summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* [svn-r5730] Purpose:Bill Wendling2002-07-014-12/+23
| | | | | | | | | | | Feature Add Description: Install the h5perf program (previously called pio_perf). This required the libh5test library to be compiled statically. I copied how things were compiled statically for the h5tools library into the test/Makefile.in. Platforms tested: Linux
* [svn-r5725] Purpose:Bill Wendling2002-06-283-10/+2
| | | | | | | | | | | Bug Fix Description: Removed reference to the Tutor/ directory in the doc tree since we aren't going to distribute it for this release. Solution: Removed the references from the configure and appropriate Makefile.in Platforms tested: Linux
* [svn-r5724] Raymond Lu2002-06-271-3/+2
| | | | | | | | | | | Purpose: bug fix Description: In H5HG_remove, heap object header wasn't included for size("need" in H5HG_remove). Solution: Added heap object header size in. Platforms tested: Linux 2.2(eirene).
* [svn-r5722] Snapshot version 1.4 release 4 (pre5)HDF Admin2002-06-2710-74/+136
|
* [svn-r5721] MuQun Yang2002-06-271-1/+2
| | | | | | | | Purpose: update install on windows doc. Description: Solution: Platforms tested:
* [svn-r5719] Purpose:Quincey Koziol2002-06-273-95/+180
| | | | | | | | | | New Feature Description: Added support for collective I/O with MPI and HDF5 access methods. Platforms tested: IRIX64 6.5 (modi4) w/parallel
* [svn-r5717] Purpose:Quincey Koziol2002-06-273-195/+150
| | | | | | | | | | | | New Feature Description: Added interleaved block pattern to MPI and HDF5 access methods. Also, changed the blocks to just use the same size as the regular blocks for I/O, instead of a separate block size. Platforms tested: IRIX64 6.5 (modi4) w/parallel
* [svn-r5715] Description:Albert Cheng2002-06-271-1/+1
| | | | | | Fixed a typo in LT_LINK_EXE=... line. Platforms tested: Eirene (pp), arabica, modi4
* [svn-r5714] MuQun Yang2002-06-261-3/+2
| | | | | | | | Purpose: remove zlib related old info. Description: Solution: Platforms tested:
* [svn-r5713] MuQun Yang2002-06-261-8/+7
| | | | | | | | Purpose: correct typos. Description: Solution: Platforms tested:
* [svn-r5712] Elena Pourmal2002-06-261-21/+5
| | | | | | | Purpose: Maintenance Description: Updated INSTALL_Windows_withF90.txt for the upcomin release
* [svn-r5711] Raymond Lu2002-06-261-1/+3
| | | | | | | | | Purpose: Information update. Description: Added IA-32 platform result. Platforms tested: platinum.
* [svn-r5709] Purpose:Bill Wendling2002-06-254-6/+6
| | | | | | Feature Fix Description: Changed NPROCS to 2 instead of 3.
* [svn-r5708] Purpose:Bill Wendling2002-06-254-21/+29
| | | | | | | | | | | | Bug Fix Description: I was nullifying the RUNPARALLEL and other macros when I shouldn't have been (they were set to sensible things). I also ported the RUNPARALLEL macros from the hdf5/config directory to the hdf5/fortran/config directory for the powerpc-ibm-[45].x files. Solution: Removed the offending 'RUNPARALLEL=""' lines. Also changed default number of processes to 3 instead of 2.
* [svn-r5706] Purpose:Quincey Koziol2002-06-251-0/+4
| | | | | | | | | | | | | | Bug Fix. Description: Contiguous types created for "all" and contiguous hyperslab selections was not being committed before using them. Solution: Commit them. :-) This fixes the problems on the LLNL Blue Pacific machine. Platforms tested: LLNL Blue Pacific w/parallel.
