Compare commits

...
106 Commits
Author SHA1 Message Date
Hans Wennborg b76842ed16 Creating release_90 branch off revision 366426
git-svn-id: https://llvm.org/svn/llvm-project/openmp/branches/release_90@366428 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-18 11:53:54 +00:00
Ron Lieberman c1b1ef1c00 [OPENMP] Resolve lost LoopTripCnt for subsequent loops in same thread.
Remove loopTripCnt from threaded device stack after consuming it.
Added a libomptarget DP message to aid in future debugging and to
validate the added testcase, which only runs in Debug build.

Differential Revision: https://reviews.llvm.org/D64808


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@366349 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-17 17:07:52 +00:00
Jonathan Peyton 07f4283e71 Remove REQUIRES OMP spec version within lit tests
This is a follow up patch to D64534 (r365963) which removed all OMP
spec versioning within the OpenMP runtime codebase.  This patch removes
REQUIRES: openmp-x.y lines from lit tests.


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@366341 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-17 15:41:00 +00:00
Jonas Hahnfeld cff3557e55 [OpenMP] Move header inclusion out of 'extern "C"'
This leads to problems when compiling C++ code with libc++ for Nvidia GPUs
because Clang now uses wrappers for math functions that might include
C++ templates not allowed in 'extern "C"'.

Differentiel Revision: https://reviews.llvm.org/D64625

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@366229 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-16 17:16:43 +00:00
Alexey Bataev 0519a2c6b2 [OPENMP][NVPTX]Fixed checks for cuda versions.
Summary:
We used CUDART_VERSION macro to check for the installed cuda version
but this macro is defined in cuda_runtime_api.h, which is not used by
project. Better to use CUDA_VERSION macro, which is defined in cuda.h.
Also, added the check if this macro is defined. If macro is undefined,
there is something wrong with the cuda configuration and we should not
continue the compilation.
This also fixes problems with runtime building in cuda 10+.

Reviewers: grokos

Subscribers: guansong, jdoerfert, caomhin, kkwli0, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D64648

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@366224 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-16 16:07:10 +00:00
Alexey Bataev 946967528b [OPENMP]Fix threadid in __kmpc_omp_taskwait call for dependent target calls.
Summary:
We used to call __kmpc_omp_taskwait function with global threadid set to
0. It may crash the application at the runtime if the thread executing
 target region is not a master thread.

Reviewers: grokos, kkwli0

Subscribers: guansong, jdoerfert, caomhin, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D64571

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@366220 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-16 15:51:32 +00:00
Jonathan Peyton d4b114904a [OpenMP] Remove OMP spec versioning
Remove all older OMP spec versioning from the runtime and build system.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D64534


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@365963 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-12 21:45:36 +00:00
Jonas Hahnfeld bb2634a97e [libomptarget] Fix typos and grammar in error messages, NFC.
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@365890 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-12 10:21:55 +00:00
Jonas Hahnfeld 8e626ba79d [libomptarget-nvptx] Remove dead functions
These entry points are never called by Clang trunk nor clang-ykt. If
XL doesn't use them either, they can finally go away.

Differential Revision: https://reviews.llvm.org/D52700

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@365817 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-11 20:12:51 +00:00
Andrey Churbanov 201ba9ed4c NFC: fixed typo #ifdef --> #if to allow macro set to 0 work correctly
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@365642 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-10 15:09:37 +00:00
Alexey Bataev 3a22f66a9b [OPENMP]Rename loopTripCnt member data to LoopTripCnt, NFC.
Rename variable to follow LLVM coding standard.

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@365368 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-08 18:45:48 +00:00
Alexey Bataev 0b1328156a [OPENMP]Make __kmpc_push_tripcount thread safe.
Summary:
__kmpc_push_tripcount function is not thread safe and may lead to data
race when the target regions are executed in parallel threads. The patch
makes loopTripCnt counter thread aware and stores the tripcount value
per thread in the map. Access to map is guarded by mutex to prevent
data race in the map itself.
Test is for NVPTX target because it does not work correctly on the
host. Seems to me, there is a problem in libomp with target regions in
the parallel threads.

Reviewers: grokos

Subscribers: guansong, jfb, jdoerfert, openmp-commits, kkwli0, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D64080

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@365332 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-08 15:30:23 +00:00
Andrey Churbanov bbbee1dd60 Create a runtime option to disable task throttling.
Patch by viroulep (Philippe Virouleau)

Differential Revision: https://reviews.llvm.org/D63196


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@364934 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-02 15:10:20 +00:00
Andrey Churbanov f9ad1a04db Cleanup of unused code
Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D63891


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@364925 91177308-0d34-0410-b5e6-96231b3b80d8
2019-07-02 13:45:40 +00:00
Alexey Bataev a31ae2e44a [OPENMP][NVPTX]Relax flush directive.
Summary:
According to the OpenMP standard, flush  makes a thread’s temporary view of memory consistent with memory and enforces an order on the memory operations of the variables explicitly specified or implied.

According to the Cuda toolkit documentation (https://docs.nvidia.com/cuda/archive/8.0/cuda-c-programming-guide/index.html#memory-fence-functions), __threadfence() functions provides required functionality.

__threadfence_system() also provides required functionality, but it also
includes some extra functionality, like synchronization of page-locked
host memory, synchronization for the host, etc. It is not required per
the standard and we can use more relaxed version of memory fence
operation.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jfb, jdoerfert, openmp-commits, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D62397

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@364572 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-27 18:33:09 +00:00
Andrey Churbanov 0afc673b17 Fixed memory use-after-free problem.
Bug reported in https://bugs.llvm.org/show_bug.cgi?id=42269.
Freeing of the contention group (CG) stucture by master thread looks wrong,
because workers can leave the CG later on. Intead the freeing
is now done by the last thread leaving the CG.

Differential Revision: https://reviews.llvm.org/D63599


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@364456 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-26 18:11:26 +00:00
Gheorghe-Teodor Bercea 4df92eda05 [OpenMP][libomptarget] Add support for declare target to clause under unified memory
Summary:
This patch adds support for handling variables under the:

```
#pragma omp declare target to()
```

clause when the 

```
#pragma omp requires unified_shared_memory
```

is used.

The address of the host variable is copied into the device pointer just like for the declare target link case.

Reviewers: ABataev, caomhin, grokos, AlexEichenberger

Reviewed By: grokos

Subscribers: jcownie, guansong, jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D63106

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@363825 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-19 15:48:10 +00:00
Alexey Bataev 79d5d6d37a [OPENMP][CUDA]Use __syncthreads when compiled by nvcc and clang >= 9.0.
Summary:
The problems with __syncthreads() were fixed in clang >= 9.0 and the
original __syncthreads() can be used instead of the ptx instruction.

Reviewers: grokos

Subscribers: guansong, jdoerfert, openmp-commits, kkwli0, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D63515

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@363807 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-19 14:20:34 +00:00
Andrey Churbanov 3f381f546e New implementation of OpenMP 5.0 detached tasks.
Patch by Alex Duran

Differential Revision: https://reviews.llvm.org/D62485


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@363799 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-19 13:23:28 +00:00
Gheorghe-Teodor Bercea e9791d7f37 [OpenMP] Add task alloc function
Summary: Add the target task allocation function to the interface.

Reviewers: ABataev, AlexEichenberger, caomhin, jlpeyton, AndreyChurbanov, RaviNarayanaswamy, hbae

Reviewed By: AlexEichenberger, hbae

Subscribers: hbae, RaviNarayanaswamy, cfe-commits, Hahnfeld, guansong, jdoerfert, openmp-commits

Tags: #openmp, #clang

Differential Revision: https://reviews.llvm.org/D63010

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@363449 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-14 20:15:15 +00:00
Andrey Churbanov 402c7439d7 Added propagation of not big initial stack size of master thread to workers.
Currently implemented only for non-Windows 64-bit platforms.

Differential Revision: https://reviews.llvm.org/D62488


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@362618 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-05 16:14:47 +00:00
Gheorghe-Teodor Bercea dba741d61d [OpenMP][libomptarget] Enable usage of unified memory for declare target link variables
Summary: This patch enables the usage of a host variable on the device for declare target link variables when unified memory is available.

Reviewers: ABataev, caomhin, grokos

Reviewed By: grokos

Subscribers: Hahnfeld, guansong, jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60884

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@362505 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-04 15:05:53 +00:00
Andrey Churbanov 6973da5c32 Fixed build warning with -DLIBOMP_USE_HWLOC=1
Made type of depth of hwloc object to correapond with
change from unsigned in hwloc 1,x to int in hwloc 2.x.
This eliminates the warning on signed-unsigned comparison.

Differential Revision: https://reviews.llvm.org/D62332


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@362401 91177308-0d34-0410-b5e6-96231b3b80d8
2019-06-03 14:21:59 +00:00
Hansang Bae 74db2a4213 Fix OMP_TARGET_OFFLOAD parsing
Current parsing allows trailing string after the permitted value,
MANDATORY|DISABLED|DEFAULT -- e.g., "mandatorynot" is also recognized
as "MANDATORY". Such cases should be recognized as incorrect/unknown
value.

Differential Revision: https://reviews.llvm.org/D62431


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@362125 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-30 18:35:07 +00:00
Hansang Bae 48eeef98d8 Add checks before pointer dereferencing
This change adds checks before dereferencing a pointer returned from a
function.

Differential Revision: https://reviews.llvm.org/D62224


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@362111 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-30 16:32:20 +00:00
Michal Gorny 93fe5cefbd [openmp] [test] Skip kernel-breaking tests on NetBSD
The omp_taskloop_num_tasks and omp_taskwait have deadlooped
on the NetBSD buildbot previously, practically hanging the host running
it.  Disable them until we can find a good solution, or make the kernel
less fragile.

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361825 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-28 14:10:47 +00:00
Alexey Bataev 34def82866 Revert "[OPENMP][NVPTX]Fix barriers and parallel level counters, NFC."
This reverts commit r361421 to split the patch into 3 parts.

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361638 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-24 14:06:47 +00:00
Alexey Bataev 926938a039 [OPENMP][NVPTX]Fix barriers and parallel level counters, NFC.
Summary:
Parallel level counter should be volatile to prevent some dangerous
optimiations by the ptxas. Otherwise, ptxas optimizations lead to
undefined behaviour in some cases.
Also, use __threadfence() for #pragma omp flush and if the barrier
should not be used (we have only one thread in the team), still perform
flush operation since the standard requires implicit flush when
executing barriers.

Reviewers: gtbercea, kkwli0, grokos

Subscribers: guansong, jfb, jdoerfert, openmp-commits, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D62199

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361421 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-22 19:50:32 +00:00
Andrey Churbanov f8e8d598bf Fixed third issue reported in https://bugs.llvm.org/show_bug.cgi?id=41584.
Removed wrong debug assertion.

