Open MPI logo

MPI_Type_indexed(3) man page (version 1.4.5)

  |   Home   |   Support   |   FAQ   |  

« Return to documentation listing

Table of Contents


MPI_Type_indexed - Creates an indexed datatype.


C Syntax

#include <mpi.h>
int MPI_Type_indexed(int count, int *array_of_blocklengths,
    int *array_of_displacements, MPI_Datatype oldtype,
    MPI_Datatype *newtype)

Fortran Syntax

INCLUDE ’mpif.h’

C++ Syntax

#include <mpi.h>
Datatype Datatype::Create_indexed(int count,
    const int array_of_blocklengths[],
    const int array_of_displacements[]) const

Input Parameters

Number of blocks -- also number of entries in array_of_displacements and array_of_blocklengths (nonnegative integer).
Number of elements per block (array of nonnegative integers).
Displacement for each block, in multiples of oldtype extent (array of integer).
Old datatype (handle).

Output Parameters

New datatype (handle).
Fortran only: Error status (integer).


The function MPI_Type_indexed allows replication of an old datatype into a sequence of blocks (each block is a concatenation of the old datatype), where each block can contain a different number of copies and have a different displacement. All block displacements are multiples of the old data type’s extent.

Example: Let oldtype have type map {(double, 0), (char, 8)}, with extent 16. Let B = (3, 1) and let D = (4, 0). A call to MPI_Type_indexed(2, B, D, oldtype, newtype) returns a datatype with type map

    {(double, 64), (char, 72), (double, 80), (char, 88),
    (double, 96), (char, 104),
    (double, 0), (char, 8)}

That is, three copies of the old type starting at displacement 4 x 16 = 64, and one copy starting at displacement 0.

In general, assume that oldtype has type map

    {(type(0), disp(0)), ..., (type(n-1), disp(n-1))},

with extent ex. Let B be the array_of_blocklength argument and D be the array_of_displacements argument. The newly created datatype has

n x S ^count-1
    i = 0           B[i]  entries:
    {(type(0), disp(0) + D[0]* ex), ...,
    (type(n-1), disp(n-1) + D[0]* ex), ...,
    (type(0), disp(0) + (D[0] + B[0]-1)* ex), ...,
    (type(n-1), disp(n-1) + (D[0]+ B[0]-1)* ex), ...,
    (type(0), disp(0) + D[count-1]* ex), ...,
    (type(n-1), disp(n-1) + D[count-1]* ex), ...,
    (type(0), disp(0) +  (D[count-1] + B[count-1] -1)* ex), ...,
    (type(n-1), disp(n-1) + (D[count-1] + B[count-1] -1)* ex)}

A call to MPI_Type_vector(count, blocklength, stride, oldtype, newtype) is equivalent to a call to MPI_Type_indexed(count, B, D, oldtype, newtype) where

    D[j] = j * stride, j = 0,..., count-1
    B[j] = blocklength, j = 0, .., count-1


Almost all MPI routines return an error value; C routines as the value of the function and Fortran routines in the last argument. C++ functions 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.

Before the error value is returned, the current MPI error handler is called. By default, this error handler aborts the MPI job, except for I/O function errors. The error handler may be changed with MPI_Comm_set_errhandler; the predefined error handler MPI_ERRORS_RETURN may be used to cause error values to be returned. Note that MPI does not guarantee that an MPI program can continue past an error.

See Also


Table of Contents

« Return to documentation listing