|
Packit Service |
a1973e |
2012-09-20
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* 708d173a man/man1/papi_avail.1 man/man1/papi_clockres.1
|
|
Packit Service |
a1973e |
man/man1/papi_command_line.1...: Rebuild the manpages for a 5.0.1 release.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
2012-09-19
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* 29cdd839 doc/Doxyfile-common papi.spec src/Makefile.in...: Bump the version
|
|
Packit Service |
a1973e |
number for a 5.0.1 release.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* bb7727f6 src/libpfm4/examples/fo src/libpfm4/examples/injectevt.c
|
|
Packit Service |
a1973e |
.../bin/usr/local/include/perfmon/perf_event.h...: Cleanup a botched libpfm4
|
|
Packit Service |
a1973e |
update. As Steve Kaufmann noted, I botched an update of libpfm4.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
2012-09-18
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* dc117410 src/configure src/configure.in: Remove a trailing slash in libpfm4
|
|
Packit Service |
a1973e |
pathing. Addresses an issue in rpmbuild when using bundled libpfm4. Reported
|
|
Packit Service |
a1973e |
and patched by William Cohen <wcohen@redhat.com>
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
2012-09-17
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* e196b89b src/components/cuda/configure src/components/cuda/configure.in:
|
|
Packit Service |
a1973e |
Minor changes to CUDA configure necessary to get it running smoothly on the
|
|
Packit Service |
a1973e |
Kepler architecture.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
2012-09-11
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* 866bd51c src/papi_internal.c src/papi_preset.c: Fix preset bug The preset
|
|
Packit Service |
a1973e |
code was only initializing the first element of the preset code[] array.
|
|
Packit Service |
a1973e |
Thus any event with more than one subevent was not terminated at all, and the
|
|
Packit Service |
a1973e |
preset code would use random garbage as presets. This exposed another
|
|
Packit Service |
a1973e |
problem; half our code assumed a 0 terminated code[] array, the rest was
|
|
Packit Service |
a1973e |
looking for PAPI_NULL (-1). This standardizes on PAPI_NULL, with comments.
|
|
Packit Service |
a1973e |
Hopefully this might fix PAPI bug #150. This is a serious bug and should be
|
|
Packit Service |
a1973e |
included in the next stable release.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
2012-08-29
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* b978a744 src/configure src/configure.in: configure: fix autodetect perfmon
|
|
Packit Service |
a1973e |
case The fixes I made yesterday to libpfm include finding broke on perfmon2
|
|
Packit Service |
a1973e |
PAPI if you were letting the library be autodetected. This change should fix
|
|
Packit Service |
a1973e |
things. Tested on an actual 2.6.30 perfmon2 system.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* 4386e6e5 src/libpfm4/Makefile src/libpfm4/README src/libpfm4/config.mk...:
|
|
Packit Service |
a1973e |
Update libpfm4 included with papi to 4.3
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
2012-08-28
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* 729a8721 src/configure src/configure.in: configure: don't check for libpfm
|
|
Packit Service |
a1973e |
if incdir specified When various --with-pfm values are passed, extra checks
|
|
Packit Service |
a1973e |
are done against the libpfm library. This was being done even if only the
|
|
Packit Service |
a1973e |
include path was specified, which probably shouldn't be necessary. This
|
|
Packit Service |
a1973e |
broke things because a recent change I made had the libpfm include path be
|
|
Packit Service |
a1973e |
always valid.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* bc9ddffc src/configure src/configure.in: Fix compiling with separate
|
|
Packit Service |
a1973e |
libpfm4 The problem was if you used any of the --with-pfm-incdir type
|
|
Packit Service |
a1973e |
directives to configure, it would them assume you wanted a perfmon2 build.
|
|
Packit Service |
a1973e |
This removes that assumption. I did check this with perfmon2, perfctr, and
|
|
Packit Service |
a1973e |
perf_event builds so hopefully I didn't break anything.
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
2012-08-27
|
|
Packit Service |
a1973e |
|
|
Packit Service |
a1973e |
* 3b737198 src/papi.c src/papi_libpfm4_events.c src/papi_preset.c...: Hack
|
|
Packit Service |
a1973e |
around debugging macros. Under NO_VARARG_MACROS configs the debug printing
|
|
Packit Service |
a1973e |
guys become two expression statements. This is bad for code expecting eg
|
|
Packit Service |
a1973e |
SUBDBG(); to be one statement. --ie-- if ( foo ) SUBDBG("Danger Will
|
|
Packit Service |
a1973e |
Robinson"); ------ In order to keep the useful file and line number
|
|
Packit Service |
a1973e |
expansions with out variadic macro support, we split SUBDBG into two parts; A
|
|
Packit Service |
a1973e |
call to DEBUGLABEL() and friends and then a call to a function to capture the
|
|
Packit Service |
a1973e |
actual informative message. So if(foo) stmt(); becomes if (foo)
|
|
Packit Service |
a1973e |
print_the_debug_label(); print_your_message(...); And your message is always
|
|
Packit Service |
a1973e |
printed. See papi_debug.h for what actually happens. I'm not clever enough
|
|
Packit Service |
a1973e |
to work around this any other way, so I exaustivly put { }s around every case
|
|
Packit Service |
a1973e |
of the above I found. (I only searched on 'DBG' so its possible I missed
|
|
Packit Service |
a1973e |
some)
|