* [svn-r5705] MuQun Yang2002-06-251-3/+12
| | | | | | | | | | Purpose: Update release doc for windows-specified issue. Description: Things like zlib out, binary and source with different zlib and backward compatible are addressed. Solution: Platforms tested:
* [svn-r5704] MuQun Yang2002-06-251-32/+28
| | | | | | | | | Purpose: update INSTALL_Windows.txt Description: zlib is moved out of HDF5 source tree, re-arrange the project file. Solution: Platforms tested:
* [svn-r5703] Purpose:Bill Wendling2002-06-251-6/+12
| | | | | Described the removal of the H4 to H5 tools from the main source tarball...
* [svn-r5702] Elena Pourmal2002-06-251-1/+4
| | | | | | | | Purpose: Maintenance Description: Added information about overloaded h5dwrite(read)_f and h5awrite(read)_f functions in 1.4.4 release.
* [svn-r5700] Purpose:Bill Wendling2002-06-251-24/+24
| | | | | | | | | | | | Bug Fix Description: Making of the programs when using the --srcdir option didn't work. It couldn't find the files to compile. Solution: Specified where the files are by prepending the $(srcdir) macro to them. Platforms tested: Linux
* [svn-r5699] Purpose:Quincey Koziol2002-06-251-9/+31
| | | | Added "Performance Improvements" section.
* [svn-r5698] Elena Pourmal2002-06-251-5/+3
| | | | | | | | Purpose: Maintenance Description: I forgot to describe C compiler flag -DIA64 that should be specified in order to build Fortran Library on IA64.
* [svn-r5697] Elena Pourmal2002-06-251-15/+31
| | | | | | | | Purpose: Maintenance Description: Did more clean-up of the "Tested Platforms" section and added information how to build with Intel Fortran compiler.
* [svn-r5695] Purpose:Quincey Koziol2002-06-251-2/+2
| | | | Update FreeBSD version info.
* [svn-r5694] Elena Pourmal2002-06-251-4/+10
| | | | | | | Purpose: Maintenance Description: Updated information about AIX 5.1, SV1 and Linux 2.4 testing platforms.
* [svn-r5693] Purpose:Bill Wendling2002-06-241-15/+23
| | | | | | | | | | | Feature Fix Description: Made the h5cc build command visible. Also updated the copyright statement... Solution: Removed the "@" from the front of the command... Platforms tested: Linux
* [svn-r5691] Purpose:Bill Wendling2002-06-241-24/+24
| | | | | | | | | | | | | | Bug Fix Description: The 'make' in the examples directory was using the "h5cc" script, but was also trying to make things the old-fashioned way (with libtool). This was causing problems on machines...there'd be conflicts and such, since h5cc doesn't use libtool... Solution: Stopped it from using libtool in the first place by having the compilation rule go directly from the .c file to the executable. Platforms tested: Linux
* [svn-r5689] Purpose:Quincey Koziol2002-06-242-21/+39
| | | | | | | | | | | | | | | | | | | | | | | | | | Bug Fix Description: When parallel I/O is used, the MPI-I/O VFL driver uses a "lazy" model to call MPI_File_set_view() in order to reduce the number of calls to this function. However, this is unsafe, because if a collective I/O which uses MPI derived types (and thus uses MPI_File_set_view()) is immediately followed by an independent I/O, the code will attempt to call MPI_File_set_view() in order to switch back to the default view of the file. MPI_File_set_view() is a collective call however, and this causes the application to hang. Solution: Removed "lazy" MPI_File_set_view() code, instead set the file view when it is needed (with MPI derived types) and immediately set the file view back to the default view before leaving the I/O routine. Platforms tested: IRIX64 6.5 (modi4) w/parallel. Also, tested with the latest development and release code for the SAF library, which now works correctly with this change. (Although the release branch of the SAF library seems to have a bug, this 1.4.4 release candidate code gets as far as the version the SAF library is released on top of (1.4.2-patch1, I believe)).
* [svn-r5688] Description:HDF Admin2002-06-209-34/+34
| | | | | | | Make a tarball of 1.4.4-pre4 that contains CVS stuff for easier commit later. Bump up version information by bin/h5vers -i. Platforms tested: No test since this is the same process the release script will do.
