Previous: Collective and Independent Operations with Parallel I/O in NetCDF-4 Next: Example of Simple Parallel I/O Access Table of contents Frames 2012 Unidata NetCDF Workshop > Parallel I/O with NetCDF

35.7 Parallel I/O Example
This example is from nc_test4/tst_parallel.c, and is run by make check on platforms with MPI/IO support.
    /* Initialize MPI. */
    MPI_Init(&argc,&argv);
    MPI_Comm_size(MPI_COMM_WORLD, &mpi_size);
    MPI_Comm_rank(MPI_COMM_WORLD, &mpi_rank);
    MPI_Get_processor_name(mpi_name, &mpi_namelen);

    if (mpi_rank == 1)
       printf("\n*** tst_parallel testing very basic parallel access.\n");

    /* Create a parallel netcdf-4 file. */
    if ((res = nc_create_par(FILE, NC_NETCDF4|NC_MPIIO, comm, 
			     info, &ncid))) ERR;

    /* Create two dimensions. */
    if ((res = nc_def_dim(ncid, "d1", DIMSIZE, dimids))) ERR;
    if ((res = nc_def_dim(ncid, "d2", DIMSIZE, &dimids[1]))) ERR;

    /* Create one var. */
    if ((res = nc_def_var(ncid, "v1", NC_INT, NDIMS, dimids, &v1id))) ERR;

    if ((res = nc_enddef(ncid))) ERR;

    /* Set up slab for this process. */
    start[0] = mpi_rank * DIMSIZE/mpi_size;
    start[1] = 0;
    count[0] = DIMSIZE/mpi_size;
    count[1] = DIMSIZE;

    /* Create phoney data. We're going to write a 24x24 array of ints,
       in 4 sets of 144. */
    for (i=mpi_rank*QTR_DATA; i < (mpi_rank+1)*QTR_DATA; i++)
       data[i] = mpi_rank;

    /*if ((res = nc_var_par_access(ncid, v1id, NC_COLLECTIVE)))
      ERR;*/
    if ((res = nc_var_par_access(ncid, v1id, NC_INDEPENDENT))) ERR;

    /* Write slabs of phoney data. */
    if ((res = nc_put_vara_int(ncid, v1id, start, count, 
			       &data[mpi_rank*QTR_DATA]))) ERR;

    /* Close the netcdf file. */
    if ((res = nc_close(ncid)))	ERR;
    
    /* Shut down MPI. */
    MPI_Finalize();

    if (mpi_rank == 1)
    {
       SUMMARIZE_ERR;
       FINAL_RESULTS;
    }
    return 0;

 


Previous: Collective and Independent Operations with Parallel I/O in NetCDF-4 Next: Example of Simple Parallel I/O Access Table of contents Frames 2012 Unidata NetCDF Workshop > Parallel I/O with NetCDF