Differential Revision: https://reviews.llvm.org/D62251


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361408 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-22 16:48:05 +00:00
Jonathan Peyton 7481323078 [OpenMP] Add implementation to two OMPT API routines
This change adds implementation to ompt_finalize_tool() and
ompt_get_task_memory().

Patch by Hansang Bae

Differential Revision: https://reviews.llvm.org/D61657


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361309 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-21 20:51:05 +00:00
Gheorghe-Teodor Bercea 9994ae3c1c [OpenMP][libomptarget] Enable requires flags for target libraries.
Summary:
Target link variables are currently implemented by creating a copy of the variables on the device side and unified memory never gets exploited.

When the prgram uses the:

```
#pragma omp requires unified_shared_memory
```

directive in conjunction with a declare target link, the linked variable is no longer allocated on the device and the host version is used instead.

This behavior is overridden by performing an explicit mapping.

A Clang side patch is required.

Reviewers: ABataev, AlexEichenberger, grokos, Hahnfeld

Reviewed By: AlexEichenberger, grokos, Hahnfeld

Subscribers: Hahnfeld, jfb, guansong, jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60223

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361294 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-21 19:35:02 +00:00
Joachim Protze 665d5c5112 [OpenMP][OMPT] Fix locking testcases for 32 bit architectures
https://reviews.llvm.org/D58454 did not fix the problem for a typical use
case of building LLVM with gcc or icc and then testing with the newly built
clang compiler.
The compilers do not agree on how to extend a 32-bit pointer to uint64, so
make the pointer unsigned first, before adjusting the size.

Patch by Joachim Protze

Differential Revision: https://reviews.llvm.org/D58506

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361158 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-20 14:21:42 +00:00
Joachim Protze dac3432cdb [OMPT] Handling of the events of initial-task-begin and initial-task-end
OpenMP 5.0 says that the callback for the events initial-task-begin and
initial-task-end has to be ompt_callback_implicit_task.

Patch by Tim Cramer

Differential Revision: https://reviews.llvm.org/D58776

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@361157 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-20 14:21:36 +00:00
Andrey Churbanov ba56714719 Fixed second issue reported in https://bugs.llvm.org/show_bug.cgi?id=41584.
Added synchronization for possible concurrent initialization of mutexes
by multiple threads. The need of synchronization caused by commit r357927
which added the use of mutexes at threads movement to/from common pool
(earlier the mutexes were used only at suspend/resume).

Patch by Johnny Peyton.

Differential Revision: https://reviews.llvm.org/D61995


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360919 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-16 17:52:53 +00:00
Paul Osmialowski 9a0d0f00e9 Fix hwloc topology traversal code unable to handle situation where L2 cache is common for the packages
Currently cores within package that share the same L2 cache are grouped together.
The current logic behind this assumes that the L2 cache is always at deeper
(or the same) level than the package itself. In case when L2 cache is common
for all packages (and the packages are at deeper level than L2 cache) the whole of
the further topology discovery fails to find any computational units resulting in
following assertion:

Assertion failure at kmp_affinity.cpp(715): nActiveThreads == __kmp_avail_proc.
OMP: Error #13: Assertion failure at kmp_affinity.cpp(715).

This patch adds a bit of a logic that prevents such situation from occurring.

Differential Revision: https://reviews.llvm.org/D61796



git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360890 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-16 13:16:24 +00:00
Andrey Churbanov a86b5e4738 Fixed https://bugs.llvm.org/show_bug.cgi?id=41584.
Removed unconditional and unsafe decrement of counter 
of active threads in pool at shutdown time.

Differential Revision: https://reviews.llvm.org/D61944


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360784 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-15 16:53:45 +00:00
Andrey Churbanov 0a3b7b60f6 Introduce new OpenMP 5.0 depend object type.
The implementation should be done by compiler, user can only declare
objects of this type and use them in OpenMP directives.

Differential Revision: https://reviews.llvm.org/D61860


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360774 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-15 13:45:36 +00:00
Eli Friedman c1985baed2 [OpenMP][AArch64] Fix compile with LLVM trunk.
The code is currently using the ambiguous instruction
"sub sp, sp, w9, lsl #4". The ARM reference manual says this isn't
valid, and it's not clear whether it's supposed to mean uxtw or uxtx.

It doesn't matter which instruction we use here, since the high
bits of the operand are zero anyway, so I arbitrarily choose uxtw, to
preserve the register name.

See https://reviews.llvm.org/D60840 for the LLVM patch.

Differential Revision: https://reviews.llvm.org/D61770



git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360711 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-14 21:44:54 +00:00
Andrey Churbanov 8db7163070 fixed typo made by commit r360595
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360602 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-13 17:04:32 +00:00
Andrey Churbanov fe501ad8d1 Fixed creation of aliases in Windows build.
Changed file extension of the destination of the copy of libomp.lib
(it was mistakely .dll, now it is .lib) in installation on Windows.

Differential Revision: https://reviews.llvm.org/D61673


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360595 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-13 16:07:37 +00:00
Alexey Bataev d5bb0a8d36 [OPENMP][NVPTX]Simplify handling of thread limit, NFC.
Summary:
Patch improves performance of the full runtime mode by moving
threads limit counter to the shared memory. It also allows to save
global memory.

Reviewers: grokos, kkwli0, gtbercea

Subscribers: guansong, jdoerfert, openmp-commits, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61801

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360584 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-13 14:21:46 +00:00
Alexey Bataev d140b83ae9 [OPENMP][NVPTX]Improve number of threads counter, NFC.
Summary:
Patch improves performance of the full runtime mode by moving
number-of-threads counter to the shared memory. It also allows to save
global memory.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jfb, jdoerfert, openmp-commits, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61785

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360457 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-10 18:56:05 +00:00
Jonathan Peyton e55ab99292 [OpenMP] Workaround gfortran bugzilla build bug 41755
This patch provides workaround to allow gfortran to compile the
OpenMP Fortran modules.

From the gfortran manual:
https://gcc.gnu.org/onlinedocs/gcc-9.1.0/gfortran/BOZ-literal-constants.html

"Note that initializing an INTEGER variable with a statement such as
DATA i/Z'FFFFFFFF'/ will give an integer overflow error rather than the desired
result of -1 when i is a 32-bit integer on a system that supports 64-bit
integers. The -fno-range-check option can be used as a workaround for legacy
code that initializes integers in this manner."

Bug filed: https://bugs.llvm.org/show_bug.cgi?id=41755

Differential Revision: https://reviews.llvm.org/D61603


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360299 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-08 23:12:31 +00:00
Dimitry Andric aebe831622 Add non-SSE wrapper for __kmp_{load,store}_mxcsr
Summary:
To be able to successfully build OpenMP on FreeBSD/i386, which still
uses i486 as its default processor, I had to provide wrappers for the
`__kmp_load_mxcsr` and `__kmp_store_mxcsr` functions.

If the compiler signals that SSE is not available, loading and storing
mxcsr does not make sense anway, so in that case the inline functions
are empty.  This gives the minimum amount of code churn.

See also https://svnweb.freebsd.org/changeset/base/345283

Reviewers: emaste, jlpeyton, Hahnfeld

Reviewed By: jlpeyton

Subscribers: hfinkel, krytarowski, jdoerfert, openmp-commits, llvm-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60916

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@360062 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-06 17:58:03 +00:00
Alexey Bataev ae9830cdb8 [OPENMP][NVPTX]Improve thread limit counter, NFC.
Summary:
Patch improves performance of the full runtime mode by moving
thread-limit counter to the shared memory. It also allows to save
global memory.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jdoerfert, caomhin, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61526

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359922 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-03 20:00:38 +00:00
Alexey Bataev 49325fc6ab [OPENMP][NVPTX]Improved several standard OpenMP functions, NFC.
Summary:
Used parallelLevel[] counter to simplify and improve implementation of
the existing standard OpenMP functions. Functions are tested already in
several tests, the patch is NFC.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jdoerfert, caomhin, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61459

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359892 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-03 14:47:20 +00:00
Alexey Bataev 2d4c5f915a [OPENMP][NVPTX]Improve code by using parallel level counter.
Summary:
Previously for the different purposes we need to get the active/common
parallel level and with full runtime we iterated over all the records to
calculate this level. Instead, we can used the warp-based parallel level
counters used in no-runtime mode.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jfb, jdoerfert, caomhin, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61395

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359822 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-02 20:05:01 +00:00
Alexey Bataev db75b85d57 [OPENMP][NVPTX]Improve omp_get_max_threads() function.
Summary:
Function omp_get_max_threads() can always return 1 if current execution
mode is SPMD.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jdoerfert, caomhin, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61379

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359792 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-02 14:52:52 +00:00
Alexey Bataev 573fae7275 [OPENMP][NVPTX]Improved omp_get_thread_limit() function.
Summary:
Function omp_get_thread_limit() in SPMD mode can return the maximum
available number of threads as a result.

Reviewers: grokos, gtbercea, kkwli0

Subscribers: guansong, jdoerfert, openmp-commits, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D61378

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359790 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-02 14:46:32 +00:00
Dimitry Andric ca840d66bb Enable OpenMP build for 32-bit FreeBSD
Summary:
To be able to successfully build OpenMP on 32-bit FreeBSD, such as
FreeBSD/i386, I first had to provide a few wrappers (see D60916), and
then add `KMP_OS_FREEBSD` to the list of defines checked for 32-bit
architectures in `kmp_runtime.cpp`.

I have successfully built libomp.so and ran a bunch of test programs on
FreeBSD/i386 with this.

See also https://svnweb.freebsd.org/changeset/base/345283

Reviewers: emaste, jlpeyton, Hahnfeld

Reviewed By: jlpeyton

Subscribers: krytarowski, guansong, jdoerfert, openmp-commits, llvm-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60917

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359716 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-01 19:32:58 +00:00
Jonathan Peyton 9377fa9653 [OpenMP] Implement task modifier for reduction clause
Implemented task modifier in two versions - one without taking into account
omp_orig variable (the omp_orig still can be processed by compiler without help
of the library, but each reduction object will need separate initializer with
global access to omp_orig), another with omp_orig variable included into
interface (single initializer can be used for multiple reduction objects of
the same type). Second version can be used when the omp_orig is not globally
accessible, or to optimize code in case of multiple reduction objects
of the same type.

