MPITypecreatedarray(3OpenMPI) MPITypecreatedarray(3OpenMPI)

NAME
       MMPPIITTyyppeeccrreeaatteeddaarrrraayy -


SSYYNNTTAAXX
CC SSyynnttaaxx
       #include 
       int MPITypecreatedarray(int size, int rank, int ndims,
            int arrayofgsizes[], int arrayofdistribs[],
            int arrayofdargs[], int arrayofpsizes[],
            int order, MPIDatatype oldtype, MPIDatatype *newtype)


FFoorrttrraann SSyynnttaaxx
       INCLUDE 'mpif.h'
       MPITYPECREATEDARRAY(SIZE, RANK, NDIMS, ARRAYOFGSIZES,
            ARRAYOFDISTRIBS, ARRAYOFDARGS, ARRAYOFPSIZES, ORDER,
            OLDTYPE, NEWTYPE, IERROR)

            INTEGER   SIZE, RANK, NDIMS, ARRAYOFGSIZES(*), ARRAYOFDISTRIBS(*),
                 ARRAYOFDARGS(*), ARRAYOFPSIZES(*), ORDER, OLDTYPE,
                 NEWTYPE, IERROR


CC++++ SSyynnttaaxx
       #include 
       MPI::Datatype MPI::Datatype::Createdarray(int size, int rank,
            int ndims, const int arrayofgsizes[],
            const int arrayofdistribs[], const int arrayofdargs[],
            const int arrayofpsizes[], int order) const


IINNPPUUTT PPAARRAAMMEETTEERRSS
       size      Size of process group (positive integer).

       rank      Rank in process group (nonnegative integer).

       ndims     Number of array dimensions as well as process grid dimensions
                 (positive integer).


       arrayofgsizes
                 Number of elements of  type  oldtype  in  each  dimension  of
                 global array (array of positive integers).


       arrayofdistribs
                 Distribution of array in each dimension (array of state).

       arrayofdargs
                 Distribution  argument  in  each dimension (array of positive
                 integers).


       arrayofpsizes
                 Size of process grid in each  dimension  (array  of  positive
                 integers).


       order     Array storage order flag (state).

       oldtype   Old data type (handle).


OOUUTTPPUUTT PPAARRAAMMEETTEERRSS
       newtype   New data type (handle).

       IERROR    Fortran only: Error status (integer).


DESCRIPTION
       MPITypecreatedarray  can  be  used to generate the data types corre-
       sponding to the distribution of an ndims-dimensional array  of  oldtype
       elements  onto  an  ndims-dimensional grid of logical processes. Unused
       dimensions of arrayofpsizes should  be  set  to  1.  For  a  call  to
       MPITypecreatedarray to be correct, the equation

           ndims-1
         pi              arrayofpsizes[i] = size
           i=0


       must  be  satisfied.  The  ordering of processes in the process grid is
       assumed to be row-major, as in the case of  virtual  Cartesian  process
       topologies in MPI-1.

       Each dimension of the array can be distributed in one of three ways:

       - MPIDISTRIBUTEBLOCK - Block distribution
       - MPIDISTRIBUTECYCLIC - Cyclic distribution
       - MPIDISTRIBUTENONE - Dimension not distributed.

       The  constant MPIDISTRIBUTEDFLTDARG specifies a default distribution
       argument. The distribution argument for a dimension that  is  not  dis-
       tributed  is  ignored. For any dimension i in which the distribution is
       MPIDISTRIBUTEBLOCK,  it  erroneous   to   specify   arrayofdargs[i]
       arrayofpsizes[i] < arrayofgsizes[i].

       For  example,  the HPF layout ARRAY(CYCLIC(15)) corresponds to MPIDIS-
       TRIBUTECYCLIC with a distribution argument of 15, and the  HPF  layout
       ARRAY(BLOCK)  corresponds  to  MPIDISTRIBUTEBLOCK with a distribution
       argument of MPIDISTRIBUTEDFLTDARG.

       The order argument is used as in  MPITYPECREATESUBARRAY  to  specify
       the storage order. Therefore, arrays described by this type constructor
       may be stored in Fortran (column-major) or C (row-major)  order.  Valid
       values for order are MPIORDERFORTRAN and MPIORDERC.

       This  routine  creates  a  new  MPI data type with a typemap defined in
       terms of a function called "cyclic()" (see below).

       Without loss of generality, it suffices to define the typemap  for  the
       MPIDISTRIBUTECYCLIC  case where MPIDISTRIBUTEDFLTDARG is not used.

       MPIDISTRIBUTEBLOCK and MPIDISTRIBUTENONE  can  be  reduced  to  the
       MPIDISTRIBUTECYCLIC case for dimension i as follows.

       MPIDISTRIBUTEBLOCK   with  arrayofdargs[i]  equal  to  MPIDISTRIB-
       UTEDFLTDARG   is    equivalent    to    MPIDISTRIBUTECYCLIC    with
       arrayofdargs[i] set to

          (arrayofgsizes[i] + arrayofpsizes[i] - 1)/arrayofpsizes[i]

       If arrayofdargs[i] is not MPIDISTRIBUTEDFLTDARG, then MPIDISTRIB-
       UTEBLOCK and DISTRIBUTECYCLIC are equivalent.

       MPIDISTRIBUTENONE  is  equivalent   to   MPIDISTRIBUTECYCLIC   with
       arrayofdargs[i] set to arrayofgsizes[i].

       Finally, MPIDISTRIBUTECYCLIC with arrayofdargs[i] equal to MPIDIS-
       TRIBUTEDFLTDARG   is   equivalent   to   MPIDISTRIBUTECYCLIC   with
       arrayofdargs[i] set to 1.



NNOOTTEESS
       For both Fortran and C arrays, the ordering of processes in the process
       grid is assumed to be row-major. This is consistent with  the  ordering
       used  in  virtual Cartesian process topologies in MPI-1. To create such
       virtual process topologies, or to find the coordinates of a process  in
       the  process grid, etc., users may use the corresponding functions pro-
       vided in MPI-1.


EERRRROORRSS
       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::ERRORSTHROWEXCEPTIONS, 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
       MPICommseterrhandler; the predefined error handler MPIERRORSRETURN
       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.





Open MPI 1.2                    September 2006MPITypecreatedarray(3OpenMPI)