summaryrefslogtreecommitdiffstats
path: root/pablo
Commit message (Collapse)AuthorAgeFilesLines
* [svn-r9852] Purpose: MaintenanceElena Pourmal2005-01-2014-6874/+0
| | | | | | | | | | Description: Removed PABLO instrumentation from HDF5 source Solution: Platforms tested: arabica, copper (parallel), mir Misc. update:
* [svn-r9729] Purpose:Quincey Koziol2004-12-291-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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:
* [svn-r8985] Purpose:Quincey Koziol2004-08-021-7/+3
| | | | | | | | | | | | | | | | | | | | | Bug fixes & code cleanups Description: Backport MPI-I/O changes from the development branch to the release branch in preparation for bringing Kent's collective chunk I/O changes back. Removed last vestiges of FPHDF5 from this branch, as it was never working here. Various code cleanups & syncrontizations to better align with development branch code and reduce diffs. Regenerate dependencies. Platforms tested: FreeBSD 4.10 (sleipnir) w/parallel IRIX64 6.5 (modi4) h5committested
* [svn-r7115] Purpose:Quincey Koziol2003-06-276-84/+220
| | | | | | | | | | | Update code Description: Incorporate Pablo support patches from Dan Wells Platforms tested: FreeBSD 4.8 (sleipnir) h5committest
* [svn-r6537] Purpose:Bill Wendling2003-03-311-4/+13
| | | | | | | | | | | | Update Description: Updated Copyright statement. Platforms tested: None needed Misc. update:
* [svn-r6276] Purpose:Quincey Koziol2003-01-132-4/+4
| | | | | | | Code cleanup Description: Check in some Pablo fixes I've had floating around for quite some time.
* [svn-r5291] Dan Wells2002-04-301-3/+3
| | | | | | | | | | | Purpose: bug fix Description: Had an #ifdef HAVE_XXX in the header file HDFIOTrace.h Solution: Changed the condition to H5_HAVE_XXX Platforms tested: Origin 2000 64 bit
* [svn-r5220] Dan Wells2002-04-226-718/+671
| | | | | | | | | | | | | Purpose: Bug Fix Description: Users could not trace MPI programs when library wasn't compiled for parallel execution Solution: Allow Pablo Trace library to set the processor number and generate the filenames for each processor. Platforms tested: Sun Workstation, HP VClass, Irix 64
* [svn-r5162] Purpose:Bill Wendling2002-04-101-1/+5
| | | | | | | | | | | | Third Time's a Charm Description: Okay...So, the H5Tinit.c isn't in the $(top_srcdir) directory but in the $(top_builddir) directory. Solution: Hack so that if it is H5Tinit that we're compiling, then point to the $(top_builddir) directory. Platforms tested: Linux
* [svn-r5161] Purpose:Bill Wendling2002-04-101-1/+1
| | | | | | | | | | | Bug Fix Fix Description: The way I fixed the bug didn't work on Linux. Solution: Changed so that we use the $* macro with a .c extension instead of assuming that $< won't have a full pathname already. Platforms tested: Linux
* [svn-r5157] Purpose:Bill Wendling2002-04-101-1/+1
| | | | | | | | | | Bug Fix Description: We couldn't find the HDF5 source files for compilation with Pablo. Solution: Have it find them in the $(top_srcdir)/src/ directory. Platforms tested: Modi4
* [svn-r5053] Purpose:Bill Wendling2002-03-081-1/+1
| | | | | | | | | | | | Bug-ish Fix Description: "make check" would barf in this directory since there's not a "check:" target. Solution: Added a ".PHONY" entry so that "make checks" and the like won't barf when they enter the pablo directory. Platforms tested: Linux
* [svn-r5051] Purpose:Bill Wendling2002-03-081-7/+6
| | | | | | | | | | dpss removal Description: Removed dpss module since we no longer have that in the source. Also fixed where the H5Tinit.c file was being looked for and how it was compiled... Platforms tested: Linux
* [svn-r5050] Purpose:Bill Wendling2002-03-081-1/+1
| | | | | | *sigh* Description: Needed to point the sed script to the CORRECT pablo directory...
