Purpose:
Remove H5_MPI_SPECIAL_COLLECTIVE_IO_WORKS and
H5_MPI_COMPLEX_DERIVED_DATATYPE_WORKS #defines from source.
Description:
Two advanced parallel functionalities, special collective IO and
complex derived datatypes, are not supported by older
implementations of mpi, and thus our code limits the use of these
features with #ifdefs and has checks in configure to set them (or
not). Unfortunately, configure can't actually run a parallel check
to see if these features are working (nor not) so it resorts to
looking in the config files where they are explicity enabled or
disabled based on versions of mpi, sytems being built on, or for
no documented reason at all (i.e. just set to on or off as some
'default'). Overriding these settings is easy if need be, provided
it is known that it needs to be done to get improved performance,
and oftentimes it is not.
Most new MPI implementations successfully handle the functionality
requested when these #defines are set, and many of the "turn these
features off" cases in the config files are for old (> 5 years)
versions of MPI and retired systems (such as NCSA's tungsten).
Therefore, the decision has been made to remove the support for
these old versions of MPI and systems that cannot handle these
behaviors. The #ifdefs and supporting setup in the config/ files
and configure script has been removed, and the code executed when
these options were not set removed from the source.
In passing, this commit also cleans up some whitespace issues in
both t_mpi.c and H5Dmpio.c. Furthermore, in t_mpi.c, the special
collective IO test was not getting regularly run due to it being
written to work only with four processes (we regularly test with
six, previously with three), and thus it failed when actually run
due to an out of bounds data buffer assignment. It has been
modified to run at any number of processes greater than four, and
the memory problem has been fixed so the test passes.
Tested:
jam, h5committest, ember
CFLAGS overhaul
Description:
Modified the way configure handles CFLAGS.
(note: all changes also apply to FCFLAGS, CXXFLAGS, CPPFLAGS, and LDFLAGS).
1. The configure process will now always preserve a user's CFLAGS
environment variable setup. Any additional flags necessary for compilation
added at configure time will be passed into the Makefiles as AM_CFLAGS,
which is an automake construct to be used in addition to CFLAGS.
This will allow a user to have the final say, as CFLAGS will always appear
later in the compile line than AM_CFLAGS. Additionally, setting CFLAGS
during make will no longer completely erase all flags set by configure,
since they're maintained in AM_CFLAGS.
2. Additionally, where possible, flags previously being assigned directly
into CFLAGS (and thus propagating into h5cc) have now been redirected into
H5_CFLAGS, so they're used ONLY for compiling hdf5, and not embedded into
the h5cc wrapper script as well.
*Note that H5_CFLAGS ultimately is assigned into AM_CFLAGS for use in the
Makefiles. Complete description of changes and build process will be
included in a Configure Document that Elena and I are working on.
3. Removed unsupported config files. This includes:
config/dec-osf*
config/hpux11.00
config/irix5.x
config/powerpc-ibm-aix4.x
config/rs6000-ibm-aix5.x
config/unicos*
4. Modified configure summary to display additional values. Specifically,
appropriate AM_* variables are being shown, as well as H5_FCFLAGS and
H5_CXXFLAGS, which were for some reason not already present.
Tested:
- H5committest
- Tested on all THG / NCSA machines, using several combinations of the more
prominent configure options (c++, fortran, szip, threadsafe, parallel,
et cetera). (Thanks to Quincey for rysnc testing setup!)
- With regards to new automated testing, anything *necessary* for
compilation will be caught by the daily tests as it stands now. (i.e.,
if LDFLAGS is not properly set when szip is used, linking will fail).
Additionally, with regards to which flags get into h5cc, if any
*necessary* flags have been improperly removed, then daily tests should
fail during make installcheck. Additional machine-specific desired
behaviors and/or checks may have to be set up separately within the
daily tests, so this is something to work on.
Improve default settings.
Use mpicc, mpif90, mpirun as the default $CC, $FC, and $RUNPARALLEL if
enable-parallel.
