PNETCDF(3) LIBRARY FUNCTIONS PNETCDF(3)NAME
PnetCDF - Parallel library for accessing files in Network Common Data
Form (CDF, CDF-2 and CDF-5 formats)
SYNOPSIS
#include <pnetcdf.h>
mpicc ... -lpnetcdf
Complete documentation for the PnetCDF libraries can be found at the
PnetCDF website: http://cucis.ece.northwestern.edu/projects/PnetCDF/.
LIBRARY VERSION
This document describes Parallel netCDF APIs for the C programming lan‐
guage.
const char* ncmpi_inq_libvers()
(Corresponds to nc_inq_libvers() in netCDF)
Returns a string identifying the version of the PnetCDF library,
and when it was built, like: "1.6.1 of 01 Jun 2015".
The RCS ident(1) command will find a string like "$Id: @(#) PnetCDF li‐
brary version 1.6.1 of 01 Jun 2015 $" in the library. The SCCS what(1)
command will find a string like "PnetCDF library version 1.6.1 of 01
Jun 2015".
RETURN VALUES
All PnetCDF functions (except ncmpi_inq_libvers() and ncmpi_strerror())
return an integer status.
If this returned status value is not equal to NC_NOERR (zero), it indi‐
cates that an error occurred. The possible status values are defined in
system include file <errno.h> and in "pnetcdf.h".
const char* ncmpi_strerror(int status)
(Corresponds to nc_strerror() in netCDF)
Returns a string textual translation of the status value, like
"Attribute or variable name contains illegal characters" or "No
such file or directory".
FILE OPERATIONS
int ncmpi_create(MPI_Comm comm, const char path[], int cmode, MPI_Info
info, int* ncid)
(Corresponds to nc_create() in netCDF)
Creates a new netCDF dataset at path collectively by a group of
MPI processes specified by comm, returning a netCDF ID in ncid.
The argument cmode may include the bitwise-or of the following
flags: NC_NOCLOBBER to protect existing datasets (default is
NC_CLOBBER, silently blows them away), NC_SHARE for stronger
metadata data consistency control, NC_64BIT_OFFSET to create a
file in the 64-bit offset format (CDF-2), as opposed to classic
format, the default, or NC_64BIT_DATA to create a file in the
64-bit data format (CDF-5). Use either NC_64BIT_OFFSET or
NC_64BIT_DATA. The 64-bit offset format allows the creation of
very large files with far fewer restrictions than netCDF classic
format, but can only be read by the netCDF library version 3.6
or greater. Users are cautioned that files that use the 64-bit
offset format will not be recognized by netCDF applications
linked to an earlier version of the netCDF library than 3.6.
Applications linked to version 3.6 or later will be able to
transparently access either the classic format or 64-bit offset
format. The 64-bit data format allows the creation of very
large array variables. CDF-5 files currently will not be recog‐
nized by netCDF 3 or 4 library.
The argument cmode must be consistent among all MPI processes
that collectively create the file. The argument info is an MPI
info object. Users can use it to supply the file access hints
further performance improvement. The hints include existing
MPI-IO hints as well as hints defined and used in PnetCDF.
When a netCDF dataset is created, it is opened in NC_WRITE mode.
When this function returns, the new netCDF dataset is in define
mode.
int ncmpi_open(MPI_Comm comm, const char path[], int mode, MPI_Info in‐
fo, int* ncid)
(Corresponds to nc_open() in netCDF)
Opens an existing netCDF dataset at path collectively by a group
of MPI processes specified by comm, returning a netCDF ID in
ncid. The type of access is described by the mode parameter,
which may include the bitwise-or of the following flags:
NC_WRITE for read-write access (default read-only), NC_SHARE for
stronger metadata data consistency control.
The argument mode must be consistent among all MPI processes
that collectively open the file. The argument info is an MPI
info object. Users can use it to supply the file access hints
further performance improvement. The hints include existing
MPI-IO hints as well as hints defined and used in PnetCDF.
int ncmpi_redef(int ncid)
(Corresponds to nc_redef() in netCDF)
Puts an open netCDF dataset into define mode, so dimensions,
variables, and attributes can be added or renamed and attributes
can be deleted.
int ncmpi_enddef(int ncid)
(Corresponds to nc_enddef() in netCDF)
Takes an open netCDF dataset out of define mode. The changes
made to the netCDF dataset while it was in define mode are
checked and committed to disk if no problems occurred. After a
successful call, variable data can be read or written to the
dataset.
int ncmpi_sync(int ncid)
(Corresponds to nc_sync() in netCDF)
Unless the NC_SHARE bit is set in ncmpi_open() or ncmpi_cre‐
ate(), data written by PnetCDF APIs may be cached by local file
system on each compute node. This API flushes cached data by
calling MPI_File_sync.
