Commit Graph

487 Commits

Author SHA1 Message Date
Andrey Churbanov 76d4285460 Fix for the __kmpc_global_num_threads function to return the value of the __kmp_all_nth global var.
Patch by Yonghong Yan.

Differential Revision: https://reviews.llvm.org/D27975

llvm-svn: 290272
2016-12-21 21:20:20 +00:00
Oren Ben Simhon c11addb506 Reverting last change.
llvm-svn: 290245
2016-12-21 09:04:08 +00:00
Oren Ben Simhon 016f2af3c7 [X86] Vectorcall Calling Convention - Adding CodeGen Complete Support
Fixing build issues.

llvm-svn: 290242
2016-12-21 08:58:19 +00:00
Jonathan Peyton de4749b748 Follow up to r289732: Update comments in source files to reference .cpp files
Patch by Hansang Bae

llvm-svn: 289739
2016-12-14 23:01:24 +00:00
Jonathan Peyton 7cc577a4ef Change source files from .c to .cpp
Patch by Hansang Bae

Differential Revision: https://reviews.llvm.org/D26688

llvm-svn: 289732
2016-12-14 22:39:11 +00:00
Andrey Churbanov 5dee8c43da Cleanup: debug print fixed and moved inside critical section.
Patch by Victor Campos.

Differential Revision: https://reviews.llvm.org/D27647

llvm-svn: 289640
2016-12-14 08:29:00 +00:00
Sylvestre Ledru cd9d374337 Support of mips & mips64 for openmprtl
Summary:
Implemented by Dejan Latinovic
See https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=790735 for more more information

Reviewers: AndreyChurbanov, jlpeyton

Subscribers: openmp-commits, mgorny

Differential Revision: https://reviews.llvm.org/D26576

llvm-svn: 289032
2016-12-08 09:22:24 +00:00
Andrey Churbanov e0a2c3e99a fixed type in Windows-specific code
llvm-svn: 288368
2016-12-01 16:08:52 +00:00
Jonathan Peyton a88e8358af Fixed typo in kmp_process_deps trace output
Patch by Victor Campos

Differential Revision: https://reviews.llvm.org/D27172

llvm-svn: 288056
2016-11-28 20:10:32 +00:00
Andrey Churbanov bcadbd6302 Cleanup: memory leaks on warnings printing fixed; some memory freeing cleaned; poor indents and one typo fixed.
Patch by Victor Campos.

Differential Revision: https://reviews.llvm.org/D26786

llvm-svn: 288054
2016-11-28 19:23:09 +00:00
Jonathan Peyton 96fe1aa380 Set task->td_dephash to NULL after free
llvm-svn: 287552
2016-11-21 16:24:59 +00:00
Jonathan Peyton 7ca7ef0478 Fix for D25504 - segfault because of double free()-ing in shutdown code.
Paul Osmialowski pointed out a double free bug in shutdown code.  This patch
Moves the freeing of the implicit task to above the freeing of all fast memory
to prevent the double-free issue.

Differential Revision: https://reviews.llvm.org/D26860

llvm-svn: 287551
2016-11-21 16:18:57 +00:00
Jonathan Peyton 5375fe820c Update stats-gathering code
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

llvm-svn: 286892
2016-11-14 21:13:44 +00:00
Jonathan Peyton 1cdd87adfd Introduce dynamic affinity dispatch capabilities
This set of changes enables the affinity interface (Either the preexisting
native operating system or HWLOC) to be dynamically set at runtime
initialization. The point of this change is that we were seeing performance
degradations when using HWLOC. This allows the user to use the old affinity
mechanisms which on large machines (>64 cores) makes a large difference in
initialization time.

These changes mostly move affinity code under a small class hierarchy:

KMPAffinity
  class Mask {}
KMPNativeAffinity : public KMPAffinity
  class Mask : public KMPAffinity::Mask
KMPHwlocAffinity
  class Mask : public KMPAffinity::Mask

Since all interface functions (for both affinity and the mask implementation)
are virtual, the implementation can be chosen at runtime initialization.

Differential Revision: https://reviews.llvm.org/D26356

llvm-svn: 286890
2016-11-14 21:08:35 +00:00
Andrey Churbanov 1fbb482928 Added check for malloc return.
Patch by Victor Campos.