Patch by Andrey Churbanov

Differential Revision: https://reviews.llvm.org/D60976


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359710 91177308-0d34-0410-b5e6-96231b3b80d8
2019-05-01 17:54:01 +00:00
Jonathan Peyton 67ef47a8a1 [OpenMP] Add OpenMP 5.0 nonmonotonic code
This patch adds:
* New omp_sched_monotonic flag to omp_sched_t which is handled within the runtime
* Parsing of monotonic/nonmonotonic in OMP_SCHEDULE
* Tests for the monotonic flag and envirable parsing
* Logic to force monotonic when hierarchical scheduling is used

Differential Revision: https://reviews.llvm.org/D60979


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359601 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-30 19:20:35 +00:00
Jonathan Peyton 03f8ac57f0 [OpenMP] Eliminate some compiler warnings
* Remove accidental == for =
* Assign values to variables to appease compiler
* Surround debug code with KMP_DEBUG
* Remove unused local typedefs

Differential Revision: https://reviews.llvm.org/D60983


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359599 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-30 19:13:37 +00:00
Alexey Bataev 867a57389a [OPENMP][NVPTX]Correctly handle L2 parallelism in SPMD mode.
Summary:
The parallelLevel counter must be on per-thread basis to fully support
L2+ parallelism, otherwise we may end up with undefined behavior.
Introduce the parallelLevel on per-warp basis using shared memory. It
allows to avoid the problems with the synchronization and allows fully
support L2+ parallelism in SPMD mode with no runtime.

Reviewers: gtbercea, grokos

Subscribers: guansong, jdoerfert, caomhin, kkwli0, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60918

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@359341 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-26 19:30:34 +00:00
Dimitry Andric 777f60f39b Use correct way to test for MIPS arch after rOMP355687
Summary:
I ran into some issues after rOMP355687, where __atomic_fetch_add was
being used incorrectly on x86, and this turns out to be caused by the
following added conditionals:

```
#if defined(KMP_ARCH_MIPS)
```

The problem is, these macros are always defined, and are either 0 or 1
depending on the architecture.  E.g. the correct way to test for MIPS
is:

```
#if KMP_ARCH_MIPS
```

Reviewers: petarj, jlpeyton, Hahnfeld, AndreyChurbanov

Reviewed By: petarj, AndreyChurbanov

Subscribers: AndreyChurbanov, sdardis, arichardson, atanasyan, jfb, jdoerfert, openmp-commits, llvm-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60938

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@358911 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-22 19:20:46 +00:00
Alexey Bataev a76db752a7 [OPENMP][NVPTX] Fix the test, NFC.
Fix the test to run it really in SPMD mode without runtime. Previously
it was run in SPMD + full runtime mode and does not allow to cehck the
functionality correctly.

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@358902 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-22 17:25:31 +00:00
Andrey Churbanov 31b09e96f2 Fixed memory leak reported in Bugzilla:
https://bugs.llvm.org/show_bug.cgi?id=41494

Freed th_cg_roots structure at exit from uber thread.

Differential Revision: https://reviews.llvm.org/D60729


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@358572 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-17 10:44:28 +00:00
Alexey Bataev 6c198765a0 [OPENMP][NVPTX]Fix dynamic scheduling in L2+ SPMD parallel regions.
Summary:
If the kernel is executed in SPMD mode and the L2+ parallel for region
with the dynamic scheduling is executed, dynamic scheduling functions
are called. They expect full runtime support, but SPMD kernels may be
executed without the full runtime. It leads to the runtime crash of the
compiled program. Patch fixes this problem + fixes handling of the
parallelism level in SPMD mode, which is required as part of this patch.

Reviewers: gtbercea, kkwli0, grokos

Subscribers: guansong, jdoerfert, openmp-commits, caomhin

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D60578

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@358442 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-15 20:15:20 +00:00
Jonathan Peyton c1629ee231 [OpenMP] Exchange code in asm file for inline assembly
This change replaces some of the assembly functions in z_Linux_asm.S
for inline asm in kmp.h. This allows better interaction with compiler
tools and sanitizers.

Differential Revision: https://reviews.llvm.org/D60423


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@358438 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-15 19:19:57 +00:00
Andrey Churbanov cc33e97870 Fixed possible out of bound array access.
The check of index value moved to before the write to the array.

Differential Revision: https://reviews.llvm.org/D60471


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@358181 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-11 15:03:44 +00:00
Jonathan Peyton e45eef02bb [OpenMP] Implement 5.0 memory management
* Replace HBWMALLOC API with more general MEMKIND API, new functions
  and variables added.
* Have libmemkind.so loaded when accessible.
* Redirect memspaces to default one except for high bandwidth which
  is processed separately.
* Ignore some allocator traits e.g., sync_hint, access, pinned, while
  others are processed normally e.g., alignment, pool_size, fallback,
  fb_data, partition.
* Add tests for memory management

Patch by Andrey Churbanov

Differential Revision: https://reviews.llvm.org/D59783


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@357929 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-08 17:59:28 +00:00
Jonathan Peyton 258655da08 [OpenMP] Clean up load balancing dynamic mode
This patch cleans up the bookkeeping code for the load balancing dynamic mode.

When a thread is moved to or from the thread pool, the th_active_in_pool flag
and the __kmp_thread_pool_active_nth global counter are both updated. This
removes the need for the corrective code in the main wait loop. Another global
counter, __kmp_thread_pool_nth, was removed completely, as it was only used for
debugging, but was not under KMP_DEBUG.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D59508


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@357927 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-08 17:50:02 +00:00
Dimitry Andric 4403c91b6b After rL357618, quote ${CMAKE_THREAD_LIBS_INIT} so CMake does not
complain when the variable is empty.  Fixes PR 41401.


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@357828 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-05 22:19:40 +00:00
Jonathan Peyton c8db463d1f [OpenMP] Fix hang on Windows
Debug dump on large machine shows when many OpenMP threads (401 in total)
sleep on a barrier, one of the innermost nesting levels sleeps
on a child's b_arrived flag whose value is equal to 4 and is equal to
checker value. i.e., (1) sleep bit is 0, and (2) done_check() would
return true if called.

It is unclear how this might happen. It could be Windows Server 2016's
error of EnterCriticalSection / LeaveCriticalSection, or
error of WaitForSingleObject / SetEvent / ResetEvent, or
error in the library which is very difficult to find.

As a workaround, change INFINITE wait to timed wait, so that each
thread awakens each 5 seconds (the timeout was chosen arbitrary to not
disturb other threads much), check flag condition under the lock, and
either go to sleep again or stop sleeping as a result of the check.

Patch by Andrey Churbanov

Differential Revision: https://reviews.llvm.org/D59793


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@357722 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-04 20:35:29 +00:00
Jonathan Peyton 3d280aa419 [OpenMP][Stats] Fix stats gathering for distribute and team clause
The distribute clause needs an explicit push of a timer. The teams
clause needs a timer added and also, similarly to parallel, exchanged
with the serial timer when encountered so that serial regions are
counted properly.

Differential Revision: https://reviews.llvm.org/D59801


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@357621 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-03 18:53:26 +00:00
Dimitry Andric cf0276b9ab Ensure correct pthread flags and libraries are used
On most platforms, certain compiler and linker flags have to be passed
when using pthreads, otherwise linking against libomp.so might fail with
undefined references to several pthread functions.

Use CMake's `find_package(Threads)` to determine these for standalone
builds, or take them (and optionally modify them) from the top-level
LLVM cmake files.

Also, On FreeBSD, ensure that libomp.so is linked against libm.so,
similar to NetBSD.

Adjust test cases with hardcoded `-lpthread` flag to use the common
build flags, which should now have the required pthread flags.

Reviewers: emaste, jlpeyton, krytarowski, mgorny, protze.joachim, Hahnfeld

Reviewed By: Hahnfeld

Subscribers: AndreyChurbanov, tra, EricWF, Hahnfeld, jfb, jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D59451


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@357618 91177308-0d34-0410-b5e6-96231b3b80d8
2019-04-03 18:11:36 +00:00
Michael Kruse 3e3199a800 [libomptarget] Introduce LIBOMPTARGET_ENABLE_DEBUG cmake option.
At the moment, support for runtime debug output using the
OMPTARGET_DEBUG=1 environment variable is only available with
CMAKE_BUILD_TYPE=Debug builds. The patch allows setting it independently
using the LIBOMPTARGET_ENABLE_DEBUG option, which is enabled by default
depending on CMAKE_BUILD_TYPE. That is, unless this option is set
explicitly, nothing changes. This is the same mechanism used by LLVM for
LLVM_ENABLE_ASSERTIONS.

This patch also removes adding -g -O0 in debug builds, it should be
handled by cmake's CMAKE_{C|CXX}_FLAGS_DEBUG configuration option.

Idea by Hal Finkel

Differential Revision: https://reviews.llvm.org/D55952

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356998 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-26 15:19:15 +00:00
Jonathan Peyton fe2a27367a [OpenMP] Add LLVM license header to file
This file was missing the LLVM license header



git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356962 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-25 22:36:31 +00:00
Jonathan Peyton e6bc0b3edb [OpenMP] Add Intel 19.0 to list of compilers in kmp_version.cpp
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356961 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-25 22:31:00 +00:00
Dimitry Andric 28e31a2d58 Fix interoperability test compilation on FreeBSD
Summary:
While building the 8.0 releases on FreeBSD, I encountered the following
error in the regression tests, where ompt/misc/interoperability.cpp
failed to compile, with:

```
projects/openmp/runtime/test/ompt/misc/interoperability.cpp:7:10: fatal error: 'alloca.h' file not found
#include <alloca.h>
         ^~~~~~~~~~
```

Like on NetBSD, alloca(3) is defined in <stdlib.h> instead.

Reviewers: emaste, jlpeyton, krytarowski, mgorny, protze.joachim

Reviewed By: jlpeyton

Subscribers: jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D59736

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356936 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-25 18:37:49 +00:00
Dimitry Andric 13cfd61cf5 Fix gettid warnings on FreeBSD
Summary:
[Split off from D59451 to get this fix in separately]

While building the 8.0 releases on FreeBSD, I encountered the following
warnings in openmp quite a few times:

```
In file included from projects/openmp/runtime/src/kmp_settings.cpp:27:
projects/openmp/runtime/src/kmp_wrapper_getpid.h:35:2: warning: #warning is a language extension [-Wpedantic]
#warning No gettid found, use getpid instead
 ^
projects/openmp/runtime/src/kmp_wrapper_getpid.h:35:2: warning: No gettid found, use getpid instead [-W#warnings]
2 warnings generated.
```

I added a gettid wrapper that uses FreeBSD's pthread_getthreadid_np(3)
function for this.