int ncmpi_abort(int ncid)
(Corresponds to nc_abort() in netCDF)
You don't need to call this function. This function is called
automatically by ncmpi_close() if the netCDF was in define mode
and something goes wrong with the commit. If the netCDF dataset
isn't in define mode, then this function is equivalent to
ncmpi_close(). If it is called after ncmpi_redef(), but before
ncmpi_enddef(), the new definitions are not committed and the
dataset is closed. If it is called after ncmpi_create() but be‐
fore ncmpi_enddef(), the dataset disappears.
int ncmpi_close(int ncid)
(Corresponds to nc_close() in netCDF)
Closes an open netCDF dataset. If the dataset is in define
mode, ncmpi_enddef() will be called before closing. After a
dataset is closed, its ID may be reassigned to another dataset.
int ncmpi_inq(int ncid, int* ndims, int* nvars, int* natts, int* un‐
limdimid)
(Corresponds to nc_inq() in netCDF)
int ncmpi_inq_ndims(int ncid, int* ndims)
(Corresponds to nc_inq_ndims() in netCDF)
int ncmpi_inq_nvars(int ncid, int* nvars)
(Corresponds to nc_inq_nvars() in netCDF)
int ncmpi_inq_natts(int ncid, int* natts)
(Corresponds to nc_inq_natts() in netCDF)
int ncmpi_inq_unlimdim(int ncid, int* unlimdimid)
(Corresponds to nc_inq_unlimdim() in netCDF)
int ncmpi_inq_format(int ncid, int* formatn)
(Corresponds to nc_inq_format() in netCDF)
Use these functions to find out what is in a netCDF dataset.
Upon successful return, ndims will contain the number of dimen‐
sions defined for this netCDF dataset, nvars will contain the
number of variables, natts will contain the number of at‐
tributes, and unlimdimid will contain the dimension ID of the
unlimited dimension if one exists, or -1 otherwise. formatn
will contain the version number of the dataset <format>, one of
NC_FORMAT_CLASSIC, NC_FORMAT_64BIT, or NC_FORMAT_64BIT_DATA. If
any of the return parameters is a NULL pointer, then the corre‐
sponding information will not be returned; hence, no space need
be allocated for it.
int ncmpi_def_dim(int ncid, const char name[], MPI_Offset len, int*
dimid)
(Corresponds to nc_def_dim() in netCDF)
Adds a new dimension to an open netCDF dataset, which must be in
define mode. name is the dimension name. If dimid is not a
NULL pointer then upon successful completion dimid will contain
the dimension ID of the newly created dimension.
DIMENSIONS
int ncmpi_inq_dimid(int ncid, const char name[], int* dimid)
(Corresponds to nc_inq_dimid() in netCDF)
Given a dimension name, returns the ID of a netCDF dimension in
dimid.
int ncmpi_inq_dim(int ncid, int dimid, char name[], MPI_Offset* len)
(Corresponds to nc_inq_dim() in netCDF)
int ncmpi_inq_dimname(int ncid, int dimid, char name[])
(Corresponds to nc_inq_dimname() in netCDF)
int ncmpi_inq_dimlen(int ncid, int dimid, MPI_Offset* len)
(Corresponds to nc_inq_dimlen() in netCDF)
Use these functions to find out about a dimension. If either
the name argument or len argument is a NULL pointer, then the
associated information will not be returned. Otherwise, name
should be big enough (NC_MAX_NAME) to hold the dimension name
as the name will be copied into your storage. The length return
parameter, len will contain the size of the dimension. For the
unlimited dimension, the returned length is the current maximum
value used for writing into any of the variables which use the
dimension.
int ncmpi_rename_dim(int ncid, int dimid, const char name[])
(Corresponds to nc_rename_dim() in netCDF)
Renames an existing dimension in an open netCDF dataset. If the
new name is longer than the old name, the netCDF dataset must be
in define mode. You cannot rename a dimension to have the same
name as another dimension.
VARIABLES
int ncmpi_def_var(int ncid, const char name[], nc_type xtype, int
ndims, const int dimids[], int* varid)
(Corresponds to nc_def_var() in netCDF)
Adds a new variable to a netCDF dataset. The netCDF must be in
define mode. If not NULL, then varid will be set to the netCDF
variable ID. ndims will be the number of dimensions for the
variable. name will be the name of the netCDF variable. xtype
is the external, netCDF type of the variable and should be one
of NC_BYTE NC_CHAR, NC_SHORT, NC_INT, NC_FLOAT, or NC_DOUBLE,
for CDF-1 and CDF-2 file formats. CDF-5 defines additional ex‐
ternal types: NC_UBYTE, NC_USHORT, NC_UINT, NC_INT64, and
NC_UINT64. dimids argument is a vector of ndims dimension IDs
corresponding to the variable dimensions.