Differential Revision: https://reviews.llvm.org/D26318

llvm-svn: 286441
2016-11-10 09:08:03 +00:00
Jonas Hahnfeld 50fed0475f [OpenMP] Enable ThreadSanitizer to check OpenMP programs
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

llvm-svn: 286115
2016-11-07 15:58:36 +00:00
Andrey Churbanov 4d49312cad fixed typo in comment
llvm-svn: 285947
2016-11-03 17:48:46 +00:00
Andrey Churbanov 753fa0468c Change task stealing to always get task from head of victim's deque.
Differential Revision: https://reviews.llvm.org/D26187

llvm-svn: 285833
2016-11-02 16:45:25 +00:00
Andrey Churbanov 51107e0abc Fixed problem introduced by part of https://reviews.llvm.org/D21196.
Check Task Scheduling Constraint (TSC) on stealing of untied task.
This is needed because the untied task can produce tied children
those can break TSC if untied is not a descendant of current task.
This can cause live lock on complex tyasking tests
(e.g. kastors/strassen-task-dep).

Differential Revision: https://reviews.llvm.org/D26182

llvm-svn: 285703
2016-11-01 16:19:04 +00:00
Andrey Churbanov dd313b0673 Add more conditions to check whether task waiting is necessary in kmp_omp_taskwait.
Differential Revision: https://reviews.llvm.org/D26058

Patch by Victor Campos

llvm-svn: 285678
2016-11-01 08:33:36 +00:00
Andrey Churbanov df0d75edf6 Fixed a memory leak related to task dependencies.
Differential Revision: http://reviews.llvm.org/D25504

Patch by Alex Duran.

llvm-svn: 285283
2016-10-27 11:43:07 +00:00
Jonathan Peyton 3c4050d698 Fixing typos in __kmp_release_deps trace outputs
Patch by Victor Campos

Differential Revision: https://reviews.llvm.org/D25972

llvm-svn: 285244
2016-10-26 21:46:43 +00:00
Jonathan Peyton 762bc46224 Use getpagesize() instead of PAGE_SIZE macro when KMP_OS_LINUX is true
Patch by Victor Campos

Differential Revision: https://reviews.llvm.org/D26001

llvm-svn: 285243
2016-10-26 21:42:48 +00:00
Andrey Churbanov 2e68768d1e Fixed memory leak mistakenly introduced by https://reviews.llvm.org/D23115
Differential Revision: http://reviews.llvm.org/D25510

llvm-svn: 284747
2016-10-20 17:14:17 +00:00
Samuel Antao 335151914a [OpenMP] Fix issue with directives used in a macro.
Summary:
If directives are used in a macro, clang complains with:
```
src/projects/openmp/runtime/src/kmp_runtime.c:7486:2: error: embedding a directive within macro arguments has undefined behavior [-Werror,-Wembedded-directive]
#if KMP_USE_MONITOR
```

This patch fixes two occurrences of the issue in `kmp_runtime.cpp`.

Reviewers: tlwilmar, jlpeyton, AndreyChurbanov, Hahnfeld

Subscribers: Hahnfeld, openmp-commits

Differential Revision: https://reviews.llvm.org/D25823

llvm-svn: 284728
2016-10-20 13:20:17 +00:00
Jonathan Peyton 0ac7b75f7b Fix OpenMP 4.0 library build
Patch by Andrey Churbanov

Differential Revision: https://reviews.llvm.org/D25505

llvm-svn: 284499
2016-10-18 17:39:06 +00:00
Michal Gorny efc536ee9d Fix a compile error on musl-libc due to strerror_r() prototype
Function strerror_r() has different signatures in different
implementations of libc: glibc's version returns a char*, while BSDs
and musl return a int. libomp unconditionally assumes glibc on Linux
and thus fails to compile against musl-libc. This patch addresses this
issue.

Differential Revision: https://reviews.llvm.org/D25071

llvm-svn: 284492
2016-10-18 16:38:44 +00:00
Jonathan Peyton 55466e9106 Mixed type atomic routines added for capture and update/capture reverse.
New mixed type atomic routines added for regular capture operations as well as
reverse update/capture operations.  LHS - all integer and float types (no
complex so far), RHS - float16.

Patch by Olga Malysheva

Differential Revision: https://reviews.llvm.org/D25275

llvm-svn: 284489
2016-10-18 16:20:55 +00:00
Jonathan Peyton e1c7c13c3d Code cleanup for the runtime without monitor thread
This change removes/disables unnecessary code when monitor thread is not used.

Patch by Hansang Bae

Differential Revision: https://reviews.llvm.org/D25102

llvm-svn: 283577
2016-10-07 18:12:19 +00:00
Jonathan Peyton a1234cf280 Enable omp_get_schedule() to return static steal type.
As the code is now, calling omp_get_schedule() when OMP_SCHEDULE=static_steal
will cause an assert.

llvm-svn: 283576
2016-10-07 18:01:35 +00:00
Paul Osmialowski 7a9c29e4b8 [cmake] Fix for a bug https://llvm.org/bugs/show_bug.cgi?id=30489 "Cannot build with -DLIBOMP_FORTRAN_MODULES=True"
Differential Revision: https://reviews.llvm.org/D24959

llvm-svn: 282965
2016-09-30 22:05:45 +00:00
Jonathan Peyton 66e212ce2b Insert missing checks for KMP_AFFINITY_CAPABLE() in affinity API.
If affinity is not capable, then these API functions will perform the stubs
version.

llvm-svn: 282947
2016-09-30 20:56:44 +00:00
Michal Gorny 3ccf825e22 [test] Support 'lit' executable name
Support finding lit as plain 'lit', which is the name used by setup.py
in LLVM's utils/lit.

