Environment.html
Introduction to HDF5 HDF5 Reference Manual Other HDF5 documents and links |
And in this document, the
HDF5 User's Guide:
Files
Datasets Data Types Dataspaces Groups References Attributes Property Lists Error Handling Filters Caching Chunking Debugging Environment DDL Ragged Arrays |
1
, PHDF5 will use the MPI optimized
code to perform parallel read/write accesses to datasets.
Currently, this optimization fails when accessing extendable
datasets. The default is not to use the optimized code.
1
, PHDF5 will write the metadata
via process 0 of each opened parallel HDF5 file. This should
improve I/O throughput. The default is not to use this
optimization.
configure --help
Introduction to HDF5 HDF5 Reference Manual Other HDF5 documents and links |
And in this document, the
HDF5 User's Guide:
Files
Datasets Data Types Dataspaces Groups References Attributes Property Lists Error Handling Filters Caching Chunking Debugging Environment DDL Ragged Arrays |
Variable | Description |
---|---|
HDF5_DEBUG |
Defines a list of debugging switches documented in the Debugging section of the HDF5 User's Guide. |
HDF5_NOCLEANUP |
If set then programs in the test directories do not remove temporary files. The default is for each test to remove the files before exit if the test succeeds but to leave the files if the test fails. |
HDF5_PREFIX |
The value of this variable is prepended to all temporary file names created by the test programs and separated from the base name of the file by a slash. The default is no prefix. |
This variable should hold the name of a low-level HDF5
file driver such as sec2 , stdio ,
core , split , or
family . The family driver also takes an
optional real-valued family member size in MB which
defaults to 1. If this variable is not set or empty then
the library-defined default file driver is used (which can
be set at configuration time with the H5F_LOW_DFLT cpp
constant, usually sec2 ). |
|
HDF5_MPI_OPT_TYPES |
When set to 1 , parallel HDF5 will use the
MPI-optimized code to perform parallel read/write accesses
to datasets. Currently, this optimization fails when
accessing extendable datasets. The default is not to use
the optimized code. |
HDF5_MPI_1_METAWRITE |
When set to 1 , parallel HDF5 will write the
metadata via process 0 of each opened parallel HDF5 file.
This should improve I/O throughput. The default is not to
use this optimization. |
configure --help