This file documents changes in recent PAPI releases in inverse chronological

order.

For details on installing PAPI on your machine, consult the INSTALL.txt file

in this directory.

===============================================================================

PAPI 5.6.0 RELEASE NOTES                                            19 Dec 2017

===============================================================================

PAPI 5.6.0 contains a major cleanup of the source code and the build

system to have consistent code structure, eliminate errors, and reduce

redundancies.  A number of validation tests have been added to PAPI to

verify the PAPI preset events.  Improvements and changes to multiple

PAPI components have been made, varying from supporting new events to

fixes in the component testing.

For specific and detailed information on changes made in this release,

see ChangeLogP560.txt for keywords of interest or go directly to the

PAPI git repository.

Major changes

* Validation tests: A substantial effort to add validation tests to

  PAPI to check and detect problems in the definition of PAPI preset

  events.

* Event testing: Thorough cleanup of code in the C and Fortran testing

  to add processor support, cleanup output and make the testing

  behavior consistent.

* CUDA component: Updated and rewritten to support CUPTI Metric API

  (combinations of basic events).  This component now supports NVLink

  information through the Metric API. Updated testing for the

  component.

* NVML component: Updated to support power management limits and

  improved event names. Minor other bug fixes.

* RAPL component: Added support for: Intel Atom models Goldmont /

  Gemini_Lake / Denverton, Skylake-X / Kabylake

* PAPI preset events: Many updates to the PAPI preset event mappings;

  Skylake X support, initial AMD fam17h, fix AMD fam16h, added more

  Power8 events, initial Power9 events.

Other changes

* Updating man and help pages for papi_avail and papi_native_avail.

* Powercap component: Added test for setting power caps via PAPI

  powercap component.

* Infiniband component: Bugfix for infiniband_umad component.

* Uncore component:  Updated to support recent processors.  

* Lmsensors component updated to support correct runtime linking,

  better events name, and a number of bug fixes.

* Updated and fixed timer support for multiple architectures.  

* All components: Cleanup and standardize testing behavior in the

  components.

* Build system: Much needed cleanup of configure and make scripts.

* Support for C++ was enhanced.

* Enabling optional support for reading events using perfevent-rdpmc

  on recent Linux kernels can speed up PAPI_read() by a factor of 5.

* Pthread testing limited to avoid excessive CPU consumption on highly

  parallel machines.

Acknowledgements: This release is the result of efforts from many

people, with special Thanks to Vince Weaver, Phil Mucci, Steve

Kauffman, William Cohen, Will Schmidt, and Stephane Eranian (for

libpfm4) from the internal PAPI team.

===============================================================================

PAPI 5.5.1 RELEASE NOTES                                            18 Nov 2016

===============================================================================

PAPI 5.5.1 is now available. This is a point release intended

primarily to add support for uncore performance monitoring events on

Intel Xeon Phi Knights Landing (KNL).  Other minor bugfixes have also

been made.

For specific and detailed information on changes made in this release,

see ChangeLogP551.txt for keywords of interest or go directly to the

PAPI git repository.

New Platforms:

* Added Knights Landing (KNL) uncore event support via libpfm4.

Bug Fixes:

* Fix some possible string termination problems.

* Cleanup lustre and mx components.

* Enable RAPL for Broadwell-EP.

===============================================================================

PAPI 5.5.0 RELEASE NOTES                                            14 Sep 2016

===============================================================================

PAPI 5.5 is now available. This release provide a new component that

provides read and write access to the information and controls exposed

via the Linux powercap interface.The PAPI powercap component supports

measuring and capping power usage on recent Intel architectures.[a][b]

We have added core support for Knights Landing (uncore support will be

released later) as well as power monitoring via the RAPL and powercap

components.

For specific and detailed information on changes made in this release,

see ChangeLogP550.txt for keywords of interest or go directly to the

PAPI git repo.

New Platforms:

* Added  Knights Landing (KNL) core events and preset events.