int ncmpi_inq_varid(int ncid, const char name[], int* varid)
(Corresponds to nc_inq_varid() in netCDF)
Returns the ID of a netCDF variable in varid given its name.
int ncmpi_inq_var(int ncid, int varid, char name[], nc_type* xtype,
int* ndims, int dimids[], int* natts)
(Corresponds to nc_inq_var() in netCDF)
int ncmpi_inq_varname(int ncid, int varid, char name[])
(Corresponds to nc_inq_varname() in netCDF)
int ncmpi_inq_vartype(int ncid, int varid, nc_type* xtype)
(Corresponds to nc_inq_vartype() in netCDF)
int ncmpi_inq_varndims(int ncid, int varid, int* ndims)
(Corresponds to nc_inq_varndims() in netCDF)
int ncmpi_inq_vardimid(int ncid, int varid, int dimids[])
(Corresponds to nc_inq_vardimid() in netCDF)
int ncmpi_inq_varnatts(int ncid, int varid, int* natts)
(Corresponds to nc_inq_varnatts() in netCDF)
Returns information about a netCDF variable, given its ID. If
any of the return parameters (name, xtype, ndims, dimids, or
natts) is a NULL pointer, then the corresponding information
will not be returned; hence, no space need be allocated for it.
int ncmpi_rename_var(int ncid, int varid, const char name[])
(Corresponds to nc_rename_var() in netCDF)
Changes the name of a netCDF variable. If the new name is
longer than the old name, the netCDF must be in define mode.
You cannot rename a variable to have the name of any existing
variable.
WRITING AND READING WHOLE VARIABLES
int ncmpi_put_var_text(int ncid, int varid, const char out[])
(Corresponds to nc_put_var_text() in netCDF)
int ncmpi_put_var_uchar(int ncid, int varid, const unsigned char out[])
(Corresponds to nc_put_var_uchar() in netCDF)
int ncmpi_put_var_schar(int ncid, int varid, const signed char out[])
(Corresponds to nc_put_var_schar() in netCDF)
int ncmpi_put_var_short(int ncid, int varid, const short out[])
(Corresponds to nc_put_var_short() in netCDF)
int ncmpi_put_var_int(int ncid, int varid, const int out[])
(Corresponds to nc_put_var_int() in netCDF)
int ncmpi_put_var_long(int ncid, int varid, const long out[])
(Corresponds to nc_put_var_long() in netCDF)
int ncmpi_put_var_float(int ncid, int varid, const float out[])
(Corresponds to nc_put_var_float() in netCDF)
int ncmpi_put_var_double(int ncid, int varid, const double out[])
(Corresponds to nc_put_var_double() in netCDF)
Writes an entire netCDF variable (i.e. all the values). The
netCDF dataset must be open and in data mode. The type of the
data is specified in the function name, and it is converted to
the external type of the specified variable, if possible, other‐
wise an NC_ERANGE error is returned. Note that rounding is not
performed during the conversion. Floating point numbers are
truncated when converted to integers.
int ncmpi_get_var_text(int ncid, int varid, char in[])
(Corresponds to nc_get_var_text() in netCDF)
int ncmpi_get_var_uchar(int ncid, int varid, unsigned char in[])
(Corresponds to nc_get_var_uchar() in netCDF)
int ncmpi_get_var_schar(int ncid, int varid, signed char in[])
(Corresponds to nc_get_var_schar() in netCDF)
int ncmpi_get_var_short(int ncid, int varid, short in[])
(Corresponds to nc_get_var_short() in netCDF)
int ncmpi_get_var_int(int ncid, int varid, int in[])
(Corresponds to nc_get_var_int() in netCDF)
int ncmpi_get_var_long(int ncid, int varid, long in[])
(Corresponds to nc_get_var_long() in netCDF)
int ncmpi_get_var_float(int ncid, int varid, float in[])
(Corresponds to nc_get_var_float() in netCDF)
int ncmpi_get_var_double(int ncid, int varid, double in[])
(Corresponds to nc_get_var_double() in netCDF)
Reads an entire netCDF variable (i.e. all the values). The
netCDF dataset must be open and in data mode. The data is con‐
verted from the external type of the specified variable, if nec‐
essary, to the type specified in the function name. If conver‐
sion is not possible, an NC_ERANGE error is returned.