* [svn-r5049] Purpose:Bill Wendling2002-03-071-3/+6
| | | | | | | | | | | Bug Fix Description: Needed more -I flags to catch some of the include files. Solution: Added them. Cleaned up the way include files and -D defines were specified in the Makefile. Platforms tested: Linux
* [svn-r5048] Purpose:Bill Wendling2002-03-071-2/+2
| | | | | | | | | | | | | Bug Fixes Description: Fixed some bugs. The CPPFLAGS wasn't being included into the Makefile. Also, there's a sed script which needed to be pointed to with the $(top_srcdir) macro. Solution: Added @CPPFLAGS@ to the CPPFLAGS line and put $(top_srcdir)/ before the sed script file's name. Platforms tested: Linux
* [svn-r5044] Purpose:Bill Wendling2002-03-071-130/+133
| | | | | | | | New Feature Addition Description: Revamped Makefile for Pablo software so that it is an option in the global configure script that the user can specify with the "--with-pablo[=DIR]" command.
* [svn-r4757] Purpose:Albert Cheng2001-12-301-2/+1
| | | | | | | | | | | | | | | | | | Removing the DPSS (gridstorage) driver source code. Description: The DPSS (using Grid-Storage) driver is retired. Removed the configure option with-gridstorage from configure.in. Cvs remove the following files ./src/H5FDdpss.c ./src/H5FDdpss.h ./test/dpss_read.c ./test/dpss_write.c Regenerated Dependencies files (some had to be hand-edited since 'make depend' did not cover them.) Removed reference to DPSS Virtual file driver from H5F.c. Platforms tested: modi4 (Parallel; -with-gass=...), eirene, arabica (fortran, cxx).
* [svn-r4395] Purpose:Dan Wells2001-08-203-21/+29
| | | | | | | | | | | | | | | | | Bug fix Description: When the Fortran interface was used on the Linux systems, there were segmentation errors. This was caused because two arrays were being accessed outside of their bounds and because the trace type parameters were specified inccorectly in the ProcTrace.inc file. There were also problems on some systems caused because the long names of HDF entries resulted in trace IDs which were too long. Solution: The lines where arrays were being accessed outside of their bounds were changed. The code in the Makefile.in and the PabloSedscr sed script file were changed so that the tracetype parameters were generated correctly. The PabloSedscr file was also modified to eliminate trace IDs for individual entries. Platforms tested: LINUX, IRIX64, IBM SP2
* [svn-r4110] Dan Wells2001-07-0510-1265/+1777
| | | | | | | | | | | | | | | Purpose: feature Description: allows the option of building the library libhdf-inst.a so that it can link with either the Pablo Trace Libraries or with the Pablo Performance Capture Facility (PCF) Solution: Added code for conditional compilation using the PCF_BUILD flag. When the library is made, the user can specify PABLO_BUILD=PCF which will cause the -DPCF_BUILD to be passed to the compiler. Platforms tested: Solaris, IRIX64
* [svn-r3957] Dan Wells2001-06-041-50/+48
| | | | | | | | | | | | Purpose: Bug fix Description: The MPI I/O calls were not being traced. Solution: Changed the calls to traceEvent from the MPI I/O tracing to HDFtraceEvent in the Pablo Traceing. Platforms tested: Irix 32 and 64, HP VClass 32 and 64 bit and Solaris
* [svn-r3874] Dan Wells2001-04-305-737/+1564
| | | | | | | | | | | | | | Purpose: feature Description: This brings the development version up to date with the release version. It now supports Pablo tracing of MPI-I/O calls from MPI-I/O versions which are not totally compliant with the standars. Solution: Added entries to bypass the current MPI-I/O tracing in the Pablo Trace Library. Platforms tested: IRIX64/Solaris/IBM SP2
* [svn-r3774] Purpose:Albert Cheng2001-04-041-2070/+0
| | | | | | | | | | | | | | | release bug fix Description: ProcTrace.inc is generated on the fly from HDFidList.h by make. It is included in the PABLO_CLEAN list which is part of the make clean and make distclean. So, the release process, which does a distclean first, could not find it for distribution later. Solution: Remove it from the source so that it is not included in the manifest of the release distribution list. (Confirmed with Dan Wells.) Platforms tested: Hard to test it without making a release. Defer to tonight snapshot release for v1.5 to verify its correctness.