* [svn-r5687] MuQun Yang2002-06-201-0/+0
| | | | | | | | | | Purpose: update fortran zip file Description: the effect of moving zlib out of windows hdf5 source tree makes the update of all fortran related project settings. Solution: Platforms tested: windows 2000
* [svn-r5685] Purpose:Albert Cheng2002-06-202-2/+2
| | | | | | | | | | | | | Special hack fix for snow.llnl.gov. aclocal.m4: Snow's names were not included in the special hack. Added its names in. Removed the trailing * in pacific.llnl.gov too. configure: Derived from aclocal.m4 Platforms tested: Snow of LLNL. Verified with Blue that everything still works.
* [svn-r5684] MuQun Yang2002-06-191-0/+0
| | | | | | | | | | | Purpose: move zlib out of windows source distribution tree Description: Need to update most project settings to reflect this change Expect zlib library is installed at c:/zlib114/lib and c:/zlib114/dll Solution: Platforms tested: windows 2000
* [svn-r5683] Purpose:Quincey Koziol2002-06-1910-42/+90
| | | | | | | | Version bump Description: I'm making another prerelease available for the SAF team, with some features I'd like them to test, so bump the prerelease number again.
* [svn-r5682] Purpose:Quincey Koziol2002-06-199-34/+34
| | | | | | | | | Update version info. Description: Bump the prelease number to reflect the fact that I gave out a prerelease to the SAF developers yesterday and I don't want to confuse people when we make another prelease tarball.
* [svn-r5681] Purpose:Quincey Koziol2002-06-195-43/+103
| | | | | | | | | | | | | | | | | | | | New feature. Description: There is some discussion among the SAF team as to whether it is better to use MPI derived types for raw data transfers (thus needing a MPI_File_set_view() call), or whether it is better to use a sequence of low-level MPI types (i.e. MPI_BYTE) for the raw data transfer. Solution: Added an internal flag to determine whether derived types are preferred (the default), or whether they should be avoided. An environment variable ("HDF5_MPI_PREFER_DERIVED_TYPES") can be set by users to control whether MPI types should be used or not. Set the environment variable to "0" (i.e.: 'setenv HDF5_MPI_PREFER_DERIVED_TYPES 0') to avoid using MPI derived types. Platforms tested: IRIX64 6.5 (modi4) w/parallel
* [svn-r5678] Purpose:Quincey Koziol2002-06-192-6/+12
| | | | | | | | | | | Code cleanup Description: Changed ifdef name from "VERBOSE" to "BARRIER_CHECKS", to better describe what it affects. Platforms tested: IRIX64 6.5 (modi4) w/parallel
* [svn-r5676] Purpose:Quincey Koziol2002-06-192-18/+4
| | | | | | | | | | | Code improvement Description: Some small code cleanups and took out the code the was turning off the metadata cache for parallel I/O (!) Platforms tested: IRIX64 6.5 (modi4) w/parallel
* [svn-r5675] Purpose:Quincey Koziol2002-06-1936-193/+182
| | | | | | | | | | Code cleanup Description: Removed more compiler warnings, etc. Platforms tested: Linux 2.2.x (eirene) w/parallel
* [svn-r5673] Elena Pourmal2002-06-191-0/+14
| | | | | | | | | | | Purpose: IA64 fortran port Description: When I did IA64 port, I never checked in the changes Solution: Check in the changes Platforms tested: Titan and OSF1 v5.1
* [svn-r5672] Elena Pourmal2002-06-191-8/+8
| | | | | | | | | | | Purpose: Code clean up Description: On OSF1 systems compiler complained about NGROUPS variable redefinition. Solution: Rename NGROUPS to H5_NGROUPS Platforms tested: OSF1 V5.1 at PSC
* [svn-r5671] Purpose:Quincey Koziol2002-06-193-26/+0