WRITING AND READING ONE DATUM
int ncmpi_put_var1_text(int ncid, int varid, const MPI_Offset index[],
char *out)
(Corresponds to nc_put_var1_text() in netCDF)
int ncmpi_put_var1_uchar(int ncid, int varid, const MPI_Offset index[],
unsigned char *out)
(Corresponds to nc_put_var1_uchar() in netCDF)
int ncmpi_put_var1_schar(int ncid, int varid, const MPI_Offset index[],
signed char *out)
(Corresponds to nc_put_var1_schar() in netCDF)
int ncmpi_put_var1_short(int ncid, int varid, const MPI_Offset index[],
short *out)
(Corresponds to nc_put_var1_short() in netCDF)
int ncmpi_put_var1_int(int ncid, int varid, const MPI_Offset index[],
int *out)
(Corresponds to nc_put_var1_int() in netCDF)
int ncmpi_put_var1_long(int ncid, int varid, const MPI_Offset index[],
long *out)
(Corresponds to nc_put_var1_long() in netCDF)
int ncmpi_put_var1_float(int ncid, int varid, const MPI_Offset index[],
float *out)
(Corresponds to nc_put_var1_float() in netCDF)
int ncmpi_put_var1_double(int ncid, int varid, const MPI_Offset in‐
dex[], double *out)
(Corresponds to nc_put_var1_double() in netCDF)
Puts a single data value into a variable at the position index
of an open netCDF dataset that is in data mode. The type of the
data is specified in the function name, and it is converted to
the external type of the specified variable, if possible, other‐
wise an NC_ERANGE error is returned.
int ncmpi_get_var1_text(int ncid, int varid, const MPI_Offset index[],
char* in)
(Corresponds to nc_get_var1_text() in netCDF)
int ncmpi_get_var1_uchar(int ncid, int varid, const MPI_Offset index[],
unsigned char* in)
(Corresponds to nc_get_var1_uchar() in netCDF)
int ncmpi_get_var1_schar(int ncid, int varid, const MPI_Offset index[],
signed char* in)
(Corresponds to nc_get_var1_schar() in netCDF)
int ncmpi_get_var1_short(int ncid, int varid, const MPI_Offset index[],
short* in)
(Corresponds to nc_get_var1_short() in netCDF)
int ncmpi_get_var1_int(int ncid, int varid, const MPI_Offset index[],
int* in)
(Corresponds to nc_get_var1_int() in netCDF)
int ncmpi_get_var1_long(int ncid, int varid, const MPI_Offset index[],
long* in)
(Corresponds to nc_get_var1_long() in netCDF)
int ncmpi_get_var1_float(int ncid, int varid, const MPI_Offset index[],
float* in)
(Corresponds to nc_get_var1_float() in netCDF)
int ncmpi_get_var1_double(int ncid, int varid, const MPI_Offset in‐
dex[], double* in)
(Corresponds to nc_get_var1_double() in netCDF)
Gets a single data value from a variable at the position index
of an open netCDF dataset that is in data mode. The data is
converted from the external type of the specified variable, if
necessary, to the type specified in the function name. If con‐
version is not possible, an NC_ERANGE error is returned.
WRITING AND READING AN ARRAY
int ncmpi_put_vara_text(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const char out[])
(Corresponds to nc_put_vara_text() in netCDF)
int ncmpi_put_vara_uchar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const unsigned char out[])
(Corresponds to nc_put_vara_uchar() in netCDF)
int ncmpi_put_vara_schar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const signed char out[])
(Corresponds to nc_put_vara_schar() in netCDF)
int ncmpi_put_vara_short(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const short out[])
(Corresponds to nc_put_vara_short() in netCDF)
int ncmpi_put_vara_int(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const int out[])
(Corresponds to nc_put_vara_int() in netCDF)
int ncmpi_put_vara_long(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const long out[])
(Corresponds to nc_put_vara_long() in netCDF)
int ncmpi_put_vara_float(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const float out[])
(Corresponds to nc_put_vara_float() in netCDF)
int ncmpi_put_vara_double(int ncid, int varid, const MPI_Offset
start[], const MPI_Offset count[], const double out[])
(Corresponds to nc_put_vara_double() in netCDF)
Writes an array section of values into a netCDF variable of an
open netCDF dataset, which must be in data mode. The array sec‐
tion is specified by the start and count vectors, which give the
starting index and count of values along each dimension of the
specified variable. The type of the data is specified in the
function name and is converted to the external type of the spec‐
ified variable, if possible, otherwise an NC_ERANGE error is re‐
turned.