* [svn-r3619] Dan Wells2001-03-137-856/+840
| | | | | | | | | | | | | | | Purpose: These changes allow the user to determine bytes requested and bytes received by MPI I/O calls. Description: User wished to know if the number of bytes requested in MPI I/O calls was save as the number actually received. Solution: Added additional fields to the HDFrecord structure for bytes requested and bytes received. Other files reflect these changes. Platforms tested: Solaris IRIX64 parallel
* [svn-r3304] Purpose:Quincey Koziol2001-01-182-29/+1
| | | | | | | | Code update Description: Remove ragged array code & tests from library before release. Platforms tested: FreeBSD 4.2 (hawkwind)
* [svn-r2810] Dan Wells2000-11-081-17/+24
| | | | | | | | | | | | | | Purpose: This fixes a bug. Description: With the previous version, the Pablo version of the library would not build. Solution: A listing of all of the files in the src directory was inserted and the library depends on their object files as well as the other .c and .f files in the pablo directory. Platforms tested: Irix, Solaris, HP Vclass, AIX
* [svn-r2690] Purpose:Quincey Koziol2000-10-171-6/+12
| | | | | | | | | | | | Bug fix Description: Non-portable constructs are causing make to fail on some machines. Solution: Replaced ":=" assignments with "=" assignments. Platforms tested: Solaris 2.6 (baldric) & gmake Solaris 2.7 (arabica) & make (a SYSV make) FreeBSD 4.1.1 (hawkwind) & make (a BSD make)
* [svn-r2635] Purpose:Quincey Koziol2000-10-051-5/+11
| | | | | | | | | | | Portability fix Description: Non-portable GNU-specific features were used. Solution: Replaced GNU-specific features with more portable (but more difficult to maintain) forms of the features. Platforms tested: FresBSD 4.1.1 (hawkwind)
* [svn-r2487] Added support for fortran. Also made the Makefile more universal.Dan Wells2000-08-294-2358/+1395
|
* [svn-r1802] Changes since 19991019Robb Matzke1999-11-011-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ---------------------- ./MANIFEST ./configure.in ./configure [REGENERATED] Added more checking for `make' features. ./Makefile.in ./doc/Makefile.in ./doc/html/Makefile.in ./doc/html/Tutor/Makefile.in ./examples/Makefile.in ./pablo/Makefile.in ./src/Makefile.in ./test/Makefile.in ./testpar/Makefile.in ./tools/Makefile.in ./config/commence.in ./config/conclude.in ./config/depend.in [REMOVED] ./config/depend1.in [NEW] ./config/depend2.in [NEW] ./config/depend3.in [NEW] ./config/depend4.in [NEW] ./config/dependN.in [NEW] The directory search stuff was moved into commence.in, thereby shortening the Makefile.in prologues. ./doc/html/Dependencies [NEW] ./doc/html/Tutor/Dependencies [NEW] ./examples/Dependencies [NEW] ./src/Dependencies [NEW] ./test/Dependencies [NEW] ./testpar/Dependencies [NEW] ./tools/Dependencies [NEW] The `.distdep' files were all renamed to `Dependencies' to make them more obvious. They are required (but may be empty) in every directory that has a Makefile.in that ends with @CONCLUDE@ (you'll get an obvious error from make if you forgot to create one). ./bin/trace ./src/H5.c Added H5E_major_t and H5E_minor_t although tracing only prints the integer value. ./src/H5E.c ./src/H5Epublic.h Added tracing information. ./src/H5FDcore.c ./src/H5FDfamily.c ./src/H5FDgass.c ./src/H5FDmpio.c ./src/H5FDsec2.c ./src/H5FDstdio.c Fixed places where FUNC_LEAVE() evaluated it's argument more than once. Added tracing information. Wrapped long lines. ./config/gnu-flags Fixed a syntax error when we don't have a gnu compiler.