| | | | | | | | | | | Code cleanup Description: Remove "COALESCE_READS" ifdefs, which were brought in by the DPSS VFL driver and are no longer used. Platforms tested: IRIX64 6.5 (modi4) w/parallel
* [svn-r5669] Purpose:Quincey Koziol2002-06-191-0/+4
| | | | | | | | | | Code cleanup Description: Remove debugging printf Platforms tested: IRIX64 6.5 (modi4) w/parallel
* [svn-r5668] Purpose:Quincey Koziol2002-06-1942-377/+240
| | | | | | | | | | Code cleanup Description: Turn on more warnings in the IRIX builds and clean them up. Platforms tested: IRIX64 6.5 (modi4) w/parallel, both -n32 and the default (-64?) mode
* [svn-r5666] Updated with the two new files,Albert Cheng2002-06-181-0/+2
| | | | | + ./config/powerpc-ibm-aix5.x + ./fortran/config/powerpc-ibm-aix5.x
* [svn-r5665] Purpose:Albert Cheng2002-06-182-2/+56
| | | | | | | | | | | | | | | | | | | | | | | | Porting to AIX 5.x Description: configure.in: fortran/configure.in: Added a case to group all AIX 5.* versions as aix5.x. This allows them to share one common config/*aix5.x file. configure: fortran/configure: Derived from configure.in (done in eirene). config/powerpc-ibm-aix4.x: Added a comment explaining why not to cache sizeof size_t and off_t fortran/config/powerpc-ibm-aix4.x: Turned of cache of sizeof size_t and off_t because they are depedent on compiler options. config/powerpc-ibm-aix5.x: fortran/config/powerpc-ibm-aix5.x: New config file for AIX 5.X Platforms tests: LLNL Blue, Frost, Snow, both serial and parallel. (Snow's parallel does not work yet because it needs the host specific hack in aclocal.m4.)
* [svn-r5664] Purpose:Albert Cheng2002-06-186-8/+106
| | | | | | | | | | | | | | | | | | | | | | | | Porting to AIX 5.x Description: configure.in: fortran/configure.in: Added a case to group all AIX 5.* versions as aix5.x. This allows them to share one common config/*aix5.x file. configure: fortran/configure: Derived from configure.in (done in eirene). config/powerpc-ibm-aix4.x: Added a comment explaining why not to cache sizeof size_t and off_t fortran/config/powerpc-ibm-aix4.x: Turned of cache of sizeof size_t and off_t because they are depedent on compiler options. config/powerpc-ibm-aix5.x: fortran/config/powerpc-ibm-aix5.x: New config file for AIX 5.X Platforms tests: LLNL Blue, Frost, Snow, both serial and parallel. (Snow's parallel does not work yet because it needs the host specific hack in aclocal.m4.)
* [svn-r5663] Purpose:Quincey Koziol2002-06-185-219/+30
| | | | | | | | | | | | | | | | | Bug fix. Description: The chunking code was using internal allocation routines to put blocks on a free list for reuse, instead of using the system allocation routines (ie. malloc, free, etc.). This causes problems when user filters attempt to allocate/free chunks for their algorithm's use. Solution: Switched the chunking code back to using the system allocation routines, we can address performance issues with them if it becomes a real problem. Platforms tested: Linux 2.2.x (eirene) && IRIX64 6.5 (modi4)
* [svn-r5661] Purpose:Quincey Koziol2002-06-186-98/+219
| | | | | | | | | | | | Code optimization Description: Avoid creating MPI types (and thus requiring a MPI_File_set_view() call) when contiguous selections are used for dataset I/O. This should be a performance improvement for those sorts of selections. Platforms tested: Linux 2.2.x (eirene) w/parallel && IRIX64 6.5 (modi4) w/parallel & FORTRAN
* [svn-r5658] Updated with TFLOPS information.Albert Cheng2002-06-171-2/+2
|
* [svn-r5655] Updated.Albert Cheng2002-06-171-4/+21
|
generated by cgit v0.12 at 2024-07-19 13:09:00 (GMT)