* Added Intel Broadwell/Skylake/Knights Landing RAPL support

* Updated PAPI preset event support for Intel Broadwell/Skylake

New Component: 

* Powercap component: PAPI now supports the Linux Power Capping

  Framework which exposes power capping devices and power measurement

  to user space via a sysfs virtual file system interface.

Enhancements:

* Add support for multiple flavors of POWER8 processors.

* Force all processors to check event schedulability by checking that

  PAPI can successfully read the counters.

* Support for Intel Broadwell-EP, Skylake, Goldmont, Haswell-EP

  inherited from libpfm4.

* Shared memory object (.so) naming is made more limited so that minor

  updates do not break ABI compatibility.

Bug Fixes:

* Improve testlib error messages if a component fails to initialize.

* Fix _papi_hwi_postfix_calc parsing and robustness.

* Clean build rules for CUDA sampling subcomponent.

* Correct IBM Power7 and Power8 computation of PAPI_L1_DCA.

* Eliminate the sole use of ftests_skip subroutine.

* Correct the event string names for tenth.c.  

* Have Fortran test support code report errors more clearly.

* Cleanup output from libmsr component.

* PAPI internal functions were marked as static to avoid exposing them

  externally.

* Multiple component were fixed to make internal functions static

  where possible, to avoid exposing the functions as externally

  accessible entry points.

* CUDA component configuration bug fixed.

===============================================================================

PAPI 5.4.3 RELEASE NOTES                                            26 Jan 2016

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP543.txt for keywords of interest or go directly to the PAPI git

repo.  

GENERAL NOTES

===============================================================================

New Implementations:

-------------------

    * libmsr component: Using LLNL's libmsr library to access Intel

      RAPL (Running Average Power Limit) library adds power capping

      abilities to PAPI.

    * CUDA PC sampling: A new standalone CUDA sampling tool

      (papi_cuda_sampling) has been added to the CUDA component

      (components/cuda/sampling/) and can be used as a preloader to

      perform PC sampling on Nvidia GPUs which support the CUPTI

      sampling interface (e.g. Maxwell).

    * ARM Cortex A53 support: Event definitions added.

Enhancements:

------------

    * Added Haswell-EP uncore support

    * Initial Broadwell, Skylake support

    * Added a general CUDA example (components/cuda/test) that uses

      LD_PRELOAD to attach to a running CUcontext.

    * Added "-check" flag to papi_avail and papi_native_avail to 

      test counter availability/validity.

Bug Fixes:

----------

    * Clean output from papi_avail tool when there are no user defined events.

    * Support PAPI_GRN_SYS granularity for perf component.

    * Bug fix for infiniband_umad component.

    * Bug fix for vmware component.

    * Bug fix for NVML component.

    * Fixed RAPL component so it reports unsupported inside a guest VM.

    * Cleanup ARM CPU detection.

    * Bug fix for PAPI_overflow issue for multiple eventsets.

    * Increased PERF_EVENT_MAX_MPX_COUNTERS to 192 from 128.

    * Fixed memory leak in papi_preset.c.

    * Free allocated memory in the stealtime component.

===============================================================================

PAPI 5.4.1 RELEASE NOTES                                            02 Mar 2015

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP541.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

The PAPI CUDA component is updated to support CUDA 6.5 with multiple GPUs.

New Platforms:

-------------

    * Updated support for Intel Haswell and Haswell-EP

    * Added ARM Cortex A7 

    * Added ARM 1176 cpu (original Raspberry Pi)

Enhancements:

------------

    * Enhance PAPI preset events to allow user defined events.

        * User defined events are set up via a user event definition file.

    * CUDA component is updated to support multiple devices and contexts.

        * Tested under and supports CUDA 6.5.

        * Note: Events for different CUDA context MUST be added from within the context.

    * New test demonstrating attaching an eventset to a single CPU rather than a thread.

    * Use the term "event qualifiers" instead of "event masks" to clarify understanding.

    * Added pkg-config support to PAPI.