Differential Revision: https://reviews.llvm.org/D25072

llvm-svn: 282876
2016-09-30 16:56:16 +00:00
Jonathan Peyton 74f3ffce24 Fix incorrect OpenMP version in Fortran module.
Add check for "45" version to use "201511" string for OpenMP 4.5,
otherwise "200505" is used in Fortran module. Also, fix kmp_openmp_version
variable (used for the debugger, e.g.) and kmp_version_omp_api that is used
in KMP_VERSION=1 output.

Patch by Olga Malysheva

Differential Revision: https://reviews.llvm.org/D24761

llvm-svn: 282868
2016-09-30 15:50:14 +00:00
Jonathan Peyton be31337e9d Mixed type atomic routines for unsigned integers.
New routines should be used for atomics like "<int>OP=<float>" when <int> is
unsigned. Using functions __kmpc_atomic_fixed<bits>_<op>_fp) produces incorrect
results

Differential Revision: https://reviews.llvm.org/D24756

llvm-svn: 282509
2016-09-27 17:38:48 +00:00
Jonathan Peyton b66d1aab25 Disable monitor thread creation by default.
This change set disables creation of the monitor thread by default.  The global
counter maintained by the monitor thread was replaced by logic that uses system
time directly, and cyclic yielding on Linux target was also removed since there
was no clear benefit of using it. Turning on KMP_USE_MONITOR variable (=1)
enables creation of monitor thread again if it is really necessary for some
reasons.

Differential Revision: https://reviews.llvm.org/D24739

llvm-svn: 282507
2016-09-27 17:11:17 +00:00
Michal Gorny cd2bfb1e7c Fix respecting LIBOMP_LLVM_LIT_EXECUTABLE as full path
Fix lit search to correctly respect LIBOMP_LLVM_LIT_EXECUTABLE as full
program path.

The variable passed to find_program() is created by CMake as a cache
variable, and therefore can be directly overriden by the user. Since
this was the design of LIBOMP_LLVM_LIT_EXECUTABLE (as can be deduced
from the error messages) and there is no other use of LIT_EXECUTABLE,
remove the redundant variable and pass LIBOMP_LLVM_LIT_EXECUTABLE
directly to find_program().

Furthermore, the previous code did not work since the HINTS argument
specifies more search directories rather than expected full path.
Quoting the CMake documentation:

> 3. Search the paths specified by the HINTS option. These should be
> paths computed by system introspection, such as a hint provided by
> the location of another item already found. Hard-coded guesses should
> be specified with the PATHS option.

Differential Revision: https://reviews.llvm.org/D24710

llvm-svn: 281887
2016-09-19 06:55:56 +00:00
Michal Gorny 23132ebb0e [cmake] Make libgomp & libiomp5 alias install optional
Introduce a new LIBOMP_INSTALL_VARIABLES cache variable that can be used
to disable creating libgomp and libiomp5 aliases on 'make install'.
Those aliases are undesired e.g. on Gentoo systems where libomp is used
purely by clang.

Differential Revision: https://reviews.llvm.org/D24563

llvm-svn: 281512
2016-09-14 17:46:27 +00:00
Jonas Hahnfeld 848d690697 [OMPT] fix task frame information for gomp interface
Previous differencials D23305-D23310 changed task frame information management only for the kmp interface, but not for the whole gomp interface. This broke some testcases when building with gcc.
This patch fixes the broken task frame information for the gomp interface.

Patch by Joachim Protze!

Differential Revision: https://reviews.llvm.org/D24502

llvm-svn: 281468
2016-09-14 13:59:39 +00:00
Jonas Hahnfeld dd9a05d5d8 [OMPT] save exit address to lwt if available
In case, the current team is a serialized team (lwt), the frame information should be written to this data structure.
Before, nested serialized teams would overwrite the same task information.

Patch by Joachim Protze!

Differential Revision: https://reviews.llvm.org/D23310

llvm-svn: 281467
2016-09-14 13:59:31 +00:00
Jonas Hahnfeld 28ea24bba7 [OMPT] fix __ompt_get_teaminfo to consult lwt entries of parent teams
The comment already states, that this function should work similarly as __ompt_get_taskinfo.

The function only looked for lwt entries of the current team, but not when unrolling the parents. This fix aligns the implementation to __ompt_get_taskinfo.