int ncmpi_get_vara_text(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], char in[])
(Corresponds to nc_get_vara_text() in netCDF)
int ncmpi_get_vara_uchar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], unsigned char in[])
(Corresponds to nc_get_vara_uchar() in netCDF)
int ncmpi_get_vara_schar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], signed char in[])
(Corresponds to nc_get_vara_schar() in netCDF)
int ncmpi_get_vara_short(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], short in[])
(Corresponds to nc_get_vara_short() in netCDF)
int ncmpi_get_vara_int(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], int in[])
(Corresponds to nc_get_vara_int() in netCDF)
int ncmpi_get_vara_long(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], long in[])
(Corresponds to nc_get_vara_long() in netCDF)
int ncmpi_get_vara_float(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], float in[])
(Corresponds to nc_get_vara_float() in netCDF)
int ncmpi_get_vara_double(int ncid, int varid, const MPI_Offset
start[], const MPI_Offset count[], double in[])
(Corresponds to nc_get_vara_double() in netCDF)
Reads an array section of values from a netCDF variable of an
open netCDF dataset, which must be in data mode. The array sec‐
tion is specified by the start and count vectors, which give the
starting index and count of values along each dimension of the
specified variable. The data is converted from the external
type of the specified variable, if necessary, to the type speci‐
fied in the function name. If conversion is not possible, an
NC_ERANGE error is returned.
WRITING AND READING A SLICED ARRAY
int ncmpi_put_vars_text(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const char
out[])
(Corresponds to nc_put_vars_text() in netCDF)
int ncmpi_put_vars_uchar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const un‐
signed char out[])
(Corresponds to nc_put_vars_uchar() in netCDF)
int ncmpi_put_vars_schar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
signed char out[])
(Corresponds to nc_put_vars_schar() in netCDF)
int ncmpi_put_vars_short(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const short
out[])
(Corresponds to nc_put_vars_short() in netCDF)
int ncmpi_put_vars_int(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const int
out[])
(Corresponds to nc_put_vars_int() in netCDF)
int ncmpi_put_vars_long(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const long
out[])
(Corresponds to nc_put_vars_long() in netCDF)
int ncmpi_put_vars_float(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const float
out[])
(Corresponds to nc_put_vars_float() in netCDF)
int ncmpi_put_vars_double(int ncid, int varid, const MPI_Offset
start[], const MPI_Offset count[], const MPI_Offset stride[],
const double out[])
(Corresponds to nc_put_vars_double() in netCDF)
These functions are used for strided output, which is like the
array section output described above, except that the sampling
stride (the interval between accessed values) is specified for
each dimension. For an explanation of the sampling stride vec‐
tor, see COMMON ARGUMENTS DESCRIPTIONS below.
int ncmpi_get_vars_text(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], char in[])
(Corresponds to nc_get_vars_text() in netCDF)
int ncmpi_get_vars_uchar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], unsigned
char in[])
(Corresponds to nc_get_vars_uchar() in netCDF)
int ncmpi_get_vars_schar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], signed char
in[])
(Corresponds to nc_get_vars_schar() in netCDF)
int ncmpi_get_vars_short(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], short in[])
(Corresponds to nc_get_vars_short() in netCDF)
int ncmpi_get_vars_int(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], int in[])
(Corresponds to nc_get_vars_int() in netCDF)
int ncmpi_get_vars_long(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], long in[])
(Corresponds to nc_get_vars_long() in netCDF)
int ncmpi_get_vars_float(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], float in[])
(Corresponds to nc_get_vars_float() in netCDF)
int ncmpi_get_vars_double(int ncid, int varid, const MPI_Offset
start[], const MPI_Offset count[], const MPI_Offset stride[],
double in[])
(Corresponds to nc_get_vars_double() in netCDF)
These functions are used for strided input, which is like the
array section input described above, except that the sampling
stride (the interval between accessed values) is specified for
each dimension. For an explanation of the sampling stride vec‐
tor, see COMMON ARGUMENTS DESCRIPTIONS below.
WRITING AND READING A MAPPED ARRAY
int ncmpi_put_varm_text(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], const char out[])
(Corresponds to nc_put_varm_text() in netCDF)
int ncmpi_put_varm_uchar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], const unsigned char out[])
(Corresponds to nc_put_varm_uchar() in netCDF)
int ncmpi_put_varm_schar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], const signed char out[])
(Corresponds to nc_put_varm_schar() in netCDF)
int ncmpi_put_varm_short(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], const short out[])
(Corresponds to nc_put_varm_short() in netCDF)
int ncmpi_put_varm_int(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], const int out[])
(Corresponds to nc_put_varm_int() in netCDF)
int ncmpi_put_varm_long(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], const long out[])
(Corresponds to nc_put_varm_long() in netCDF)
int ncmpi_put_varm_float(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], const float out[])
(Corresponds to nc_put_varm_float() in netCDF)
int ncmpi_put_varm_double(int ncid, int varid, const MPI_Offset
start[], const MPI_Offset count[], const MPI_Offset stride[],
const MPI_Offset imap[], const double out[])
(Corresponds to nc_put_varm_double() in netCDF)
These functions are used for mapped output, which is like strid‐
ed output described above, except that an additional index map‐
ping vector is provided to specify the in-memory arrangement of
the data values. For an explanation of the index mapping vec‐
tor, see COMMON ARGUMENTS DESCRIPTIONS below.