Bug Fixes:

----------

    * Fixed lustre segfault bug.

    * Fixed compilation in the absence of a Fortran compiler.

    * Fixed bug in krental_pthreads ctest to join threads properly on exit.

    * Fixed bug in perf_events where event masks were not getting cleared properly.

    * Fixed memory leak bug in perf_events.

===============================================================================

PAPI 5.4.0 RELEASE NOTES                                            13 Nov 2014

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP540.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

Full support for CUDA 6.5 has been delayed and will be included in the next 

release.

New Platforms:

-------------

	* EMON power component for IBM Blue Gene/Q

    * Support for the Applied Micro X-Gene processor

	* Support for IBM POWER non-virtualized platform

    * RAPL support for Intel Haswell models (60,69,71)

Enhancements:

------------

    * Added list of supported PMU names (core/uncore components)  

    * Support for extended event masks (core/uncore components)

    * Extension of the RAPL energy measurements on Intel via msr-safe

    * Updated IBM POWER7, POWER8 presets

	* 'papi_native_avail --validate' supports events that require

	  multiple masks to be valid  

Bug Fixes:

----------

    * HW counter and event count added/fixed for BGPM components

	* Reduce cost of using PAPI_name_to_code

	* Non-null terminated strings fixed

	* Growing list of native events in core/uncore components fixed

    * Cleaned up Intel IvyBridge presets

	* Addressed Coverity reported issues

===============================================================================

PAPI 5.3.2 RELEASE NOTES                                            30 Jun 2014

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP532.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

An internal 5.3.1 is skipped, changes since 5.3 are detailed below.

New Platforms:

-------------

    * Intel Silvermont

    * ARM Qualcomm Krait

Enhancements:

------------

    * Rapl component support for Intel Haswell-EP

    * Add units to NVML component

    * Refine the definition of a Flop on the *-Bridge Intel chips. 

    * Updated Intel Haswell presets

Bug Fixes:

----------

    * FreeBSD build and component fixes

    * Uncore enumeration

    * Printf format specifiers standardized (use # for hex)

===============================================================================

PAPI 5.3.0 RELEASE NOTES                                            18 Nov 2013

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP530.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

New Platforms:

-------------

    * Intel Xeon Phi ( for offload code )

Enhancements:

------------

    * RAPL component better deals with counter wrap 

    * Floating support added for Intel IvyBridge

    * PAPI_L1_ICM event added for Intel Haswell

    * AMD Fam15h gets Core select umasks

    * CUDA component now sets the number of native events supported

    * Installed tests' code can now be built.

    * host-micpower utility

Bug Fixes:

----------

    * command_line utility event skipping bug

    * remove extranious -openmp flag from icc builds

    * Default to building all ctests, clean up much bit rot

===============================================================================

PAPI 5.2.0 RELEASE NOTES                                            06 Aug 2013

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP520.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

This release represents a major overhaul of several components. Support for

Intel Haswell and Power 8 has been added. Processor support code has been 

moved to the components directory.

New Platform:

-------------

	* Intel Haswell (initial support)

	* Power 8 (initial support)

New Components:

---------------

	* Host-side MIC power component

Enhancements:

------------

	* Component tests are now included with install-tests make target.

	* Components with external library dependencies load them at runtime 

		allowing better distribution (infiniband, cuda, vmware, nvml and

		host-side micpower)

	* Perf_events, perfctr[_ppc] and perfmon2[_ia64] have been moved under the

	 	components directory

	* (Intel) Uncore support has been split into its own component

	* Lustre component better handles large numbers of filesystems

===============================================================================

PAPI 5.1.1 RELEASE NOTES                                            21 May 2013

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP511.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

This is a bug fix release.  

New Platform:

-------------

	* Intel IvyBridge-EP

Bug Fixes:

----------

	* Many perf_event fixes

	* Cuda component fixes

	* IA64 and SPARC build fixes

Enhancements:

------------

	* Better logic in run_tests.sh script

	* ARM builds now use pthread_mutexes

	* BG/Q overflow enhancements

===============================================================================

PAPI 5.1.0 RELEASE NOTES                                            11 Jan 2013

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP510.txt for keywords of interest or go directly to the PAPI git

repo.

