Pnetcdf New File Format
kgao at eecs.northwestern.edu
kgao at eecs.northwestern.edu
Mon Aug 11 22:20:13 CDT 2008
Hi, Katie,
Thank you very much for testing the new pnetcdf file format.
Current version can not support the size of each dimension larger
than 2^31 bytes. The limitation comes from >
MPI_Type_create_subarray(int ndims, int array_of_sizes[], int >
array_of_subsizes[], int array_of_starts[], int order, MPI_Datatype
oldtype, MPI_Datatype *newtype) function. The array_of_sizes are
(int *) type.
1 dimensional array could support the size larger than 4GB in the
developing version. I am working against the limitation about
multi-dimensional array. When I finish this part, we will update the
pnetcdf library.
MPI_Offset is replaced by int64_t in current version.
Thanks and regards,
Kui.
----- Original Message -----
From: "Katie Antypas" <kantypas at lbl.gov>
To: <parallel-netcdf at mcs.anl.gov>
Sent: Monday, August 11, 2008 7:23 PM
Subject: Pnetcdf New File Format
> Hi Rob,
>
> I am testing out the new pnetcdf file format which is supposed to allow
> variable sizes greater than 4GB (as long as they have fewer than 2^31
> elements). I am running on the Franklin Cray XT4 system at NERSC with
> the PGI compilers and have not successfully created a 1d variable size
> larger than 4GB. (I'll try multi-dimensions soon.)
>
> I pass "NC_CLOBBER | NC_64BIT_DATA" to ncmpi_create now. Also, I was
> getting type warnings and noticed a new type int64_t in places where
> type int and MPI_Offset were used before in a number of calls. What is
> your recommendation to users regarding the int64_t type? Should they
> replace MPI_Offset with?
>
> In either case though, if I do or don't make any changes to the ncmpi
> calls (namely ncmpi_create, ncmpi_def_var, ncmpi_put_vara_double_all)
> then I can only create a variable up to 2GB variable size which is under
> 2^31 NC_DOUBLE elements in a 1 dimensional array. (If we were counting
> bytes, rather than doubles my test would be at the 2^31 elements
> limit.) I didn't think this was the way elements were counted though?
>
> Katie
>
More information about the parallel-netcdf
mailing list