Reviewers: emaste, jlpeyton, krytarowski, mgorny, protze.joachim

Reviewed By: jlpeyton

Subscribers: jfb, jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D59735

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356934 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-25 18:37:14 +00:00
Jonathan Peyton 5696c2b695 [OpenMP] Fix pause check with version info
Add 5.0 guard to pause code for now.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D59428


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356933 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-25 18:17:55 +00:00
Jonathan Peyton 59e2a5754d [OpenMP] Fix OMPT cancellation test for GOMP
The GOMP sections interface uses schedule(dynamic) dispatch so it cannot
be assumed which thread executes the cancel and which thread executes
the cancellation point.  This patch allows either thread to execute either
section.


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356302 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-15 21:24:45 +00:00
Jonathan Peyton 9b5ef0220a [OpenMP] Add missing parenthesis in Perl module
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356289 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-15 18:27:14 +00:00
Jonathan Peyton e7e8b2803e [OpenMP] Remove deprecated taskq
Remove very old, unused, and deprecated taskq code.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D58989


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@356288 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-15 18:24:59 +00:00
Jonathan Peyton 922ed1345c [OpenMP][stats] Update stats gathering macros
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@355739 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-08 21:23:34 +00:00
Petar Jovanovic e0a1fba241 [mips] Use libatomic instead of GCC intrinsics for 64bit
The following GCC intrinsics are not available on MIPS32:

__sync_fetch_and_add_8
__sync_fetch_and_and_8
__sync_fetch_and_or_8
__sync_val_compare_and_swap_8

Replace these with appropriate libatomic implementation.

Patch by Miodrag Dinic.

Differential Revision: https://reviews.llvm.org/D45691


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@355687 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-08 10:53:19 +00:00
Shoaib Meenai 6b80cedde4 [build] Rename clang-headers to clang-resource-headers
Summary:
The current install-clang-headers target installs clang's resource
directory headers. This is different from the install-llvm-headers
target, which installs LLVM's API headers. We want to introduce the
corresponding target to clang, and the natural name for that new target
would be install-clang-headers. Rename the existing target to
install-clang-resource-headers to free up the install-clang-headers name
for the new target, following the discussion on cfe-dev [1].

I didn't find any bots on zorg referencing install-clang-headers. I'll
send out another PSA to cfe-dev to accompany this rename.

[1] http://lists.llvm.org/pipermail/cfe-dev/2019-February/061365.html

Reviewers: beanz, phosek, tstellar, rnk, dim, serge-sans-paille

Subscribers: mgorny, javed.absar, jdoerfert, #sanitizers, openmp-commits, lldb-commits, cfe-commits, llvm-commits

Tags: #clang, #sanitizers, #lldb, #openmp, #llvm

Differential Revision: https://reviews.llvm.org/D58791

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@355340 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-04 21:19:53 +00:00
Stefan Pintilie 9aa5fc8a74 [OPENMP] Deal with additional store inserted by Clang under -fno-PIC for PowerPC.
Changing the default from -fPIC to -fno-PIC on PowerPC exposed an issue in
OpenMP for PowerPC.
The issue is reported here:
https://bugs.llvm.org/show_bug.cgi?id=40082

This is a fix for that issue.
Also removed the XFAIL from the two tests that were failing under -fno-PIC.

Differential Revision: https://reviews.llvm.org/D56286

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@355229 91177308-0d34-0410-b5e6-96231b3b80d8
2019-03-01 21:16:45 +00:00
Jonathan Peyton 2e429f17a6 [OpenMP][OMPT] Distinguish different barrier kinds
This change makes the runtime decide the intended use of each barrier
invocation, for the OMPT synchronization tool callbacks.  The OpenMP 5.0
specification defines four possible barrier kinds -- implicit, explicit,
implementation, and just normal barrier.

Patch by Hansang Bae

Differential Revision: https://reviews.llvm.org/D58247


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@355140 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-28 20:55:39 +00:00
Jonathan Peyton 8453ca8594 [OpenMP 5.0] Deprecate nest-var and associated features
Nest-var, OMP_NESTED, omp_set_nested()., and omp_get_nested() have been
deprecated in the 5.0 spec. Initial nesting info is now derived from
OMP_MAX_ACTIVE_LEVELS, OMP_NUM_THREADS, and OMP_PROC_BIND.

This patch deprecates the internal ICV that corresponds to nest-var, and
replaces it with the max-active-levels-var ICV to determine nesting. The
change still allows for use of OMP_NESTED (according to 5.0 changes),
omp_get_nested, and omp_set_nested, which have had deprecation messages
added to them. The change allows certain settings of OMP_NUM_THREADS,
OMP_PROC_BIND, and OMP_MAX_ACTIVE_LEVELS to turn on nesting, but
OMP_NESTED=0 will still force nesting to be off.

The runtime now prints informative messages about deprecation of
OMP_NESTED, omp_set_nested(), and omp_get_nested(), when those
environment variables or routines are used. It also prints deprecated
message in output for KMP_SETTINGS and OMP_DISPLAY_ENV for OMP_NESTED.
This patch also fixes OMP_DISPLAY_ENV output for OMP_TARGET_OFFLOAD.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D58408


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@355138 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-28 20:47:21 +00:00
Jonathan Peyton bbb6f01707 [OpenMP] Make use of sched_yield optional in runtime
This patch cleans up the yielding code and makes it optional. An
environment variable, KMP_USE_YIELD, was added. Yielding is still
on by default (KMP_USE_YIELD=1), but can be turned off completely
(KMP_USE_YIELD=0), or turned on only when oversubscription is detected
(KMP_USE_YIELD=2). Note that oversubscription cannot always be detected
by the runtime (for example, when the runtime is initialized and the
process forks, oversubscription cannot be detected currently over
multiple instances of the runtime).

Because yielding can be controlled by user now, the library mode
settings (from KMP_LIBRARY) for throughput and turnaround have been
adjusted by altering blocktime, unless that was also explicitly set.

In the original code, there were a number of places where a double yield
might have been done under oversubscription. This version checks
oversubscription and if that's not going to yield, then it does
the spin check.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D58148


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@355120 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-28 19:11:29 +00:00
Jonas Hahnfeld acb2548dde [OpenMP] Fix check-openmp after r354553
Calling add_openmp_testsuite will add the tests to check-openmp unless
EXCLUDE_FROM_ALL is set. This is problematic because the tests for OMPT
will be included twice which doesn't work if the same test is executed
concurrently by multiple threads.

See:
http://lab.llvm.org:8011/builders/openmp-gcc-x86_64-linux-debian/builds/163
http://lab.llvm.org:8011/builders/openmp-clang-x86_64-linux-debian/builds/184

http://lab.llvm.org:8011/builders/openmp-clang-ppc64le-linux-rhel/builds/133
(On PPC some failures are unrelated to r354553, the bot has been red before
and this commit is not expected to fix that. For a proper patch please see
https://reviews.llvm.org/D56286.)

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@354572 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-21 12:00:57 +00:00
Joachim Protze 698a904a22 [OpenMP][OMPT] Fix locking testcases for 32 bit architectures
Fix for the bug reported in:
https://bugs.llvm.org/show_bug.cgi?id=40531

The address is now casted the same way as in the runtime code.

Differential Revision: https://reviews.llvm.org/D58454

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@354553 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-21 08:50:49 +00:00
Gheorghe-Teodor Bercea eaaceb40bb [OpenMP][libomptarget] New reduction scheme for team reductions
Summary:
This patch adds a more sophisticated team reduction scheme to the OpenMP libomptarget-nvptx runtime.

The scheme uses a fixed size global memory buffer whose length can be adjusted via compiler flag:
```
-fopenmp-cuda-teams-reduction-recs-num=1024
```
The global buffer is a structure of arrays (with default size of 1024 each and controlled by the above flag), one array for each reduction variable.

Values in the buffer are processed by the last team to finish executing the body of the target region.

In addition to adding support for the new flag, the compiler also emits special functions used for the reduction of the intermediate reduction values. These changes will be added in a separate compiler patch following this one.




Reviewers: ABataev, caomhin

Reviewed By: ABataev

Subscribers: guansong, jfb, jdoerfert, openmp-commits

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D58409

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@354471 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-20 14:55:55 +00:00
Jonathan Peyton ebd6a4561f [OpenMP] Remove XFAIL for cancellation tests using gcc
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@354370 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-19 19:00:29 +00:00
Jonathan Peyton 85df023bba [OpenMP 5.0] Add omp_get_supported_active_levels()
This patch adds the new 5.0 API function omp_get_supported_active_levels().

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D58211


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@354368 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-19 18:51:11 +00:00
Jonathan Peyton 553654650e [OpenMP] Adding GOMP compatible cancellation
Remove fatal error messages from the cancellation API for GOMP
Add __kmp_barrier_gomp_cancel() to implement cancellation of parallel regions.
This new function uses the linear barrier algorithm with a cancellable
nonsleepable wait loop.

Differential Revision: https://reviews.llvm.org/D57969


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@354367 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-19 18:47:57 +00:00
Jonathan Peyton e518cdac15 [OpenMP] Fix broken link to browse sources
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@353858 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-12 17:00:57 +00:00
Jonathan Peyton bde568706e [OpenMP] Remove accidental commit to config-ix.cmake in r353747
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@353748 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-11 21:09:15 +00:00
Jonathan Peyton e85e92b0ff [OpenMP] Fix thread_limits to work properly for teams construct
The thread-limit-var and omp_get_thread_limit API was not perfectly handled for
teams construct. Now, when modified by thread_limit clause, omp_get_thread_limit
reports the correct value. In addition, the value is restored when leaving the
teams construct to what it was in the encountering context.

This is done partly by creating the notion of a Contention Group root (CG root)
that keeps track of the thread at the root of each separate CG, the
thread-limit-var associated with the CG, and associated counter of active
threads within the contention group.

thread-limits are passed from master to worker threads via an entry in the ICV
data structure. When a "contention group switch" occurs, a new CG root record is
made and passed from master to worker. A thread could potentially have several
CG root records if it encounters multiple nested teams constructs (but at the
moment the spec doesn't allow for nested teams, so the most one could have
currently is 2). The master of the teams masters gets the thread-limit clause
value stored to its local ICV structure, and the other teams masters copy it
from the master. The thread-limit is set from that ICV copy and restored to the
ICV copy when entering and leaving the teams construct.

This change also fixes a bug when the top-level teams construct team gets
reused, and OMP_DYNAMIC was true, which can cause the expected size of this team
to be smaller than what was actually allocated. The fix updates the size of the
team after its threads were reserved.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D56804


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@353747 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-11 21:04:23 +00:00
Jonas Hahnfeld 41cad1362d [OMPT] Remove test output from source tree
%s refers to the test file in the source tree. This was accidentally added in
r351197 / 2b46d30 ("[OMPT] Second chunk of final OMPT 5.0 interface updates").