New Platform:

-------------

	* Intel Xeon Phi ( Knight's Corner or KNC or MIC )

Bug Fixes:

----------

	* Various build system fixes. 

	* NVML component fix.

	* Work around a sampling bug on Power Linux

Enhancements:

------------

	* ARM Cortex A15 support.

	* New API entry, PAPI_get_eventset_component

	* Add options to papi_command_line to print in hex and unsigned formats

New Components:

---------------

	* MIC Power component. 

===============================================================================

PAPI 5.0.1 RELEASE NOTES                                            20 Sep 2012

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP501.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

This in a bug fix release of PAPI. Including a major bug fix in the preset

code, we recommend that all users of PAPI 5.0 upgrade; see commit 866bd51c

for a detailed discussion.  

Bug Fixes:

----------

	* Debugging macros with out variadic macro support. 

	* Building PAPI with an external libpfm4 installation.

	* Fix a major bug in the preset code. 

Enhancements:

-------------

	* CUDA configure script better supports Kepler architecture.

	* rapl support for IvyBridge.

	* Libpfm4 updates for SandyBridge-EP counters.

===============================================================================

PAPI 5.0.0 RELEASE NOTES                                            23 Aug 2012

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP500.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

This is a major release of PAPI. Parts of both the internal component and 

external low-level interfaces have changed, this will break your 4.4 compliant 

components. Numerous bug fixes are also included in this release.  

New Platforms:

-------------

  * Intel IvyBridge

  * Intel Atom Cedarview

New / Improved Components:

---------------

  * nVidia Management library component - support for various system health

    and power measurements on supported nVidia gpus.

  * stealtime - When running in a VM, this provides information on how much 

    time was "stolen" by the hypervisor due to the VM being disabled.  

    This is currently only supported on KVM.

  * RAPL - a SandyBridge RAPL (Running Average Power Level) Component  

    providing for energy measurement at the package-level. 

  * VMware component for VMware pseudo-counters

  * appio - This application I/O component enables PAPI-C to determine

    I/O used by the application.

Bug Fixes:

----------

  * Numerous memory leaks, thread races, and compiler warnings corrected.

Enhancements:

-------------

  * Major overhaul of the component interface. 

  * Update perf_event.c rdpmc support  

  * Minor uncore fixes plus changes for rdpmc.

  * Add a PAPI_REF_CYC preset event, defined as UNHALTED_REFERENCE_CYCLES for

    all Intel platforms on which this native event is supported.

  * Component names are now standardized in a meaningful way. 

  * Multiplexing under perf_events has been improved. 

  * FreeBSD cleanup/updates 

  * appio component now intercepts recv()

  * Power7 definition of L1_DCA and LST_INS updated to a countable definition

  * Added BGPM's opcode and generic event functionality to PAPI for BG/Q

    (requires Q32 driver V1R1M2).

Open Issues:

-------------

  * SandyBridge PAPI_FP_* events only produce reasonable results when counted 

    by themselves.

  * Ivy Bridge does not support floating point events.

Experimental:

-------------

Known Bugs:

-----------

  * Software multiplexing is known to have a memory leak.

  * The byte-profile test is known to fail on Power7/AIX

Deprecated:

---------------------

  * Java PAPI wrappers

  * Windows

===============================================================================

PAPI 4.4.0 RELEASE NOTES                                            17 Apr 2012

===============================================================================

For specific and detailed information on changes made in this release, grep

ChangeLogP440.txt for keywords of interest or go directly to the PAPI git

repo.

GENERAL NOTES

===============================================================================

This is a major release of PAPI-C. Support for IBM Blue Gene/Q has been added.

Multiple bug fixes are also included in this release.  