The new test case creates a single theaded team (->lwt) and then a nested active team.
Before the innermost print_id(1) would deliver a different team then the outer print_id(0).

Patch by Joachim Protze!

Differential Revision: https://reviews.llvm.org/D23309

llvm-svn: 281466
2016-09-14 13:59:24 +00:00
Jonas Hahnfeld 8a27064e05 [OMPT] Reset task exit frame when execution is finished
The exit address is set when execution of a task is started and should be reset as soon as the execution is finished.
Especially for the asm implementation of __kmp_invoke_microtask, resetting in this call would be painfull, so reset just after the invokation.

The testcase shows the effect of this patch:
Before, the implicit barriers at the end of an implicit task would see an exit address for the implicit task.

This barrier is a task scheduling point. Thus, any explicit task scheduled there would see an exit, but no reenter address for the implicit task.

Patch by Joachim Protze!

Differential Revision: https://reviews.llvm.org/D23307

llvm-svn: 281465
2016-09-14 13:59:19 +00:00
Jonas Hahnfeld fd0614d830 [OMPT] Align implementation of reenter frame address to latest (frozen) version of OMPT spec
The latest OMPT spec changed the semantic of a tasks reenter frame to be the application frame, that will be entered, when the runtime frame drops.
Before it was the last frame in the runtime. This doesn't work for some gcc execution pathes or even clang generated code for :
Since there is no runtime frame between the executed task and the encountering task.

The test case compares exit and reenter addresses against addresses captured in application code

Patch by Joachim Protze!

Differential Revision: https://reviews.llvm.org/D23305

llvm-svn: 281464
2016-09-14 13:59:13 +00:00
Jonas Hahnfeld 464cdca9d3 [OMPT] extend ompt tests by checks for frame pointers
OMPT tests can check for right frame information of tasks:
 * parent_task_frame was directly printed as a pointer, but actually points to a struct ompt_frame {void*, void*}
 * NULL is printed in the beginning of execution and loaded to FileChecker variable [[NULL]]
 * implicit tasks now also print their frame information
 * macro to print frame address from application
 * print task info for barrier begin

Patch by Joachim Protze!

Differential Revision: https://reviews.llvm.org/D23304

llvm-svn: 281463
2016-09-14 13:59:05 +00:00
Jonathan Peyton 7c465a5f41 Fix bitmask upper bounds check
Rather than checking KMP_CPU_SETSIZE, which doesn't exist when using Hwloc, we
use the get_max_proc() function which can vary based on the operating system.
For example on Windows with multiple processor groups, it might be the case that
the highest bit possible in the bitmask is not equal to the number of hardware
threads on the machine but something higher than that.

Differential Revision: https://reviews.llvm.org/D24206

llvm-svn: 281245
2016-09-12 19:02:53 +00:00
George Rokos 118de30b44 [OPENMP] ppc64le recognized as big-endian
There is a bug in CMakeLists which causes powerpc64le systems to be recognized as big-endian. This patch fixes the issue.

Differential Revision: https://reviews.llvm.org/D23626

llvm-svn: 281068
2016-09-09 18:04:23 +00:00
George Rokos 28f31b405e [OPENMP] Implementation of omp_get_default_device and omp_set_default_device
Implementation of missing OpenMP 4.0 API functions omp_get_default_device and omp_set_default_device.
Also, added support for the environment variable OMP_DEFAULT_DEVICE.

Differential Revision: https://reviews.llvm.org/D23587

llvm-svn: 281065
2016-09-09 17:55:26 +00:00
Jonathan Peyton e6abe52905 Move function into cpp file under KMP_AFFINITY_SUPPORTED guard.
When affinity isn't supported, __kmp_affinity_compact doesn't exist.  The
problem is that in kmp_affinity.h there is a function which uses it without the
proper KMP_AFFINITY_SUPPORTED guard around it.  The compiler was smart enough to
ignore it and the function __kmp_affinity_cmp_Address_child_num which relies on
it, but I think it is cleaner to have it under the proper guard.  Since the
function is only used in the kmp_affinity.cpp file and there aren't any plans to
have it elsewhere.  I have moved it there.

llvm-svn: 280542
2016-09-02 20:54:58 +00:00
Jonathan Peyton 9e69696f5a Decouple the kmp_affin_mask_t type from determining if affinity is capable
the __kmp_affinity_determine_capable() functions are highly operating system
specific.  This change has the functions use the type they expect explicitly.

llvm-svn: 280538
2016-09-02 20:35:47 +00:00
Jonathan Peyton 788c5d65e8 Replace a bad instance of __kmp_free() with KMP_CPU_FREE_ARRAY() macro.
llvm-svn: 280530
2016-09-02 19:37:12 +00:00