* [svn-r1515] Changes since 19990715Robb Matzke1999-07-191-62/+63
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ---------------------- ./Makefile.in [1.3] ./examples/Makefile.in [1.3] ./pablo/Makefile.in [1.3] ./src/Makefile.in [1.3] ./test/Makefile.in [1.3] ./testpar/Makefile.in [1.3] ./tools/Makefile.in [1.3] ./config/commence.in [1.3] ./config/conclude.in [1.3] ./config/depend.in [1.3] Added a `.PATH' target for Irix pmake which is identical to the VPATH used by most other `make' programs. Irix 6.5 (or 6.4?) and later `make' ignores VPATH. Started all beginning-of-line comments with `##' instead of just `#' because Irix `pmake' barfs on things like the following because it sees the `# if' as a directive: # make will barf on the following line # if running Irix pmake ./config/commence.in [1.3] Added empty definitions for optional `make' macros because Irix pmake complains if it sees a macro which has never been defined. The main body of the Makefiles can redefine these macros to whatever they need.
* [svn-r1440] Fixed distclean targetQuincey Koziol1999-07-071-1/+5
|
* [svn-r1353] Added new hdf routine to the library.Dan Wells1999-06-161-1/+22
|
* [svn-r1238] prototype change in Pablo trace libraryDan Wells1999-04-291-3/+2
|
* [svn-r1225] File explaining how to build Pablo instrumented library.Dan Wells1999-04-271-0/+13
|
* [svn-r1199] Corrected a problem with file mappings.Dan Wells1999-04-201-4/+5
|
* [svn-r1197] correcting a problem that causes a compile error on SPDan Wells1999-04-191-1/+1
|
* [svn-r1185] Using same file for HDF 4 and HDF 5.Dan Wells1999-04-151-0/+1745
|
* [svn-r1181] Changes to allow automatic building of tables for event IDs and ↵Dan Wells1999-04-147-2033/+1796
| | | | for compatiblity of HDF 4 and HDF 5 trace files.
* [svn-r1180] Changes to allow automatic building of tables of event IDs and ↵Dan Wells1999-04-144-811/+312
| | | | to make HDF 4 and HDF 5 output compatible.
* [svn-r1179] Changes made to enable automatic building of list of event IDs ↵Dan Wells1999-04-143-176/+558
| | | | and to make output of HDF 4 and HDF 5 tracing compatible.
* [svn-r1123] Updates for bug fixes and new entry points in files from src ↵Dan Wells1999-03-098-680/+927
| | | | directory.
* [svn-r924] Added names of new entry points. Sorted the entry names ↵Dan Wells1998-11-181-275/+282
| | | | alphabetically.
* [svn-r923] Using buff to hold tracefile name.Dan Wells1998-11-181-0/+1
|
* [svn-r922] Using CLOCK structure for timings as opposed to doubles for ↵Dan Wells1998-11-182-59/+72
| | | | better accuracy.
* [svn-r909] Dummied out make of progs and test to avoid rebuild of the library.Dan Wells1998-11-131-33/+9
|
* [svn-r908] Fixed a bug in the I/O totals computation.Dan Wells1998-11-131-21/+30
|
* [svn-r881] Updates to support MPIO real-time tracingDan Wells1998-11-062-25/+731
|
* [svn-r880] Made some changes for 64 bit file IDsDan Wells1998-11-061-2/+2
|
* [svn-r866] Modified for parallel configuration.Dan Wells1998-11-031-1/+9
|