This is also the first release of papi made from the git repository; 

git clone http://icl.cs.utk.edu/git/papi.git 

Visit the PAPI Reference pages for more information at:

http://icl.cs.utk.edu/projects/papi/wiki/Main_Page

And visit the PAPI website for the latest updates:

http://icl.cs.utk.edu/papi/

RECENT CHANGES IN PAPI 4.4.0

===============================================================================

New Platforms:

-------------

  * src/Rules.bgpm... Added PAPI support for Blue Gene/Q.

Bug Fixes:

----------

  * Fix buffer overrun in lmsensors component  

  * libpfm4: Update to current git libpfm4 snapshot

  * Fix broken Pentium 4 Prescott support we were missing the netbusrt_p 

	declaration in papi_events.csv

  * Fix various locking issues in the threaded code. 

  * Fix multiplexing of large eventsets on perf_events systems.

	This presented when using more than 31 multiplexed events on perf_event  

Enhancements:

-------------

  * Update the release machinery for git.  

===============================================================================

PAPI 4.2.1 RELEASE NOTES                                            13 Feb 2012

===============================================================================

For specific and detailed information on changes made in this release, grep

the ChangeLogP421.txt file for keywords of interest or go directly to the PAPI

cvs tree.

GENERAL NOTES

===============================================================================

This is a minor release of PAPI-C. It does not break binary or semantic 

compatibility with previous versions.

Visit the PAPI Reference pages for more information at:

http://icl.cs.utk.edu/projects/papi/wiki/Main_Page

And visit the PAPI website for the latest updates:

http://icl.cs.utk.edu/papi/

RECENT CHANGES IN PAPI 4.2.1

===============================================================================

Bug Fixes:

----------

	* solaris substrate set_domain call was added.

	* multiplexing math errors were fixed in perf_events.c

	* more multiplexing read path errors were identified and fixed

	* src/linux-timer.c: Fix compilation warning if you specify

	  --with-walltime=gettimeofday

	* src/linux-timer.c: Fix the build on Linux systems using mmtimer

	* src/linux-common.c: Update the linux MHz detection code to use

	  bogoMIPS when there is no MHz field available in /proc/cpuinfo.

	* src/: configure, configure.in: Fix a typo in the perfctr section;

	  it was causing a machine to default to perfctr when it had no

	  performance interface.  ( a centos vm image with a 2.6.18 kernel)

	  Also checks that we actually have perfctr if we specify

	  --with-perfctr.

	* Fix SMP ARM issues reported by Harald Servat.

	  Also, adds proper header dependency checking in the Rules files.

	* src/ctests/api.c: Make the api test actually test PAPI_flops() as

	  it claims to do, rather than PAPI_flips().

	* src/papi_events.csv: Update the coreduo (not core2) events.  Most

	  notably the FP events were wrong.

	* src/papi_events.csv: Modify Intel Sandybridge PAPI_FP_OPS and

	  PAPI_FP_INS events to not count x87 fp instructions.

	  The problem is that the current predefines were made by adding 5

	  events.  With the NMI watchdog stealing an event and/or

	  hyperthreading reducing the number of available counters by half,

	  we just couldn't fit.

	  This now raises the potential for people using x87-compiled

	  floating point on Sandybridge and getting 0 FP_OPS.  This is only

	  likely if running a 32-bit kernel and *not* compiling your code

	  with -msse.

	  A long-term solution might be trying to find a better set of FP

	  predefines for sandybridge.

	* src/components/lmsensors/: Rules.lmsensors, configure.in: Fixed

	  configure error message and rules link error for shared object

	  linking. Thanks Will Cohen.

	* src/components/lmsensors/linux-lmsensors.h: Added missing string

	  header

	* src/components/net/tests/: net_values_by_code.c,

	  net_values_by_name.c: Apply patch suggested by Will Cohen to

	  check for system return values.

	* src/Makefile.inc: Patch to cleanup dependencies, allowing for

	  parallel makes.  Patch due to Will Cohen from redhat

	* src/: papi_internal.c, threads.c: Fix two race

	  conditions that are probably the cause of the pthrtough

	  double-free error.