Differential Revision: https://reviews.llvm.org/D58002

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@353715 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-11 16:14:51 +00:00
Taewook Oh 87a0e3609f Guard a feature that unsupported by old GCC
Summary:
As @david2050 commented, changes introduced by https://reviews.llvm.org/D56397 break builds for older compilers
which don't support `__has(_cpp)_attribute`. This is a fix for the break.

Reviewers: protze.joachim, jlpeyton, AndreyChurbanov, Hahnfeld, david2050

Subscribers: openmp-commits, david2050

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D57851

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@353538 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-08 17:15:50 +00:00
Joachim Protze 9d191f041c [OMPT] Make sure that OMPT is enabled when accessing internals of the runtime
The three switch fallthrough generate a warning with -Wimplicit-fallthrough.
Two are documented as fallthrough, one is not, but I think the intention is to also fallthrough in kmp_tasking.cpp.

Not sure whether kmp.h is the best place to define the macro.

Reviewers: jlpeyton, AndreyChurbanov, Hahnfeld

Reviewed By: jlpeyton

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D56397

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@353052 91177308-0d34-0410-b5e6-96231b3b80d8
2019-02-04 15:59:42 +00:00
Joachim Protze 71c5f3cb2f [OMPT] Make sure that OMPT is enabled when accessing internals of the runtime
Redo after revert by hans. The wrong include in one test is fixed.

Make sure that OMPT is enabled in runtime entry points that access internals
of the runtime. Else, return an appropiate value indicating an error or that
the data is not available.

Patch provided by @sconvent

Reviewers: jlpeyton, omalyshe, hbae, Hahnfeld, joachim.protze

Reviewed By: joachim.protze

Tags: #openmp, #ompt

Differential Revision: https://reviews.llvm.org/D47717

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@352611 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-30 08:41:06 +00:00
James Y Knight 2853609484 Adjust documentation for git migration.
This fixes most references to the paths:
 llvm.org/svn/
 llvm.org/git/
 llvm.org/viewvc/
 github.com/llvm-mirror/
 github.com/llvm-project/
 reviews.llvm.org/diffusion/

to instead point to https://github.com/llvm/llvm-project.

This is *not* a trivial substitution, because additionally, all the
checkout instructions had to be migrated to instruct users on how to
use the monorepo layout, setting LLVM_ENABLE_PROJECTS instead of
checking out various projects into various subdirectories.

I've attempted to not change any scripts here, only documentation. The
scripts will have to be addressed separately.

Additionally, I've deleted one document which appeared to be outdated
and unneeded:
  lldb/docs/building-with-debug-llvm.txt

Differential Revision: https://reviews.llvm.org/D57330

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@352514 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-29 16:37:27 +00:00
Arnaud A. de Grandmaison 95c11ec5a9 Remove no longer needed Arm specific words in the LICENSE.txt file.
As the codebase is now under the Apache 2.0 license with LLVM
Exceptions, and all Arm's contributions, past or future, are under that
new license, this Arm specific words in LICENSE.txt are no longer
needed.

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@352377 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-28 15:42:58 +00:00
Andrey Churbanov c1fe93aaa4 NFC: fixed formatting to be consistent across the file
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351748 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-21 16:11:43 +00:00
Andrey Churbanov f30a96a18f Fixed https://reviews.llvm.org/D55078 broken Fortran fixed form.
Long lines split in order to obey Fortran fixed form compilation.

Differential Revision: https://reviews.llvm.org/D57017


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351745 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-21 15:30:31 +00:00
Chandler Carruth 4b75f4e92a Fix typos throughout the license files that somehow I and my reviewers
all missed!

Thanks to Alex Bradbury for pointing this out, and the fact that I never
added the intended `legacy` anchor to the developer policy. Add that
anchor too. With hope, this will cause the links to all resolve
successfully.

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351731 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-21 09:52:34 +00:00
Chandler Carruth 7e084d9fdf Update more file headers across all of the LLVM projects in the monorepo
to reflect the new license. These used slightly different spellings that
defeated my regular expressions.

We understand that people may be surprised that we're moving the header
entirely to discuss the new license. We checked this carefully with the
Foundation's lawyer and we believe this is the correct approach.

Essentially, all code in the project is now made available by the LLVM
project under our new license, so you will see that the license headers
include that license only. Some of our contributors have contributed
code under our old license, and accordingly, we have retained a copy of
our old license notice in the top-level files in each project and
repository.

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351648 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-19 10:56:40 +00:00
Chandler Carruth 42bf584150 Install new LLVM license structure and new developer policy.
This installs the new developer policy and moves all of the license
files across all LLVM projects in the monorepo to the new license
structure. The remaining projects will be moved independently.

Note that I've left odd formatting and other idiosyncracies of the
legacy license structure text alone to make the diff easier to read.
Critically, note that we do not in any case *remove* the old license
notice or terms, as that remains necessary until we finish the
relicensing process.

I've updated a few license files that refer to the LLVM license to
instead simply refer generically to whatever license the LLVM project is
under, basically trying to minimize confusion.

This is really the culmination of so many people. Chris led the
community discussions, drafted the policy update and organized the
multi-year string of meeting between lawyers across the community to
figure out the strategy. Numerous lawyers at companies in the community
spent their time figuring out initial answers, and then the Foundation's
lawyer Heather Meeker has done *so* much to help refine and get us ready
here. I could keep going on, but I just want to make sure everyone
realizes what a huge community effort this has been from the begining.

Differential Revision: https://reviews.llvm.org/D56897

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351631 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-19 06:14:24 +00:00
Hans Wennborg e223da31a4 Revert r351311 "[OMPT] Make sure that OMPT is enabled when accessing internals of the runtime"
and also the follow-up r351315.

The new test is failing on the buildbots.

> Make sure that OMPT is enabled in runtime entry points that access internals
> of the runtime. Else, return an appropiate value indicating an error or that
> the data is not available.
>
> Patch provided by @sconvent
>
> Reviewers: jlpeyton, omalyshe, hbae, Hahnfeld, joachim.protze
>
> Reviewed By: joachim.protze
>
> Tags: #openmp, #ompt
>
> Differential Revision: https://reviews.llvm.org/D47717

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351431 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-17 11:31:03 +00:00
Jonathan Peyton 4338c2574e [OpenMP] Add omp_pause_resource* API
Add omp_pause_resource and omp_pause_resource_all API and enum, plus stub for
internal implementation. Implemented callable helper function to do local pause,
and added basic functionality for hard and soft pause.

Patch by Terry Wilmarth

Differential Revision: https://reviews.llvm.org/D55078


git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351372 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-16 20:07:39 +00:00
Joachim Protze da71b1ee45 [OpenMP] Output written by tests should go to build directory
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351332 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-16 13:06:10 +00:00
Joachim Protze 9c08284967 [OpenMP] Remove compiler warning about unused value
The compiler warns about an unused variable/statement:

    runtime/src/kmp_affinity.cpp:4958:18: warning: statement has no effect [-Wunused-value]
       KA_TRACE(1000, ; {
                      ^
    runtime/src/kmp_debug.h:84:24: note: in definition of macro 'KA_TRACE'
         __kmp_debug_printf x;                                                      \
                            ^

Instead of the unused reference to this function, this patch now calls the function
with an empty string. The call to this function should have no effect.