int ncmpi_get_varm_text(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], char in[])
(Corresponds to nc_get_varm_text() in netCDF)
int ncmpi_get_varm_uchar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], unsigned char in[])
(Corresponds to nc_get_varm_uchar() in netCDF)
int ncmpi_get_varm_schar(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], signed char in[])
(Corresponds to nc_get_varm_schar() in netCDF)
int ncmpi_get_varm_short(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], short in[])
(Corresponds to nc_get_varm_short() in netCDF)
int ncmpi_get_varm_int(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], int in[])
(Corresponds to nc_get_varm_int() in netCDF)
int ncmpi_get_varm_long(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], long in[])
(Corresponds to nc_get_varm_long() in netCDF)
int ncmpi_get_varm_float(int ncid, int varid, const MPI_Offset start[],
const MPI_Offset count[], const MPI_Offset stride[], const
MPI_Offset imap[], float in[])
(Corresponds to nc_get_varm_float() in netCDF)
int ncmpi_get_varm_double(int ncid, int varid, const MPI_Offset
start[], const MPI_Offset count[], const MPI_Offset stride[],
const MPI_Offset imap[], double in[])
(Corresponds to nc_get_varm_double() in netCDF)
These functions are used for mapped input, which is like strided
input described above, except that an additional index mapping
vector is provided to specify the in-memory arrangement of the
data values. For an explanation of the index mapping vector,
see COMMON ARGUMENTS DESCRIPTIONS below.
ATTRIBUTES
int ncmpi_put_att_text(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, const char out[])
(Corresponds to nc_put_att_text() in netCDF)
int ncmpi_put_att_uchar(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, const unsigned char out[])
(Corresponds to nc_put_att_uchar() in netCDF)
int ncmpi_put_att_schar(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, const signed char out[])
(Corresponds to nc_put_att_schar() in netCDF)
int ncmpi_put_att_short(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, const short out[])
(Corresponds to nc_put_att_short() in netCDF)
int ncmpi_put_att_int(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, const int out[])
(Corresponds to nc_put_att_int() in netCDF)
int ncmpi_put_att_long(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, const long out[])
(Corresponds to nc_put_att_long() in netCDF)
int ncmpi_put_att_float(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, const float out[])
(Corresponds to nc_put_att_float() in netCDF)
int ncmpi_put_att_double(int ncid, int varid, const char name[],
nc_type xtype, MPI_Offset len, const double out[])
(Corresponds to nc_put_att_double() in netCDF)
int ncmpi_put_att(int ncid, int varid, const char name[], nc_type
xtype, MPI_Offset len, void * ip)
(Corresponds to nc_put_att() in netCDF)
int ncmpi_get_att(int ncid, int varid, const char name[], void ** ip)
(Corresponds to nc_get_att() in netCDF)
Unlike variables, attributes do not have separate functions for
defining and writing values. This family of functions defines a
new attribute with a value or changes the value of an existing
attribute. If the attribute is new, or if the space required to
store the attribute value is greater than before, the netCDF
dataset must be in define mode. The parameter len is the number
of values from out to transfer. It is often one, except that
for ncmpi_put_att_text() it will usually be strlen(out).
For these functions, the type component of the function name
refers to the in-memory type of the value, whereas the xtype ar‐
gument refers to the external type for storing the value. An
NC_ERANGE error results if a conversion between these types is
not possible. In this case the value is represented with the
appropriate fill-value for the associated external type.
int ncmpi_inq_attname(int ncid, int varid, int attnum, char name[])
(Corresponds to nc_inq_attname() in netCDF)
Gets the name of an attribute, given its variable ID and at‐
tribute number. This function is useful in generic applications
that need to get the names of all the attributes associated with
a variable, since attributes are accessed by name rather than
number in all other attribute functions. The number of an at‐
tribute is more volatile than the name, since it can change when
other attributes of the same variable are deleted. The at‐
tributes for each variable are numbered from 0 (the first at‐
tribute) to nvatts-1, where nvatts is the number of attributes
for the variable, as returned from a call to ncmpi_inq_var‐
natts(). If the name parameter is a NULL pointer, no name will
be returned and no space need be allocated.
int ncmpi_inq_att(int ncid, int varid, const char name[], nc_type*
xtype, MPI_Offset* len)
(Corresponds to nc_inq_att() in netCDF)
int ncmpi_inq_attid(int ncid, int varid, const char name[], int* at‐
tnum)
(Corresponds to nc_inq_attid() in netCDF)
int ncmpi_inq_atttype(int ncid, int varid, const char name[], nc_type*
xtype)
(Corresponds to nc_inq_atttype() in netCDF)
int ncmpi_inq_attlen(int ncid, int varid, const char name[], MPI_Off‐
set* len)
(Corresponds to nc_inq_attlen() in netCDF)
These functions return information about a netCDF attribute,
given its variable ID and name. The information returned is the
external type in xtype and the number of elements in the at‐
tribute as len. If any of the return arguments is a NULL point‐
er, the specified information will not be returned.