	  When freeing a thread, we remove and free all eventsets belonging

	  to that thread.  This could race with the thread itself removing

	  the evenset, causing some ESI fields to be freed twice.

	  The problem was found by using the Valgrind 3.8 Helgrind tool

	    valgrind --tool=helgrind --free-is-write=yes ctests/pthrtough

	  In order for Helgrind to work, I had to temporarily modify PAPI

	  to use POSIX pthread mutexes for locking.

Enhancements:

-------------

	* general doxygen cleanups

	* cleanup output of overflow_allcounters for clarity in debugging

	* updates to most recent (as of Feb 1) libpfm4

	* remove now-opaque event codes from papi_native_avail

	  and papi_xml_event_info

	* src/: papi_internal.c Update the component initialization code 

	  so that it can handle a PAPI ERROR return gracefully.  Previously 

	  there was no way to indicate initialization failure besides just 

	  setting num_native_events to 0.

New Platforms:

-------------

 	* src/libpfm4/lib/: pfmlib_amd64_fam11h.c, events/amd64_events_fam11h.h

	  Support for AMD Family 11.

	* src/libpfm4/lib/: pfmlib_amd64_fam12h.c, events/amd64_events_fam12h.h

	  Support for AMD Family 12.

Deprecated Platforms:

---------------------

	* remove obsolete ACPI component

New / Improved Components:

---------------

	* PAPI CUDA component updated for CUDA / CUPTI 4.1.

		* SetCudaDevice() now works with the latest CUDA 4.1 version.

		* Auto-detection of CUDA version for backward compatibility.

		* PAPI_read() now accumulates event values. This fixes a bug

		in earlier versions.

	* extensive updates and cleanups to the example and coretemp components.

	* significant updates of lustre, and mx components

	* The linux net component underwent extensive updates and cleanups.

  	  In particular, it nows dynamically detects the network

	  interface names [1] and export 16 counters for each interface

  	  (see also src/components/net/{CHANGES,README}).

Open Issues:

-------------

	* multiplex1.c was rewritten to expose a multiplexing bug in the perf_events

	kernel (3.0.3) for MIPS

	* src/components/lmsensors/: Latest versions of lmsensors are incompatible

	  with current lmsensors component. Interface needs to be updated for forward

	  compatibility.

	* There's a problem with broken overflow on POWER6 linux systems.

	  We suspect a kernel problem, but don't know exactly which version(s)

	  We're running a 2.6.36 kernel where the problem has been identified.

	  It may be fixed in newer versions.

Experimental:

-------------

	* a new vmware component has been added to report a variety of soft events

	  when running as a guest in a VMWare environment

===============================================================================

PAPI 4.2.0 RELEASE NOTES                                            26 Oct 2011

===============================================================================

For specific and detailed information on changes made in this release, grep

the ChangeLogP420.txt file for keywords of interest or go directly to the PAPI

cvs tree.

GENERAL NOTES

===============================================================================

This is a major release of PAPI-C. It add a significant new feature in 

user-defined events. It also marks a shift from external (and out-dated) 

man pages to doxygen generated man pages. These pages can be found online at:

http://icl.cs.utk.edu/papi/docs/. They are also installable with "make install", 

and you can build your own versions using doxygen.

Visit the PAPI Reference pages for more information at:

http://icl.cs.utk.edu/projects/papi/wiki/Main_Page

And visit the PAPI website for the latest updates:

http://icl.cs.utk.edu/papi/

RECENT CHANGES IN PAPI 4.2.0

===============================================================================

Bug Fixes:

----------

	* Bug in CUDA v4.0 fixed. It caused a threaded application to hang when 

	  parent called cuInit() before fork() and child called also cuInit().

	  All fork ctests pass now if papi is configured with cuda component. 