Tested:
in TG-NCSA both serial and parallel.
Add collective chunk IO supports
Description:
Added a macro hdf5_mpi_special_collective_io_works to filter out
some mpi-io packages that don't support collective IO for no IO
contributions in some processes.
Solution:
1.
"hdf5_mpi_special_collective_io_works=${hdf5_mpi_special_collective_io_works=
'no'}"
has been added at the end of file ia64-linux-gnu and linux-gnulibc1
2. Some comments are added in ia64-linux-gnu and linux-gnulibc1.
3. Documents are added inside RELEASE.txt.
Platforms tested:
Parallel:
IBM AIX 5.2(copper)
Linux (heping) mpich-1.2.6
SDSC Teragrid mpich-1.2.5
Linux(Tungsten) mpich-1.2.6
Altix(NCSA cobalt)
Seq:
Linux(heping)
Misc. update:
Bug fix.
Description:
The previous way of detecting the MPICH version fails if the suspected
$CC does not give the expected MPICH version information. Though no
consequence, it generates error messages that alarm users.
Also, mpich2 gives the version information as if it were mpich v1.0.2
which was incorrectly included as an earlier version of the origianl
mpich.
Solution:
Implemented a more robust code to detect the version and narrow the
recognition down to v1.2.0-v1.2.5. Also, the code were duplicated in
two files (linux-gnulibc1 and ia64-linux-gnu). Combined them into a
new file called mpich.
Platforms tested:
Tested in heping using mpicc and mpich2/mpicc and also in tg-ncsa.
Misc. update:
Updated MANIFEST.
Description:
Add source code copyright notice; comment symbols vary by type of file.
Platforms tested:
No changes that should cause any problems. Nonetheless, the tree will
be checked out fresh and tests run immediately post-commit.
Code cleanup
Description:
Removed Fortran type sizes from config/* files.
Solution:
These lines weren't doing anything anymore; they've been replaced by automatic
type generation. This is just housekeeping to remove them from
the config/* files.
Platforms tested:
mir, sol, modi4
Updating phase 2 work of collective IO
Description:
When the size is bigger than some value for MPI derived data type, mpich 1.2.5 and lower
version won't work any more, so in the configuration file, we will check the version number
and switch from collective IO to independent IO by turning off complex derived datatype.
Solution:
Platforms tested:
linux 2.4, AIX 5.1, Linux 2.4 IA64 and IRIX 6.5
Misc. update:
Description: Altix configuration file used icc for the default C++ compiler.
Since cobalt moved to Intel 8.1, C++ compilation failed.
Solution: Changed icc to icpc for the default C++ compiler on Altix.
Platforms tested: cobalt
Misc. update:
Automake version upgrade
Description:
Upgraded automake version from 1.6.2 to 1.9.5.
Changed bin/reconfigure script to use automake 1.9.5.
Changed configure.in and Makefiles to use new FCFLAGS and FC variables
instead of FFLAGS and F9X.
Automake and configure should now do the lion's share of the work
supporting Fortran 9X; macros in acsite.m4 are now mostly unused (will
be cleaned later).
Altered how configure handles pmake; now root-level Makefile.in is
processed by bin/reconfigure to have a .MAKEFLAGS target, since
automake no longer allows us to define unused variables.
Configure now always checks for C++ compiler even if it is not
used, since automake thinks this is the Right Thing To Do and
will break otherwise.
Platforms tested:
Sol, copper, heping, mir, sleipnir, eirene, pommier, kelgia, modi4.
Bug Fix/Code Cleanup/Doc Cleanup/Optimization/Branch Sync :-)
Description:
Generally speaking, this is the "signed->unsigned" change to selections.
However, in the process of merging code back, things got stickier and stickier
until I ended up doing a big "sync the two branches up" operation. So... I
brought back all the "infrastructure" fixes from the development branch to the
release branch (which I think were actually making some improvement in
performance) as well as fixed several bugs which had been fixed in one branch,
but not the other.