int ncmpi_copy_att(int ncid, int varid_in, const char name[], int
ncid_out, int varid_out)
(Corresponds to nc_copy_att() in netCDF)
Copies an attribute from one netCDF dataset to another. It can
also be used to copy an attribute from one variable to another
within the same netCDF. ncid_in is the netCDF ID of an input
netCDF dataset from which the attribute will be copied.
varid_in is the ID of the variable in the input netCDF dataset
from which the attribute will be copied, or NC_GLOBAL for a
global attribute. name is the name of the attribute in the in‐
put netCDF dataset to be copied. ncid_out is the netCDF ID of
the output netCDF dataset to which the attribute will be copied.
It is permissible for the input and output netCDF ID's to be the
same. The output netCDF dataset should be in define mode if the
attribute to be copied does not already exist for the target
variable, or if it would cause an existing target attribute to
grow. varid_out is the ID of the variable in the output netCDF
dataset to which the attribute will be copied, or NC_GLOBAL to
copy to a global attribute.
int ncmpi_rename_att(int ncid, int varid, const char name[], const char
newname[])
(Corresponds to nc_rename_att() in netCDF)
Changes the name of an attribute. If the new name is longer
than the original name, the netCDF must be in define mode. You
cannot rename an attribute to have the same name as another at‐
tribute of the same variable. name is the original attribute
name. newname is the new name to be assigned to the specified
attribute. If the new name is longer than the old name, the
netCDF dataset must be in define mode.
int ncmpi_del_att(int ncid, int varid, const char name[])
(Corresponds to nc_del_att() in netCDF)
Deletes an attribute from a netCDF dataset. The dataset must be
in define mode.
int ncmpi_get_att_text(int ncid, int varid, const char name[], char
in[])
(Corresponds to nc_get_att_text() in netCDF)
int ncmpi_get_att_uchar(int ncid, int varid, const char name[], un‐
signed char in[])
(Corresponds to nc_get_att_uchar() in netCDF)
int ncmpi_get_att_schar(int ncid, int varid, const char name[], signed
char in[])
(Corresponds to nc_get_att_schar() in netCDF)
int ncmpi_get_att_short(int ncid, int varid, const char name[], short
in[])
(Corresponds to nc_get_att_short() in netCDF)
int ncmpi_get_att_int(int ncid, int varid, const char name[], int in[])
(Corresponds to nc_get_att_int() in netCDF)
int ncmpi_get_att_long(int ncid, int varid, const char name[], long
in[])
(Corresponds to nc_get_att_long() in netCDF)
int ncmpi_get_att_float(int ncid, int varid, const char name[], float
in[])
(Corresponds to nc_get_att_float() in netCDF)
int ncmpi_get_att_double(int ncid, int varid, const char name[], double
in[])
(Corresponds to nc_get_att_double() in netCDF)
Gets the value(s) of a netCDF attribute, given its variable ID
and name. Converts from the external type to the type specified
in the function name, if possible, otherwise returns an
NC_ERANGE error. All elements of the vector of attribute values
are returned, so you must allocate enough space to hold them.
If you don't know how much space to reserve, call ncmpi_inq_at‐
tlen() first to find out the length of the attribute.
COMMON ARGUMENT DESCRIPTIONS
In this section we define some common arguments which are used in the
"FUNCTION DESCRIPTIONS" section.
int ncid
is the netCDF ID returned from a previous, successful call to
ncmpi_open() or ncmpi_create()
char name[]
is the name of a dimension, variable, or attribute. The names of
dimensions, variables and attributes consist of arbitrary se‐
quences of alphanumeric characters (as well as underscore '_',
period '.' and hyphen '-'), beginning with a letter or under‐
score. (However names commencing with underscore are reserved
for system use.) Case is significant in netCDF names. A zero-
length name is not allowed. As an input argument, it shall be a
pointer to a 0-terminated string; as an output argument, it
shall be the address of a buffer in which to hold such a string.
The maximum allowable number of characters (excluding the termi‐
nating 0) is NC_MAX_NAME.
nc_type xtype
specifies the external data type of a netCDF variable or at‐
tribute and is one of the following: NC_BYTE, NC_CHAR, NC_SHORT,
NC_INT, NC_FLOAT, or NC_DOUBLE for CDF-1 and CDF-2 file formats.