Patch provided by joachim.protze

Reviewers: jlpeyton, hbae, AndreyChurbanov

Reviewed By: AndreyChurbanov

Tags: #openmp, #ompt

Differential Revision: https://reviews.llvm.org/D56775

git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@351323 91177308-0d34-0410-b5e6-96231b3b80d8
2019-01-16 11:35:11 +00:00
251 changed files with 6889 additions and 12169 deletions
+237 -50
View File
@@ -1,4 +1,241 @@
==============================================================================
The LLVM Project is under the Apache License v2.0 with LLVM Exceptions:
==============================================================================
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
---- LLVM Exceptions to the Apache 2.0 License ----
As an exception, if, as a result of your compiling your source code, portions
of this Software are embedded into an Object form of such source code, you
may redistribute such embedded portions in such Object form without complying
with the conditions of Sections 4(a), 4(b) and 4(d) of the License.
In addition, if you combine or link compiled forms of this Software with
software that is licensed under the GPLv2 ("Combined Software") and if a
court of competent jurisdiction determines that the patent provision (Section
3), the indemnity provision (Section 9) or other Section of the License
conflicts with the conditions of the GPLv2, you may retroactively and
prospectively choose to deem waived or otherwise exclude such Section(s) of
the License, but only in their entirety and only with respect to the Combined
Software.
==============================================================================
Software from third parties included in the LLVM Project:
==============================================================================
The LLVM Project contains third party software which is under different license
terms. All such code will be identified clearly using at least one of two
mechanisms:
1) It will be in a separate directory tree with its own `LICENSE.txt` or
`LICENSE` file at the top containing the specific license and restrictions
which apply to that software, or
2) It will contain specific license and restriction terms at the top of every
file.
==============================================================================
Legacy LLVM License (https://llvm.org/docs/DeveloperPolicy.html#legacy):
==============================================================================
The software contained in this directory tree is dual licensed under both the
University of Illinois "BSD-Like" license and the MIT license. As a user of
@@ -122,53 +359,3 @@ conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE.
==============================================================================
ARM Limited
Software Grant License Agreement ("Agreement")
Except for the license granted herein to you, ARM Limited ("ARM") reserves all
right, title, and interest in and to the Software (defined below).
Definition
"Software" means the code and documentation as well as any original work of
authorship, including any modifications or additions to an existing work, that
is intentionally submitted by ARM to llvm.org (http://llvm.org) ("LLVM") for
inclusion in, or documentation of, any of the products owned or managed by LLVM
(the "Work"). For the purposes of this definition, "submitted" means any form of
electronic, verbal, or written communication sent to LLVM or its
representatives, including but not limited to communication on electronic
mailing lists, source code control systems, and issue tracking systems that are
managed by, or on behalf of, LLVM for the purpose of discussing and improving
the Work, but excluding communication that is conspicuously marked otherwise.
1. Grant of Copyright License. Subject to the terms and conditions of this
Agreement, ARM hereby grants to you and to recipients of the Software
distributed by LLVM a perpetual, worldwide, non-exclusive, no-charge,
royalty-free, irrevocable copyright license to reproduce, prepare derivative
works of, publicly display, publicly perform, sublicense, and distribute the
Software and such derivative works.
2. Grant of Patent License. Subject to the terms and conditions of this
Agreement, ARM hereby grants you and to recipients of the Software
distributed by LLVM a perpetual, worldwide, non-exclusive, no-charge,
royalty-free, irrevocable (except as stated in this section) patent license
to make, have made, use, offer to sell, sell, import, and otherwise transfer
the Work, where such license applies only to those patent claims licensable
by ARM that are necessarily infringed by ARM's Software alone or by
combination of the Software with the Work to which such Software was
submitted. If any entity institutes patent litigation against ARM or any
other entity (including a cross-claim or counterclaim in a lawsuit) alleging
that ARM's Software, or the Work to which ARM has contributed constitutes
direct or contributory patent infringement, then any patent licenses granted
to that entity under this Agreement for the Software or Work shall terminate
as of the date such litigation is filed.
Unless required by applicable law or agreed to in writing, the software is
provided on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
either express or implied, including, without limitation, any warranties or
conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE.
==============================================================================
+2 -6
View File
@@ -141,10 +141,6 @@ Options for ``libomp``
Intel(R) Many Integrated Core Architecture (Intel(R) MIC Architecture) to
build for. This value is ignored if **LIBOMP_ARCH** does not equal ``mic``.
**LIBOMP_OMP_VERSION** = ``50|45|40|30``
OpenMP version to build for. Older versions will disable certain
functionality and entry points.
**LIBOMP_LIB_TYPE** = ``normal|profile|stubs``
Library type can be ``normal``, ``profile``, or ``stubs``.
@@ -192,8 +188,8 @@ Optional Features
multi-node systems where a small ``CACHE_LINE`` setting leads to false sharing.
**LIBOMP_OMPT_SUPPORT** = ``ON|OFF``
Include support for the OpenMP Tools Interface (OMPT).
This option is supported and ``ON`` by default for x86, x86_64, AArch64, and
Include support for the OpenMP Tools Interface (OMPT).
This option is supported and ``ON`` by default for x86, x86_64, AArch64, and
PPC64 on Linux* and macOS*.
This option is ``OFF`` if this feature is not supported for the platform.
+6 -2
View File
@@ -18,8 +18,12 @@ if (NOT OpenMP_Found)
set(OpenMP_CXX_FLAGS "-fopenmp")
endif()
set(C_FLAGS ${flags} ${OpenMP_C_FLAGS})
set(CXX_FLAGS ${flags} ${OpenMP_CXX_FLAGS})
set(CMAKE_THREAD_PREFER_PTHREAD TRUE)
set(THREADS_PREFER_PTHREAD_FLAG TRUE)
find_package(Threads REQUIRED)
set(C_FLAGS "${OpenMP_C_FLAGS} ${CMAKE_THREAD_LIBS_INIT}")
set(CXX_FLAGS "${OpenMP_CXX_FLAGS} ${CMAKE_THREAD_LIBS_INIT}")
# TODO: Implement blockaddress in GlobalISel and remove this flag!
if (CMAKE_C_COMPILER_ID STREQUAL "Clang")
+10 -2
View File
@@ -120,8 +120,16 @@ else()
set(OPENMP_TEST_COMPILER_VERSION "${LLVM_VERSION}")
set(OPENMP_TEST_COMPILER_VERSION_MAJOR "${LLVM_MAJOR_VERSION}")
set(OPENMP_TEST_COMPILER_VERSION_MAJOR_MINOR "${LLVM_MAJOR_VERSION}.${LLVM_MINOR_VERSION}")
# Unfortunately the top-level cmake/config-ix.cmake file mangles CMake's
# CMAKE_THREAD_LIBS_INIT variable from the FindThreads package, so work
# around that, until it is fixed there.
if("${CMAKE_THREAD_LIBS_INIT}" STREQUAL "-lpthread")
set(OPENMP_TEST_COMPILER_THREAD_FLAGS "-pthread")
else()
set(OPENMP_TEST_COMPILER_THREAD_FLAGS "${CMAKE_THREAD_LIBS_INIT}")
endif()
# TODO: Implement blockaddress in GlobalISel and remove this flag!
set(OPENMP_TEST_COMPILER_OPENMP_FLAGS "-fopenmp -fno-experimental-isel")
set(OPENMP_TEST_COMPILER_OPENMP_FLAGS "-fopenmp ${OPENMP_TEST_COMPILER_THREAD_FLAGS} -fno-experimental-isel")
endif()
# Function to set compiler features for use in lit.
@@ -167,7 +175,7 @@ function(add_openmp_testsuite target comment)
add_lit_testsuite(${target}
${comment}
${ARG_UNPARSED_ARGUMENTS}
DEPENDS clang clang-headers FileCheck ${ARG_DEPENDS}
DEPENDS clang clang-resource-headers FileCheck ${ARG_DEPENDS}
ARGS ${ARG_ARGS}
)
endif()
+11 -8
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
@@ -41,13 +40,17 @@ set (LIBOMPTARGET_ALL_TARGETS "${LIBOMPTARGET_ALL_TARGETS} nvptx64-nvidia-cuda")
# the list of supported targets in the current system.
set (LIBOMPTARGET_SYSTEM_TARGETS "")
# If building this library in debug mode, we define a macro to enable
# dumping progress messages at runtime.
# Check whether using debug mode. In debug mode, allow dumping progress
# messages at runtime by default. Otherwise, it can be enabled
# independently using the LIBOMPTARGET_ENABLE_DEBUG option.
string( TOLOWER "${CMAKE_BUILD_TYPE}" LIBOMPTARGET_CMAKE_BUILD_TYPE)
if(LIBOMPTARGET_CMAKE_BUILD_TYPE MATCHES debug)
option(LIBOMPTARGET_ENABLE_DEBUG "Allow debug output with the environment variable LIBOMPTARGET_DEBUG=1" ON)
else()
option(LIBOMPTARGET_ENABLE_DEBUG "Allow debug output with the environment variable LIBOMPTARGET_DEBUG=1" OFF)
endif()
if(LIBOMPTARGET_ENABLE_DEBUG)
add_definitions(-DOMPTARGET_DEBUG)
add_definitions(-g)
add_definitions(-O0)
endif()
include_directories(include)
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
# ##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
//===------ cancel.cu - NVPTX OpenMP cancel interface ------------ CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -1,9 +1,8 @@
//===------ critical.cu - NVPTX OpenMP critical ------------------ CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -1,9 +1,8 @@
//===----- data_sharing.cu - NVPTX OpenMP debug utilities -------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
+3 -4
View File
@@ -1,9 +1,8 @@
//===------------- debug.h - NVPTX OpenMP debug macros ----------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
+11 -43
View File
@@ -1,9 +1,8 @@
//===------- interface.h - NVPTX OpenMP interface definitions ---- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -11,8 +10,7 @@
//
// This file contains all the definitions that are relevant to
// the interface. The first section contains the interface as
// declared by OpenMP. A second section includes library private calls
// (mostly debug, temporary?) The third section includes the compiler
// declared by OpenMP. The second section includes the compiler
// specific interfaces.
//
//===----------------------------------------------------------------------===//
