The code is tested to work with latest clang, GNU and Intel compiler. The implementation
is optimized for low overhead when no tool is attached shifting the cost to execution with
tool attached.
This patch does not implement OMPT for libomptarget.
Patch by Simon Convent and Joachim Protze
Differential Revision: https://reviews.llvm.org/D38185
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@317085 91177308-0d34-0410-b5e6-96231b3b80d8
While importing libomp into the FreeBSD base system we encountered
Clang warnings that "'register' storage class specifier is deprecated
and incompatible with C++1z [-Wdeprecated-register]".
Differential Revision: https://reviews.llvm.org/D35124
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@307441 91177308-0d34-0410-b5e6-96231b3b80d8
Changes are: replaced C-style casts with cons_cast and reinterpret_cast;
type of several counters changed to signed; type of parameters of 32-bit and
64-bit AND and OR intrinsics changes to unsigned; changed files formatted
using clang-format version 3.8.1.
Differential Revision: https://reviews.llvm.org/D34759
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@307020 91177308-0d34-0410-b5e6-96231b3b80d8
This patch contains the clang-format and cleanup of the entire code base. Some
of clang-formats changes made the code look worse in places. A best effort was
made to resolve the bulk of these problems, but many remain. Most of the
problems were mangling line-breaks and tabbing of comments.
Patch by Terry Wilmarth
Differential Revision: https://reviews.llvm.org/D32659
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@302929 91177308-0d34-0410-b5e6-96231b3b80d8
When the monitor thread is used, most threads in the team directly go to
sleep if the copy of bt_intervals/bt_set is not available in the cache,
and this happens at least once per thread in the wait function, making the
overall performance slightly better.
This change tries to mimic this behavior by using the bt_intervals cache,
which simply keeps the blocktime interval in terms of the platform-dependent
ticks or nanoseconds.
Patch by Hansang Bae
Differential Revision: https://reviews.llvm.org/D28906
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@293312 91177308-0d34-0410-b5e6-96231b3b80d8
Have developer timers use partitioning scheme which also required that some
redundant developer timers be removed in favor of the already existing normal
timers. Move per thread stats initialization to just after global thread id
assignment which is as early as possible. Also put all global stats
initialization code in __kmp_stats_init() and all global stats destruction code
in __kmp_stats_fini().
Differential Revision: https://reviews.llvm.org/D26361
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@286892 91177308-0d34-0410-b5e6-96231b3b80d8
This patch allows ThreadSanitizer (Tsan) to verify OpenMP programs.
It means that no false positive will be reported by Tsan when
verifying an OpenMP programs.
This patch introduces annotations within the OpenMP runtime module to
provide information about thread synchronization to the Tsan runtime.
In order to enable the Tsan support when building the runtime, you must
enable the TSAN_SUPPORT option with the following environment variable:
-DLIBOMP_TSAN_SUPPORT=TRUE
The annotations will be enabled in the main shared library
(same mechanism of OMPT).
Patch by Simone Atzeni and Joachim Protze!
Differential Revision: https://reviews.llvm.org/D13072
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@286115 91177308-0d34-0410-b5e6-96231b3b80d8
OpenMP 4.1 is now OpenMP 4.5. Any mention of 41 or 4.1 is replaced with
45 or 4.5. Also, if the CMake option LIBOMP_OMP_VERSION is 41, CMake warns that
41 is deprecated and to use 45 instead.
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@272687 91177308-0d34-0410-b5e6-96231b3b80d8
This change removes the current timers with ones that partition time properly.
The current timers are nested, so that if a new timer, B, starts when the
current timer, A, is already timing, A's time will include B's. To eliminate
this problem, the partitioned timers are designed to stop the current timer (A),
let the new timer run (B), and when the new timer is finished, restart the
previously running timer (A). With this partitioning of time, a threads' timers
all sum up to the OMP_worker_thread_life time and can now easily show the
percentage of time a thread is spending in different parts of the runtime or
user code.
There is also a new state variable associated with each thread which tells where
it is executing a task. This corresponds with the timers: OMP_task_*, e.g., if
time is spent in OMP_task_taskwait, then that thread executed tasks inside a
#pragma omp taskwait construct.
The changes are mostly changing the MACROs to use the new PARITIONED_* macros,
the new partitionedTimers class and its methods, and new state logic.
Differential Revision: http://reviews.llvm.org/D19229
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@268640 91177308-0d34-0410-b5e6-96231b3b80d8
ittnotify fix for barrier imbalance time in case tasks exist. In the current
implementation, task execution time is included into aggregated time on a
barrier. This fix calculates task execution time and corrects the arrive time
by subtracting the task execution time.
Since __kmp_invoke_task() can not only be called on a barrier, the field
th.th_bar_arrive_time is used to check if the function was called at the
barrier (th.th_bar_arrive_time != 0). So for this check, th_bar_arrive_time
is set to zero right after the value is used on the barrier.
Differential Revision: http://reviews.llvm.org/D19030
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@266332 91177308-0d34-0410-b5e6-96231b3b80d8
1) When the number of threads in a team increases, new threads need to have all
their barrier struct fields initialized. We were missing the parent_bar and
team fields.