These are used to specify 8-bit integers, characters, 16-bit in‐
tegers, 32-bit integers, 32-bit IEEE floating point numbers, and
64-bit IEEE floating-point numbers, respectively. (NC_LONG in
netCDF version 2 is now obsolete and set to NC_INT). CDF-5 de‐
fines additional external types: NC_UBYTE, NC_USHORT, NC_UINT,
NC_INT64, and NC_UINT64.
int dimids[]
is a vector of dimension ID's and defines the shape of a netCDF
variable. The size of the vector shall be greater than or equal
to the rank (i.e. the number of dimensions) of the variable
(ndims). The vector shall be ordered by the speed with which a
dimension varies: dimids[ndims-1] shall be the dimension ID of
the most rapidly varying dimension and dimids[0] shall be the
dimension ID of the most slowly varying dimension. The maximum
possible number of dimensions for a variable is given by the
symbolic constant NC_MAX_VAR_DIMS.
int dimid
is the ID of a netCDF dimension. netCDF dimension ID's are al‐
located sequentially from the non-negative integers beginning
with 0.
int ndims
is either the total number of dimensions in a netCDF dataset or
the rank (i.e. the number of dimensions) of a netCDF variable.
The value shall not be negative or greater than the symbolic
constant NC_MAX_VAR_DIMS.
int varid
is the ID of a netCDF variable or (for the attribute-access
functions) the symbolic constant NC_GLOBAL, which is used to
reference global attributes. netCDF variable ID's are allocated
sequentially from the non-negative integers beginning with 0.
int* natts
is the number of global attributes in a netCDF dataset for the
ncmpi_inquire() function or the number of attributes associated
with a netCDF variable for the ncmpi_varinq() function.
const MPI_Offset index[]
specifies the coordinates of the netCDF data value to be ac‐
cessed. The indices start at 0; thus, for example, the first
data value of a two-dimensional variable is (0,0). The size of
the vector shall be at least the rank of the associated netCDF
variable and its elements shall correspond, in order, to the
variable's dimensions.
const MPI_Offset start[]
specifies the starting point for accessing a netCDF variable's
data values in terms of the indicial coordinates of the corner
of the array section. The indices start at 0; thus, the first
data value of a variable is (0, 0, ..., 0). The size of the
vector shall be at least the rank of the associated netCDF vari‐
able and its elements shall correspond, in order, to the vari‐
able's dimensions.
const MPI_Offset count[]
specifies the number of indices selected along each dimension of
the array section. Thus, to access a single value, for example,
specify count as (1, 1, ..., 1). Note that, for strided I/O,
this argument must be adjusted to be compatible with the stride
and start arguments so that the interaction of the three does
not attempt to access an invalid data co-ordinate. The elements
of the count vector correspond, in order, to the variable's di‐
mensions.
const MPI_Offset stride[]
specifies the sampling interval along each dimension of the
netCDF variable. The elements of the stride vector correspond,
in order, to the netCDF variable's dimensions (stride[0]) gives
the sampling interval along the most slowly varying dimension of
the netCDF variable). Sampling intervals are specified in type-
independent units of elements (a value of 1 selects consecutive
elements of the netCDF variable along the corresponding dimen‐
sion, a value of 2 selects every other element, etc.). A NULL
stride argument is treated as (1, 1, ... , 1).
const MPI_Offset imap[]
specifies the mapping between the dimensions of a netCDF vari‐
able and the in-memory structure of the internal data array.
The elements of the index mapping vector correspond, in order,
to the netCDF variable's dimensions (imap[0] gives the distance
between elements of the internal array corresponding to the most
slowly varying dimension of the netCDF variable). Distances be‐
tween elements are specified in type-independent units of ele‐
ments (the distance between internal elements that occupy adja‐
cent memory locations is 1 and not the element's byte-length as
in netCDF 2). A NULL pointer means the memory-resident values
have the same structure as the associated netCDF variable.
VARIABLE PREFILLING
PnetCDF does not support data filling.
ENVIRONMENT VARIABLES
PNETCDF_SAFE_MODE
Set to 1 to enable metadata consistency check. Warning messages
will be printed to stdout if any inconsistency is detected.
MAILING-LISTS
A mailing list is available for discussion of the PnetCDF interface and
announcements about PnetCDF bugs, fixes, and enhancements. To sub‐
scribe or unsubscribe to the PnetCDF mailing list, visit
https://lists.mcs.anl.gov/mailman/listinfo/parallel-netcdf
SEE ALSOncmpidump(1), ncmpigen(1), ncmpidiff(1), ncmpivalid(1), pnetcdf(3).
PnetCDF User's Guide, published by Northwestern University and Argonne
National Laboratory. This document is adopted from the netCDF User's
Guide, developed at the Unidata Program Center, University Corporation
for Atmospheric Research, located in Boulder, Colorado.
PnetCDF home page at http://cucis.ece.northwest‐
ern.edu/projects/PnetCDF/.
Printed: 2024-04-28 2015-06-01 PNETCDF(3)
