|
« Return to documentation listing
NAME
MPI_File_iread - Reads a file starting at the location specified by the
individual file pointer (nonblocking, noncollective).
SYNTAX
C Syntax
#include <mpi.h>
int MPI_File_iread(MPI_File fh, void *buf, int count,
MPI_Datatype datatype, MPI_Request *request)
Fortran Syntax
INCLUDE 'mpif.h'
MPI_FILE_IREAD(FH, BUF, COUNT, DATATYPE, REQUEST, IERROR)
<type> BUF(*)
INTEGER FH, COUNT, DATATYPE, REQUEST, IERROR
C++ Syntax
#include <mpi.h>
MPI::Request MPI::File::Iread(void* buf, int count,
const MPI::Datatype& datatype)
INPUT/OUTPUT PARAMETER
fh File handle (handle).
INPUT PARAMETERS
count Number of elements in the buffer (integer).
datatype Data type of each buffer element (handle).
OUTPUT PARAMETERS
buf Initial address of buffer (choice).
request Request object (handle).
IERROR Fortran only: Error status (integer).
DESCRIPTION
MPI_File_iread is a nonblocking version of MPI_File_read. It attempts
to read from the file associated with fh at the current individual file
pointer position maintained by the system in which a total number of
count data items having datatype type are read into the user's buffer
buf. The data is taken out of those parts of the file specified by the
current view. MPI_File_iread stores the number of data-type elements
actually read in status. All other fields of status are undefined. It
is erroneous to call this function if MPI_MODE_SEQUENTIAL mode was
specified when the file was opened.
ERRORS
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 does not guarantee that an MPI program can continue past an error.
1.3.4 Nov 11, 2009 MPI_File_iread(3)
« Return to documentation listing
|