	* If papi is configured with cuda component and running a threaded 

	  application, we need to make sure that a thread doesn't free the same 

	  memory location(s) more than once. Now all pthread ctests pass with cuda.

	* ctests/thrspecific works now with the CUDA component

	* Added CudaRemoveEvent functionality (broken in earlier CUDA RC versions). 

	* ctests/all_native_events works now for the default CUDA device.

	* Add locking to papi_pfm4_events so that adding/looking up event names 

	  doesn't have a race condition when multiple threads are doing it at once.

	* Fixed a series of problems with Itanium builds.

	* Set FD_CLOEXEC on the overflow signal handler fd. Otherwise if we exec()

	  with overflow enabled, the exec'd process will quickly die due to lack 

	  of signal handler. This patch is needed due to a change in behavior in 

	  Linux 3.0. Mark Krentel first noticed this problem.

	* Recent Ubuntu versions use the ld flag --as-needed by default, which

	  breaks the PAPI configure step for the libdl check, as the

	  --as-needed flag enforces the rule that libraries must come after the 

	  object files on the command line, not before. The fix for this is to put 

	  the libdl check it in LIBS instead of in LDFLAGS.

	* Removed an fopen() without an fclose() on /proc/cpuinfo in papi.c. 

	  This was being done to set the event masks properly for itanium and p4.

	  Since the platform code sets CPU vendor and family for us we don't

	  really have to open cpuinfo.  This fix may also work on non-Linux 

	  systems too.

	* Update papi.h to properly detect if being built with a C99 compiler.

Enhancements:

-------------

	* Default support for libpfm4

	* ./configure --with-libpfm3 to support legacy libpfm3 builds

	* PERF_COUNT_SW software events are available under perf_events with 

	  libpfm4

	* Nehalem/Westmere/SandyBridge Offcore event support is ready, 

	  but support is not yet available in the Linux kernel.

	* Add new utility to display PAPI error codes and description strings.

	* Add API to access error descriptions: PAPI_descr_error( int error_code).

	* Add support for handling multiattach properly.

	* Cleanups to avoid gcc-4.6 warnings.

	* Added ability to add tests to components. All component tests are

	  compiled with PAPI when typing 'make'and cleaned up with 'make clean' 

	  or 'make clobber'. Also added tests to the example and cuda components.

	* CUDA component is now thread-safe. Multiple CPU

	  threads can access the same CUDA context. Note, it's possible to

	  create a different CUDA context for each thread, but then we are

	  likely running into a limitation that only one context can be

	  profiled at a time.

	* LOTS of code cleanup thanks to Will Cohen of RedHat.

	* Refactored test code so no-cpu-counters can build with components

	* Build all utilities with no-cpu-counters

	* Modify run_tests.sh so that you can set the VALGRIND command 

	  externally via environment variable without having to edit 

	  run_tests.sh itself. Also adds Date and cpuinfo information to the 

	  beginning of run_tests.sh results.  This can help when run_tests.sh 

	  output is passed around when debugging a problem.

	* Parallel make now works.

New Platforms:

-------------

	* AMD Family 14h Bobcat (libpfm4 only)

	* Intel SandyBridge (libpfm4 only)

	* ARM Cortex-A8 and Cortex-A9 (libpfm4 only)

Deprecated Platforms:

---------------------

	* although still technically supported, we are no longer actively testing

	  platforms based on the perfmon and perfctr patches. All linux kernels

	  > 2.6.32 provide internal support for perf_events.

New / Improved Components:

---------------

	* Add a number of 'native' events to the component info structure in 

	  example component.

	* Introduce a papi_component_avail utility; lists the components we were

	  built with, optionally with native/preset counts and version number.

Open Issues:

-------------

	* On newer Linux kernels (2.6.34+) the nmi_watchdog counter can	steal one

	  of the counters, reducing by one the total available.

	  There's a bug in Linux where if you try to use the full number of

	  counters on such a system with a group leader, the sys_perf_open()

	  call will succeed only to fail at read time.

	  (instead of the proper error code at open time).

