Bug fix
Problem:
On the ASCI Red machine, the configure step is executed from the platform
cross compiler, so that the configure test for "long long int" format support
was inconclusive.
Solution:
It was necessary to uncomment the line
#hdf5_cv_printf_ll=${hdf5_cv_printf_ll='ll'}
in config/intel-osf1 to force "long long int" format support.
Platform tested:
TFLOPS Application server, Intel TFLOPS
./configure.in
./config/BlankForm
./src/H5.c
Configure tries to figure out how to print `long long' types
and then defines PRINTF_LL_WIDTH to be `ll' or `q' or
something. It does this by running little sprintf() programs
with various formats until it gets one that works. If this
causes problems when cross compiling (like with parallel
machines) then you may add the following to the appropriate
config file:
hdf5_cv_printf_ll=${hdf5_cv_printf_ll='ll'} or
hdf5_cv_printf_ll=${hdf5_cv_printf_ll='q'} or
hdf5_cv_printf_ll=${hdf5_cv_printf_ll='l'}
./config/intel-osf1
./config/irix5.3
Updated these config files to match the others. This allows
the `--enable-production' configure flag to work properly.
Documentation (mostly!)
Solution:
This change in the hdf5/config/intel-osf1 file makes the $(RUNTEST)
variable used in the Makefiles explicitly list the number of processors
used during execution (the change is: yod -> yod -sz 1).
Platform tested:
Intel TFLOPS (ASCI Red)
To resolve a reference.
Problem:
Reference to routine 'getrusage()' is unresolved during link step.
Solution:
In the site config file, hdf5/config/intel-osf1, the line
LIBS="-L./ -L../"
has been extended to include ...
LIBS="-L./ -L../ -lnoop_stubs",
a reference to a library which includes the 'getrusage()' routine.
Platform tested:
sasn100
New feature
Problem:
No support of sequential HDF5 on ASCI Red machine.
Solution:
Set-up site config file for the ASCI Red platform.
Set environmental varibles CC, AR, RANLIB, RUNTEST,
and default value for CCFLAGS if not already set.
Platform tested:
TFLOPS Application Server: sasn100
ASCI Red machine: janus