2) For non-forkjoin barriers, we now do the __kmp_task_team_setup before the
gather. The setup now sets up the task_team that all the threads will switch
to after the barrier, but it needs to be done before other threads do the
switch.
3) Remove an unneeded assignment of tt_found_tasks in task team free function.
Differential Revision: http://reviews.llvm.org/D14456
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@252486 91177308-0d34-0410-b5e6-96231b3b80d8
This is a refactoring of the task_team code that more elegantly handles the two
task_team case. Two task_teams per team are kept in use for the lifetime of the
team. Thus no reference counting is needed.
Differential Revision: http://reviews.llvm.org/D13993
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@252082 91177308-0d34-0410-b5e6-96231b3b80d8
These changes improve the wait/release mechanism for threads spinning in
barriers that are handling tasks while spinnin by providing feedback to the
barriers about any task stealing that occurs.
Differential Revision: http://reviews.llvm.org/D13353
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@249711 91177308-0d34-0410-b5e6-96231b3b80d8
Prior to this change, OMPT had a status flag ompt_status, which could take
several values. This was due to an earlier OMPT design that had several levels
of enablement (ready, disabled, tracking state, tracking callbacks). The
current OMPT design has OMPT support either on or off.
This revision replaces ompt_status with a boolean flag ompt_enabled, which
simplifies the runtime logic for OMPT.
Patch by John Mellor-Crummey
Differential Revision: http://reviews.llvm.org/D12999
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@248189 91177308-0d34-0410-b5e6-96231b3b80d8
The fix is to make b_arrived flag 64 bit in both structures - kmp_balign_team_t
and kmp_balign_t. Otherwise when flag in kmp_balign_team_t wrapped over
UINT_MAX the library hangs.
Differential Revision: http://reviews.llvm.org/D12563
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@247320 91177308-0d34-0410-b5e6-96231b3b80d8
This change just removes the variables created solely for KMP_DEBUG_ASSERT statements
and puts the definition of the removed variables inside the KMP_DEBUG_ASSERT
statements.
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@246065 91177308-0d34-0410-b5e6-96231b3b80d8
This removes some statistics counters and timers which were not used,
adds new counters and timers for some language features that were not
monitored previously and separates the counters and timers into those
which are of interest for investigating user code and those which are
only of interest to the developer of the runtime itself.
The runtime developer statistics are now ony collected if the
additional #define KMP_DEVELOPER_STATS is set.
Additional user statistics which are now collected include:
* Count of nested parallelism (omp parallel inside a parallel region)
* Count of omp distribute occurrences
* Count of omp teams occurrences
* Counts of task related statistics (taskyield, task execution, task
cancellation, task steal)
* Values passed to omp_set_numtheads
* Time spent in omp single and omp master
None of this affects code compiled without stats gathering enabled,
which is the normal library build mode.
This also fixes the CMake build by linking to the standard c++ library
when building the stats library as it is a requirement. The normal library
does not have this requirement and its link phase is left alone.
Differential Revision: http://reviews.llvm.org/D11759
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@244677 91177308-0d34-0410-b5e6-96231b3b80d8
A while back, we made an initial change where dangerous C API functions were
replaced with macros that translated the dangerous API function calls to safer
function calls e.g., sprintf() replaced with KMP_SPRINTF() which translates to
sprintf_s() on Windows. Currently, the only operating system where this is
applicable is Windows. Unix-like systems are still using the dangerous API
e.g., KMP_SPRINTF() translates to sprintf(). Our own testing showed no
performance differences.
Differential Revision: http://reviews.llvm.org/D9918
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@241833 91177308-0d34-0410-b5e6-96231b3b80d8
These changes enable external debuggers to conveniently interface with
the LLVM OpenMP Library. Structures are added which describe the important
internal structures of the OpenMP Library e.g., teams, threads, etc.
This feature is turned on by default (CMake variable LIBOMP_USE_DEBUGGER)
and can be turned off with -DLIBOMP_USE_DEBUGGER=off.
Differential Revision: http://reviews.llvm.org/D10038
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@241832 91177308-0d34-0410-b5e6-96231b3b80d8
The OMPT status is never equal to ompt_status_track. ompt_status_track = 0x2
and ompt_status_track_callback = 0x6 just share a bit, so that we can check
for traceing and callbacks with the same status.
Patch by Tim Cramer
Differential Revision: http://reviews.llvm.org/D10863
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@241167 91177308-0d34-0410-b5e6-96231b3b80d8
Fix OMPT support for barriers so that state changes occur even if OMPT_TRACE turned off.
These state changes are needed by performance tools that use callbacks for either
ompt_event_wait_barrier_begin or ompt_event_wait_barrier_end. Change ifdef flag to OMPT_BLAME
for callbacks ompt_event_wait_barrier_begin or ompt_event_wait_barrier_end rather than
OMPT_TRACE -- they were misclassified. Without this patch, when the runtime is compiled with
LIBOMP_OMPT_SUPPORT=true, LIBOMP_OMPT_BLAME=true, and LIBOMP_OMPT_TRACE=false, and a callback
is registered for either ompt_event_wait_barrier_begin or ompt_event_wait_barrier_end, then an
assertion will trip. Fix the scoping of one OMPT_TRACE ifdef, which should not have surrounded
an update of an OMPT state. Add a missing initialization of an OMPT task id for an implicit task.