	  I do wish there were a way to notify the user more visibly,

	  because losing a counter (when you might only have 4 total to

	  begin with) is a big deal, and most Linux vendors are starting to

	  ship kernels with the nmi_watchdog enabled.

Experimental:

-------------

	* Preliminary support for MIPS 74K.

===============================================================================

PAPI 4.1.4 RELEASE NOTES                                            29 Aug 2011

===============================================================================

For specific and detailed information on changes made in this release, grep

the ChangeLogP414.txt file for keywords of interest or go directly to the PAPI

cvs tree.

GENERAL NOTES

===============================================================================

This is an internal release of PAPI-C targetted specifically for a Cray tools

release. It precedes a more general 4.2.0 release and incorporates changes and

updates since PAPI 4.1.3.

Detailed changes will be documented in the 4.2.0 release. Meanwhile the list

below highlights the most significant changes since 4.1.3.

	* Intel SandyBridge is now supported

	* libpfm4 support has been updated

	* internal doxygen documentation has been added for the entire API

	* the man pages have been replaced with doxygen generated man pages

	* CUDA component support has been improved

	* an infrastructure for testing components only has been implemented

	* various bugs have been addressed

If you find issues with the 4.1.4 release, please bring them to our attention

ASAP, so they can be addressed prior to the general 4.2.0 release.

Visit the PAPI Reference pages for more information at:

http://icl.cs.utk.edu/projects/papi/wiki/Main_Page

And visit the PAPI website for the latest updates:

http://icl.cs.utk.edu/papi/

===============================================================================

PAPI 4.1.3 RELEASE NOTES                                            06 May 2011

===============================================================================

For specific and detailed information on changes made in this release, grep

the ChangeLogP413.txt file for keywords of interest or go directly to the PAPI

cvs tree.

GENERAL NOTES

===============================================================================

This is a minor release of PAPI-C. It addresses a number of bugs and other

issues that have surfaced since the 4.1.2 release.

Visit the PAPI Reference pages for more information at:

http://icl.cs.utk.edu/projects/papi/wiki/Main_Page

And visit the PAPI website for the latest updates:

http://icl.cs.utk.edu/papi/

CHANGES IN PAPI 4.1.3 SINCE PAPI 4.1.2

===============================================================================

Bug Fixes:

----------

	* Fixed a linux-timer.c compile error that only shows up on PPC.

	* Fixed ctests/all_native_events.c:

	  It failed when PAPI was built with several components because the 

	  eventset failed to add events that were not from the first component.

	* Redefined PAPI_FP_OPS for Nehalem; Now counts properly for 32-bit code.

	* Uncovered and resolved bugs in attaching to fork/exec'd code.

	* Reworked eventset cleanup code to avoid an error situation in perf_events

	  where events were being removed from a terminated attached process.

	* Fixed a configure bug preventing non-default bitmode builds of perf_event

	  versions of PAPI.

Enhancements:

-------------

	* consolidated a bunch of duplicated linux code into "linux-xxx.c" files.

	* Split WIN32 specific code out from linux common code.

	* Renamed various perfctr functions to be _perfctr_ rather than _linux_.

	* Added function pointer destroy_eventset to the PAPI vector table.

	  Needed for the CUDA Component.

	* PAPI_assign_eventset_component now refuses to reassign components.

	* Implemented inherit feature for perf_events. Thanks to Gary Mohr.

	* Added a case to utils/cost.c to test for processing derived events.

	* Added utils/multiplex_cost.c.

	* Added --with-assumed-kernel to configure

New Platforms:

-------------

	* POWER7 / AIX support is now available (see Known Bugs below)

	* Intel Westmere for perfctr.

	* AMD Family 15h (Interlagos) and 10h RevE processors.

Deprecated Platforms:

---------------------

New Components:

---------------

	* NVidia CUDA: still in pre-release until NVidia releases official CUDA4.

Open Issues:

-------------

	* Currently using PAPI_attach() to attach to multiple processes at the same