I've also tagged the repository before making this checkin with the label
"before_signed_unsigned_changes".
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel & fphdf5
FreeBSD 4.10 (sleipnir) w/threadsafe
FreeBSD 4.10 (sleipnir) w/backward compatibility
Solaris 2.7 (arabica) w/"purify options"
Solaris 2.8 (sol) w/FORTRAN & C++
AIX 5.x (copper) w/parallel & FORTRAN
IRIX64 6.5 (modi4) w/FORTRAN
Linux 2.4 (heping) w/FORTRAN & C++
Misc. update:
Improvement.
Description:
Change the default CC, F9X and CXX compilers from ecc/efc/ecc
to icc/ifort/icc because Intel keeps changing their compiler
names. This eliminated the warning messages that a wrong
compiler name is used.
Platforms tested:
Tested in Tg-login NCSA only since that is the only
IA64 platform on site.
Bug fix.
Description:
$CXX_BASENAME was not set yet if $CXX was pre-set to g++. In turn,
CXX_flags are not picking up the g++ values.
Solution:
The correct solution should be done in configure which should have
setup CXX_BASENAME if $CC is set before sourcing this file.
Put a special patch here for g++ for now.
(Also added the recognization of icc as another name for Intel
compilers.)
Platforms tested:
No h5committest but tested in TG-NCSA since these changes affected
the IA64 platform only.
Misc. update:
Fix to config for ia64-linux (C++)
Description:
missing character in config file
Solution:
add the missing character
Platforms tested:
'hal'
Misc. update:
Improvement.
Description:
setup default setting for C++ API. Default to use the ecc compiler.
Platforms tested:
Tested in TG-ncsa which is the IA64 platform. None of the standard committest
platforms would have tested this change.
Misc. update:
bug fix.
Description:
The previous patch of -D__GNUC__ was causing failure in the
newer compiler. The previous failure could not be repeated
any more. So, removed it.
Platforms tested:
Tested only in TG-NCSA since the change affects only the ia64 platform.
Misc. update:
Description: After titan updated ecc compiler, int64_t cannot be found.
Solution: Added -D__GNUC__ to CFLAGS to enable int64_t in /usr/include/stdint.h
Platforms tested: titan(titan specific)
Bug fix
Description:
Fix problems building on Debian Linux when Intel's "ecc" compiler is
not available.
Platforms tested:
Eyeballed - very trivial patch from user.
Bug Fix
Description:
The FFLAGS, CXXFLAGS, and CPPFLAGS variables weren't carrying
user-defined values into the Makefiles.
Solution:
Changed the flags from FOO="..." to FOO="$FOO ..."
Platforms tested:
Copper
Verbena
Arabica
Misc. update:
Purpose: Bug fix (by Bill Wendling)
Description: When efc compiler was used, FFLAGS were not set up
to deal with !DEC amd !MS dirctive and to use
-Vaxlib flag for exit call.
Solution: Modify the file to set up the flag.
Platforms tested: titan
Misc. update:
Update
Description:
Revamped the configuration system. The configurations for the Fortran
and C++ libraries are no longer separate from the "main"
configuration system. This involved removing the "configure*" and
"aclocal.m4" files from the fortran/ and c++/ subdirectories. Also
merging settings in the config/ subdirectories into the main config/
subdirectory.
Fortran header files had to be modified a little for Linux. It was
checking if it was a Linux machine by some #defines, however with the
-std=c99 switch, these defines weren't there. I added a check for
some other ones which should be there whether the -std=c99 switch is
used or not.
Platforms tested:
Verbena (Fortran & C++)
Sol (Fortran & C++)
Copper (Fortran & C++)
Modi4 (Parallel, Fortran, & C++)
Misc. update:
Feature (bug fix)
Description:
Added a new configure file specifically for the IA64 platform
in which ecc and efc are the default compilers.
Also added all the Fortran special setup in the fortran version
Platforms tested:
no h5committest since this is a IA64 platform stuff.
Tested in Titan.
Misc. update:
MANIFEST Updated.