@@ -201,6 +199,7 @@ typedef void (*kmp_CopyToScratchpadFctPtr)(void *reduceData, void *scratchpad,
typedef void (*kmp_LoadReduceFctPtr)(void *reduceData, void *scratchpad,
int32_t index, int32_t width,
int32_t reduce);
typedef void (*kmp_ListGlobalFctPtr)(void *buffer, int idx, void *reduce_data);
// task defs
typedef struct kmp_TaskDescr kmp_TaskDescr;
@@ -211,51 +210,14 @@ typedef struct kmp_TaskDescr {
int32_t partId; // unused
kmp_TaskFctPtr destructors; // destructor of c++ first private
} kmp_TaskDescr;
// task dep defs
#define KMP_TASKDEP_IN 0x1u
#define KMP_TASKDEP_OUT 0x2u
typedef struct kmp_TaskDep_Public {
void *addr;
size_t len;
uint8_t flags; // bit 0: in, bit 1: out
} kmp_TaskDep_Public;
// flags that interpret the interface part of tasking flags
#define KMP_TASK_IS_TIED 0x1
#define KMP_TASK_FINAL 0x2
#define KMP_TASK_MERGED_IF0 0x4 /* unused */
#define KMP_TASK_DESTRUCTOR_THUNK 0x8
// flags for task setup return
#define KMP_CURRENT_TASK_NOT_SUSPENDED 0
#define KMP_CURRENT_TASK_SUSPENDED 1
// sync defs
typedef int32_t kmp_CriticalName[8];
////////////////////////////////////////////////////////////////////////////////
// flags for kstate (all bits initially off)
////////////////////////////////////////////////////////////////////////////////
// first 2 bits used by kmp_Reduction (defined in kmp_reduction.cpp)
#define KMP_REDUCTION_MASK 0x3
#define KMP_SKIP_NEXT_CALL 0x4
#define KMP_SKIP_NEXT_CANCEL_BARRIER 0x8
////////////////////////////////////////////////////////////////////////////////
// data
////////////////////////////////////////////////////////////////////////////////
////////////////////////////////////////////////////////////////////////////////
// external interface
////////////////////////////////////////////////////////////////////////////////
// query
EXTERN int32_t __kmpc_global_num_threads(kmp_Ident *loc); // missing
EXTERN int32_t __kmpc_bound_thread_num(kmp_Ident *loc); // missing
EXTERN int32_t __kmpc_bound_num_threads(kmp_Ident *loc); // missing
EXTERN int32_t __kmpc_in_parallel(kmp_Ident *loc); // missing
// parallel
EXTERN int32_t __kmpc_global_thread_num(kmp_Ident *loc);
EXTERN void __kmpc_push_num_threads(kmp_Ident *loc, int32_t global_tid,
@@ -411,6 +373,12 @@ EXTERN int32_t __kmpc_nvptx_parallel_reduce_nowait_simple_generic(
EXTERN int32_t __kmpc_nvptx_simd_reduce_nowait(
int32_t global_tid, int32_t num_vars, size_t reduce_size, void *reduce_data,
kmp_ShuffleReductFctPtr shflFct, kmp_InterWarpCopyFctPtr cpyFct);
EXTERN int32_t __kmpc_nvptx_teams_reduce_nowait_v2(
kmp_Ident *loc, int32_t global_tid, void *global_buffer,
int32_t num_of_records, void *reduce_data, kmp_ShuffleReductFctPtr shflFct,
kmp_InterWarpCopyFctPtr cpyFct, kmp_ListGlobalFctPtr lgcpyFct,
kmp_ListGlobalFctPtr lgredFct, kmp_ListGlobalFctPtr glcpyFct,
kmp_ListGlobalFctPtr glredFct);
EXTERN int32_t __kmpc_nvptx_teams_reduce_nowait(
int32_t global_tid, int32_t num_vars, size_t reduce_size, void *reduce_data,
kmp_ShuffleReductFctPtr shflFct, kmp_InterWarpCopyFctPtr cpyFct,
+43 -118
View File
@@ -1,9 +1,8 @@
//===------------ libcall.cu - NVPTX OpenMP user calls ----------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -38,51 +37,34 @@ EXTERN void omp_set_num_threads(int num) {
PRINT(LD_IO, "call omp_set_num_threads(num %d)\n", num);
if (num <= 0) {
WARNING0(LW_INPUT, "expected positive num; ignore\n");
} else {
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(/*isSPMDExecutionMode=*/false);
currTaskDescr->NThreads() = num;
} else if (parallelLevel[GetWarpId()] == 0) {
nThreads = num;
}
}
EXTERN int omp_get_num_threads(void) {
bool isSPMDExecutionMode = isSPMDMode();
int tid = GetLogicalThreadIdInBlock(isSPMDExecutionMode);
int rc =
GetNumberOfOmpThreads(tid, isSPMDExecutionMode, isRuntimeUninitialized());
int rc = GetNumberOfOmpThreads(isSPMDMode());
PRINT(LD_IO, "call omp_get_num_threads() return %d\n", rc);
return rc;
}
EXTERN int omp_get_max_threads(void) {
if (isRuntimeUninitialized()) {
ASSERT0(LT_FUSSY, isSPMDMode(),
"Expected SPMD mode only with uninitialized runtime.");
if (parallelLevel[GetWarpId()] > 0)
// We're already in parallel region.
return 1; // default is 1 thread avail
}
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(isSPMDMode());
int rc = 1; // default is 1 thread avail
if (!currTaskDescr->InParallelRegion()) {
// Not currently in a parallel region, return what was set.
rc = currTaskDescr->NThreads();
ASSERT0(LT_FUSSY, rc >= 0, "bad number of threads");
}
return 1; // default is 1 thread avail
// Not currently in a parallel region, return what was set.
int rc = 1;
if (parallelLevel[GetWarpId()] == 0)
rc = nThreads;
ASSERT0(LT_FUSSY, rc >= 0, "bad number of threads");
PRINT(LD_IO, "call omp_get_max_threads() return %d\n", rc);
return rc;
}
EXTERN int omp_get_thread_limit(void) {
if (isRuntimeUninitialized()) {
ASSERT0(LT_FUSSY, isSPMDMode(),
"Expected SPMD mode only with uninitialized runtime.");
return 0; // default is 0
}
// per contention group.. meaning threads in current team
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(isSPMDMode());
int rc = currTaskDescr->ThreadLimit();
if (isSPMDMode())
return GetNumberOfThreadsInBlock();
int rc = threadLimit;
PRINT(LD_IO, "call omp_get_thread_limit() return %d\n", rc);
return rc;
}
@@ -90,7 +72,7 @@ EXTERN int omp_get_thread_limit(void) {
EXTERN int omp_get_thread_num() {
bool isSPMDExecutionMode = isSPMDMode();
int tid = GetLogicalThreadIdInBlock(isSPMDExecutionMode);
int rc = GetOmpThreadId(tid, isSPMDExecutionMode, isRuntimeUninitialized());
int rc = GetOmpThreadId(tid, isSPMDExecutionMode);
PRINT(LD_IO, "call omp_get_thread_num() returns %d\n", rc);
return rc;
}
@@ -102,18 +84,7 @@ EXTERN int omp_get_num_procs(void) {
}
EXTERN int omp_in_parallel(void) {
int rc = 0;
if (isRuntimeUninitialized()) {
ASSERT0(LT_FUSSY, isSPMDMode(),
"Expected SPMD mode only with uninitialized runtime.");
rc = 1; // SPMD mode is always in parallel.
} else {
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(isSPMDMode());
if (currTaskDescr->InParallelRegion()) {
rc = 1;
}
}
int rc = parallelLevel[GetWarpId()] > OMP_ACTIVE_PARALLEL_LEVEL ? 1 : 0;
PRINT(LD_IO, "call omp_in_parallel() returns %d\n", rc);
return rc;
}
@@ -162,63 +133,28 @@ EXTERN int omp_get_max_active_levels(void) {
}
EXTERN int omp_get_level(void) {
if (isRuntimeUninitialized()) {
ASSERT0(LT_FUSSY, isSPMDMode(),
"Expected SPMD mode only with uninitialized runtime.");
return parallelLevel;
}
int level = 0;
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(isSPMDMode());
ASSERT0(LT_FUSSY, currTaskDescr,
"do not expect fct to be called in a non-active thread");
do {
if (currTaskDescr->IsParallelConstruct()) {
level++;
}
currTaskDescr = currTaskDescr->GetPrevTaskDescr();
} while (currTaskDescr);
int level = parallelLevel[GetWarpId()] & (OMP_ACTIVE_PARALLEL_LEVEL - 1);
PRINT(LD_IO, "call omp_get_level() returns %d\n", level);
return level;
}
EXTERN int omp_get_active_level(void) {
if (isRuntimeUninitialized()) {
ASSERT0(LT_FUSSY, isSPMDMode(),
"Expected SPMD mode only with uninitialized runtime.");
return 1;
}
int level = 0; // no active level parallelism
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(isSPMDMode());
ASSERT0(LT_FUSSY, currTaskDescr,
"do not expect fct to be called in a non-active thread");
do {
if (currTaskDescr->ThreadsInTeam() > 1) {
// has a parallel with more than one thread in team
level = 1;
break;
}
currTaskDescr = currTaskDescr->GetPrevTaskDescr();
} while (currTaskDescr);
int level = parallelLevel[GetWarpId()] > OMP_ACTIVE_PARALLEL_LEVEL ? 1 : 0;
PRINT(LD_IO, "call omp_get_active_level() returns %d\n", level)
return level;
}
EXTERN int omp_get_ancestor_thread_num(int level) {
if (isRuntimeUninitialized()) {
ASSERT0(LT_FUSSY, isSPMDMode(),
"Expected SPMD mode only with uninitialized runtime.");
if (isSPMDMode())
return level == 1 ? GetThreadIdInBlock() : 0;
}
int rc = -1;
if (level == 0) {
rc = 0;
} else if (level > 0) {
// If level is 0 or all parallel regions are not active - return 0.
unsigned parLevel = parallelLevel[GetWarpId()];
if (level == 1 && parLevel > OMP_ACTIVE_PARALLEL_LEVEL) {
int totLevel = omp_get_level();
if (level <= totLevel) {
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(isSPMDMode());
getMyTopTaskDescriptor(/*isSPMDExecutionMode=*/false);
int steps = totLevel - level;
PRINT(LD_IO, "backtrack %d steps\n", steps);
ASSERT0(LT_FUSSY, currTaskDescr,
@@ -234,9 +170,8 @@ EXTERN int omp_get_ancestor_thread_num(int level) {
(currTaskDescr->IsParallelConstruct() ? "par" : "task"),
(int)currTaskDescr->InParallelRegion(), (int)sched,
currTaskDescr->RuntimeChunkSize(),
(int)currTaskDescr->ThreadId(),
(int)currTaskDescr->ThreadsInTeam(),
(int)currTaskDescr->NThreads());
(int)currTaskDescr->ThreadId(), (int)threadsInTeam,
(int)nThreads);
}
if (currTaskDescr->IsParallelConstruct()) {
@@ -251,6 +186,12 @@ EXTERN int omp_get_ancestor_thread_num(int level) {
} while (currTaskDescr);
ASSERT0(LT_FUSSY, !steps, "expected to find all steps");
}
} else if (level == 0 ||
(level > 0 && parLevel < OMP_ACTIVE_PARALLEL_LEVEL &&
level <= parLevel) ||
(level > 1 && parLevel > OMP_ACTIVE_PARALLEL_LEVEL &&
level <= (parLevel - OMP_ACTIVE_PARALLEL_LEVEL))) {
rc = 0;
}
PRINT(LD_IO, "call omp_get_ancestor_thread_num(level %d) returns %d\n", level,
rc)
@@ -258,35 +199,19 @@ EXTERN int omp_get_ancestor_thread_num(int level) {
}
EXTERN int omp_get_team_size(int level) {
if (isRuntimeUninitialized()) {
ASSERT0(LT_FUSSY, isSPMDMode(),
"Expected SPMD mode only with uninitialized runtime.");
if (isSPMDMode())
return level == 1 ? GetNumberOfThreadsInBlock() : 1;
}
int rc = -1;
if (level == 0) {
unsigned parLevel = parallelLevel[GetWarpId()];
// If level is 0 or all parallel regions are not active - return 1.
if (level == 1 && parLevel > OMP_ACTIVE_PARALLEL_LEVEL) {
rc = threadsInTeam;
} else if (level == 0 ||
(level > 0 && parLevel < OMP_ACTIVE_PARALLEL_LEVEL &&
level <= parLevel) ||
(level > 1 && parLevel > OMP_ACTIVE_PARALLEL_LEVEL &&
level <= (parLevel - OMP_ACTIVE_PARALLEL_LEVEL))) {
rc = 1;
} else if (level > 0) {
int totLevel = omp_get_level();
if (level <= totLevel) {
omptarget_nvptx_TaskDescr *currTaskDescr =
getMyTopTaskDescriptor(isSPMDMode());
int steps = totLevel - level;
ASSERT0(LT_FUSSY, currTaskDescr,
"do not expect fct to be called in a non-active thread");
do {
if (currTaskDescr->IsParallelConstruct()) {
if (!steps) {
// found the level
rc = currTaskDescr->ThreadsInTeam();
break;
}
steps--;
