disp (*)

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_create_hindexed() function is 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() is a similar function. However, due to it only passing 32-bit sized displacements in FORTRAN, its use is deprecated.

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.

The C++ version of this function passes the new type as the return value.

PMPI_Type_create_hindexed() is the profiling version of this function.

ERRORS

All MPI routines except for MPI_Wtime and MPI_Wtick return an error code. The the current MPI error handler is invoked if the 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.

In C, the error code is passed as the return value. In FORTRAN, all functions have an parameter ierr which returns the error code. MPI C++ functions do not directly return an error code. However, C++ users may want to use the MPI::ERRORS_THROW_EXCEPTIONS handler. This will throw an MPI::Exception with the corresponding error code. To prevent exceptions from being raised from within C and Fortran code, they will see all error return values as MPI_ERR_PENDING when this handler is chosen. In this implementation, call MPI::throw_exception() to throw the correct exception if this occurs.

MPI_SUCCESS - No error;

MPI_ERR_PENDING - Pending exception;

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_hindexed (3) MPI_Type_vector (3) MPI_Type_hvector (3) MPI_Type_create_hvector (3)

About Us Returns Policy Privacy Policy Send us Feedback
Company Info | Product Index | Category Index | Help | Terms of Use
Copyright © Lockless Inc All Rights Reserved.