Patch by John Mellor-Crummey
Differential Revision: http://reviews.llvm.org/D10759
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@240970 91177308-0d34-0410-b5e6-96231b3b80d8
As an ongoing effort to sanitize the openmp code, these changes move
variables under already existing macro guards.
Patch by Jack Howarth
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@239331 91177308-0d34-0410-b5e6-96231b3b80d8
Some variables are convenient to keep around even if they aren't
really used in a release build. This is often seen in DEBUG guarded code where the variable
is only used in a DEBUG build.
Patch by Jack Howarth
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@239326 91177308-0d34-0410-b5e6-96231b3b80d8
understand that this is not friendly, and are working to change our
internal code-development to make it easier to make development
features available more frequently and in finer (more functional)
chunks. Unfortunately we haven't got that in place yet, and unpicking
this into multiple separate check-ins would be non-trivial, so please
bear with me on this one. We should be better in the future.
Apologies over, what do we have here?
GGC 4.9 compatibility
--------------------
* We have implemented the new entrypoints used by code compiled by GCC
4.9 to implement the same functionality in gcc 4.8. Therefore code
compiled with gcc 4.9 that used to work will continue to do so.
However, there are some other new entrypoints (associated with task
cancellation) which are not implemented. Therefore user code compiled
by gcc 4.9 that uses these new features will not link against the LLVM
runtime. (It remains unclear how to handle those entrypoints, since
the GCC interface has potentially unpleasant performance implications
for join barriers even when cancellation is not used)
--- new parallel entry points ---
new entry points that aren't OpenMP 4.0 related
These are implemented fully :-
GOMP_parallel_loop_dynamic()
GOMP_parallel_loop_guided()
GOMP_parallel_loop_runtime()
GOMP_parallel_loop_static()
GOMP_parallel_sections()
GOMP_parallel()
--- cancellation entry points ---
Currently, these only give a runtime error if OMP_CANCELLATION is true
because our plain barriers don't check for cancellation while waiting
GOMP_barrier_cancel()
GOMP_cancel()
GOMP_cancellation_point()
GOMP_loop_end_cancel()
GOMP_sections_end_cancel()
--- taskgroup entry points ---
These are implemented fully.
GOMP_taskgroup_start()
GOMP_taskgroup_end()
--- target entry points ---
These are empty (as they are in libgomp)
GOMP_target()
GOMP_target_data()
GOMP_target_end_data()
GOMP_target_update()
GOMP_teams()
Improvements in Barriers and Fork/Join
--------------------------------------
* Barrier and fork/join code is now in its own file (which makes it
easier to understand and modify).
* Wait/release code is now templated and in its own file; suspend/resume code is also templated
* There's a new, hierarchical, barrier, which exploits the
cache-hierarchy of the Intel(r) Xeon Phi(tm) coprocessor to improve
fork/join and barrier performance.
***BEWARE*** the new source files have *not* been added to the legacy
Cmake build system. If you want to use that fixes wil be required.
Statistics Collection Code
--------------------------
* New code has been added to collect application statistics (if this
is enabled at library compile time; by default it is not). The
statistics code itself is generally useful, the lightweight timing
code uses the X86 rdtsc instruction, so will require changes for other
architectures.
The intent of this code is not for users to tune their codes but
rather
1) For timing code-paths inside the runtime
2) For gathering general properties of OpenMP codes to focus attention
on which OpenMP features are most used.
Nested Hot Teams
----------------
* The runtime now maintains more state to reduce the overhead of
creating and destroying inner parallel teams. This improves the
performance of code that repeatedly uses nested parallelism with the
same resource allocation. Set the new KMP_HOT_TEAMS_MAX_LEVEL
envirable to a depth to enable this (and, of course, OMP_NESTED=true
to enable nested parallelism at all).
Improved Intel(r) VTune(Tm) Amplifier support
---------------------------------------------
* The runtime provides additional information to Vtune via the
itt_notify interface to allow it to display better OpenMP specific
analyses of load-imbalance.
Support for OpenMP Composite Statements
---------------------------------------
* Implement new entrypoints required by some of the OpenMP 4.1
composite statements.
Improved ifdefs
---------------
* More separation of concepts ("Does this platform do X?") from
platforms ("Are we compiling for platform Y?"), which should simplify
future porting.
ScaleMP* contribution
---------------------
Stack padding to improve the performance in their environment where
cross-node coherency is managed at the page level.
Redesign of wait and release code
---------------------------------
The code is simplified and performance improved.
Bug Fixes
---------
*Fixes for Windows multiple processor groups.
*Fix Fortran module build on Linux: offload attribute added.
*Fix entry names for distribute-parallel-loop construct to be consistent with the compiler codegen.
*Fix an inconsistent error message for KMP_PLACE_THREADS environment variable.
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@219214 91177308-0d34-0410-b5e6-96231b3b80d8
Joachim Protze