}
currTaskDescr = currTaskDescr->GetPrevTaskDescr();
} while (currTaskDescr);
ASSERT0(LT_FUSSY, !steps, "expected to find all steps");
}
}
PRINT(LD_IO, "call omp_get_team_size(level %d) returns %d\n", level, rc)
return rc;
+41 -40
View File
@@ -1,9 +1,8 @@
//===------------ loop.cu - NVPTX OpenMP loop constructs --------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -96,17 +95,13 @@ public:
INLINE static void for_static_init(int32_t gtid, int32_t schedtype,
int32_t *plastiter, T *plower, T *pupper,
ST *pstride, ST chunk,
bool IsSPMDExecutionMode,
bool IsRuntimeUninitialized) {
bool IsSPMDExecutionMode) {
// When IsRuntimeUninitialized is true, we assume that the caller is
// in an L0 parallel region and that all worker threads participate.
int tid = GetLogicalThreadIdInBlock(IsSPMDExecutionMode);
// Assume we are in teams region or that we use a single block
// per target region
ST numberOfActiveOMPThreads = GetNumberOfOmpThreads(
tid, IsSPMDExecutionMode, IsRuntimeUninitialized);
ST numberOfActiveOMPThreads = GetNumberOfOmpThreads(IsSPMDExecutionMode);
// All warps that are in excess of the maximum requested, do
// not execute the loop
@@ -206,11 +201,15 @@ public:
INLINE static void dispatch_init(kmp_Ident *loc, int32_t threadId,
kmp_sched_t schedule, T lb, T ub, ST st,
ST chunk) {
ASSERT0(LT_FUSSY, checkRuntimeInitialized(loc),
"Expected non-SPMD mode + initialized runtime.");
if (checkRuntimeUninitialized(loc)) {
// In SPMD mode no need to check parallelism level - dynamic scheduling
// may appear only in L2 parallel regions with lightweight runtime.
ASSERT0(LT_FUSSY, checkSPMDMode(loc), "Expected non-SPMD mode.");
return;
}
int tid = GetLogicalThreadIdInBlock(checkSPMDMode(loc));
omptarget_nvptx_TaskDescr *currTaskDescr = getMyTopTaskDescriptor(tid);
T tnum = currTaskDescr->ThreadsInTeam();
T tnum = GetNumberOfOmpThreads(checkSPMDMode(loc));
T tripCount = ub - lb + 1; // +1 because ub is inclusive
ASSERT0(LT_FUSSY, threadId < tnum,
"current thread is not needed here; error");
@@ -440,15 +439,20 @@ public:
INLINE static int dispatch_next(kmp_Ident *loc, int32_t gtid, int32_t *plast,
T *plower, T *pupper, ST *pstride) {
ASSERT0(LT_FUSSY, checkRuntimeInitialized(loc),
"Expected non-SPMD mode + initialized runtime.");
if (checkRuntimeUninitialized(loc)) {
// In SPMD mode no need to check parallelism level - dynamic scheduling
// may appear only in L2 parallel regions with lightweight runtime.
ASSERT0(LT_FUSSY, checkSPMDMode(loc), "Expected non-SPMD mode.");
if (*plast)
return DISPATCH_FINISHED;
*plast = 1;
return DISPATCH_NOTFINISHED;
}
// ID of a thread in its own warp
// automatically selects thread or warp ID based on selected implementation
int tid = GetLogicalThreadIdInBlock(checkSPMDMode(loc));
ASSERT0(LT_FUSSY,
gtid < GetNumberOfOmpThreads(tid, checkSPMDMode(loc),
checkRuntimeUninitialized(loc)),
ASSERT0(LT_FUSSY, gtid < GetNumberOfOmpThreads(checkSPMDMode(loc)),
"current thread is not needed here; error");
// retrieve schedule
kmp_sched_t schedule =
@@ -499,13 +503,12 @@ public:
*pupper = myUb;
*pstride = 1;
PRINT(
LD_LOOP,
"Got sched: active %d, total %d: lb %lld, ub %lld, stride = %lld, "
"last %d\n",
(int)GetNumberOfOmpThreads(tid, isSPMDMode(), isRuntimeUninitialized()),
(int)GetNumberOfWorkersInTeam(), (long long)*plower, (long long)*pupper,
(long long)*pstride, (int)*plast);
PRINT(LD_LOOP,
"Got sched: active %d, total %d: lb %lld, ub %lld, stride = %lld, "
"last %d\n",
(int)GetNumberOfOmpThreads(isSPMDMode()),
(int)GetNumberOfWorkersInTeam(), (long long)*plower,
(long long)*pupper, (long long)*pstride, (int)*plast);
return DISPATCH_NOTFINISHED;
}
@@ -619,7 +622,7 @@ EXTERN void __kmpc_for_static_init_4(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_4\n");
omptarget_nvptx_LoopSupport<int32_t, int32_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
checkSPMDMode(loc), checkRuntimeUninitialized(loc));
checkSPMDMode(loc));
}
EXTERN void __kmpc_for_static_init_4u(kmp_Ident *loc, int32_t global_tid,
@@ -630,7 +633,7 @@ EXTERN void __kmpc_for_static_init_4u(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_4u\n");
omptarget_nvptx_LoopSupport<uint32_t, int32_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
checkSPMDMode(loc), checkRuntimeUninitialized(loc));
checkSPMDMode(loc));
}
EXTERN void __kmpc_for_static_init_8(kmp_Ident *loc, int32_t global_tid,
@@ -641,7 +644,7 @@ EXTERN void __kmpc_for_static_init_8(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_8\n");
omptarget_nvptx_LoopSupport<int64_t, int64_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
checkSPMDMode(loc), checkRuntimeUninitialized(loc));
checkSPMDMode(loc));
}
EXTERN void __kmpc_for_static_init_8u(kmp_Ident *loc, int32_t global_tid,
@@ -652,7 +655,7 @@ EXTERN void __kmpc_for_static_init_8u(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_8u\n");
omptarget_nvptx_LoopSupport<uint64_t, int64_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
checkSPMDMode(loc), checkRuntimeUninitialized(loc));
checkSPMDMode(loc));
}
EXTERN
@@ -664,7 +667,7 @@ void __kmpc_for_static_init_4_simple_spmd(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_4_simple_spmd\n");
omptarget_nvptx_LoopSupport<int32_t, int32_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/true, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/true);
}
EXTERN
@@ -676,7 +679,7 @@ void __kmpc_for_static_init_4u_simple_spmd(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_4u_simple_spmd\n");
omptarget_nvptx_LoopSupport<uint32_t, int32_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/true, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/true);
}
EXTERN
@@ -688,7 +691,7 @@ void __kmpc_for_static_init_8_simple_spmd(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_8_simple_spmd\n");
omptarget_nvptx_LoopSupport<int64_t, int64_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/true, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/true);
}
EXTERN
@@ -700,7 +703,7 @@ void __kmpc_for_static_init_8u_simple_spmd(kmp_Ident *loc, int32_t global_tid,
PRINT0(LD_IO, "call kmpc_for_static_init_8u_simple_spmd\n");
omptarget_nvptx_LoopSupport<uint64_t, int64_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/true, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/true);
}
EXTERN
@@ -711,7 +714,7 @@ void __kmpc_for_static_init_4_simple_generic(
PRINT0(LD_IO, "call kmpc_for_static_init_4_simple_generic\n");
omptarget_nvptx_LoopSupport<int32_t, int32_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/false, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/false);
}
EXTERN
@@ -722,7 +725,7 @@ void __kmpc_for_static_init_4u_simple_generic(
PRINT0(LD_IO, "call kmpc_for_static_init_4u_simple_generic\n");
omptarget_nvptx_LoopSupport<uint32_t, int32_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/false, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/false);
}
EXTERN
@@ -733,7 +736,7 @@ void __kmpc_for_static_init_8_simple_generic(
PRINT0(LD_IO, "call kmpc_for_static_init_8_simple_generic\n");
omptarget_nvptx_LoopSupport<int64_t, int64_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/false, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/false);
}
EXTERN
@@ -744,7 +747,7 @@ void __kmpc_for_static_init_8u_simple_generic(
PRINT0(LD_IO, "call kmpc_for_static_init_8u_simple_generic\n");
omptarget_nvptx_LoopSupport<uint64_t, int64_t>::for_static_init(
global_tid, schedtype, plastiter, plower, pupper, pstride, chunk,
/*IsSPMDExecutionMode=*/false, /*IsRuntimeUninitialized=*/true);
/*IsSPMDExecutionMode=*/false);
}
EXTERN void __kmpc_for_static_fini(kmp_Ident *loc, int32_t global_tid) {
@@ -776,9 +779,7 @@ EXTERN void __kmpc_reduce_conditional_lastprivate(kmp_Ident *loc, int32_t gtid,
"Expected non-SPMD mode + initialized runtime.");
omptarget_nvptx_TeamDescr &teamDescr = getMyTeamDescriptor();
int tid = GetLogicalThreadIdInBlock(checkSPMDMode(loc));
uint32_t NumThreads = GetNumberOfOmpThreads(tid, checkSPMDMode(loc),
checkRuntimeUninitialized(loc));
uint32_t NumThreads = GetNumberOfOmpThreads(checkSPMDMode(loc));
uint64_t *Buffer = teamDescr.getLastprivateIterBuffer();
for (unsigned i = 0; i < varNum; i++) {
// Reset buffer.
@@ -1,9 +1,8 @@
//===------------ omp_data.cu - NVPTX OpenMP GPU objects --------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -32,8 +31,10 @@ __device__ omptarget_nvptx_SimpleMemoryManager
__device__ __shared__ uint32_t usedMemIdx;
__device__ __shared__ uint32_t usedSlotIdx;
__device__ __shared__ uint8_t parallelLevel;
__device__ __shared__ uint8_t parallelLevel[MAX_THREADS_PER_TEAM / WARPSIZE];
__device__ __shared__ uint16_t threadLimit;
__device__ __shared__ uint16_t threadsInTeam;
__device__ __shared__ uint16_t nThreads;
// Pointer to this team's OpenMP state object
__device__ __shared__
omptarget_nvptx_ThreadPrivateContext *omptarget_nvptx_threadPrivateContext;
@@ -1,9 +1,8 @@
//===--- omptarget-nvptx.cu - NVPTX OpenMP GPU initialization ---- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -44,6 +43,8 @@ EXTERN void __kmpc_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime) {
ASSERT0(LT_FUSSY, RequiresOMPRuntime,
"Generic always requires initialized runtime.");
setExecutionParameters(Generic, RuntimeInitialized);
for (int I = 0; I < MAX_THREADS_PER_TEAM / WARPSIZE; ++I)
parallelLevel[I] = 0;
int threadIdInBlock = GetThreadIdInBlock();
ASSERT0(LT_FUSSY, threadIdInBlock == GetMasterThreadID(),
@@ -62,7 +63,7 @@ EXTERN void __kmpc_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime) {
// init team context
omptarget_nvptx_TeamDescr &currTeamDescr = getMyTeamDescriptor();
currTeamDescr.InitTeamDescr(/*isSPMDExecutionMode=*/false);
currTeamDescr.InitTeamDescr();
// this thread will start execution... has to update its task ICV
// to point to the level zero task ICV. That ICV was init in
// InitTeamDescr()
@@ -72,8 +73,8 @@ EXTERN void __kmpc_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime) {
// set number of threads and thread limit in team to started value
omptarget_nvptx_TaskDescr *currTaskDescr =
omptarget_nvptx_threadPrivateContext->GetTopLevelTaskDescr(threadId);
currTaskDescr->NThreads() = GetNumberOfWorkersInTeam();
currTaskDescr->ThreadLimit() = ThreadLimit;
nThreads = GetNumberOfWorkersInTeam();
threadLimit = ThreadLimit;
}
EXTERN void __kmpc_kernel_deinit(int16_t IsOMPRuntimeInitialized) {
@@ -92,35 +93,37 @@ EXTERN void __kmpc_spmd_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime,
int16_t RequiresDataSharing) {
PRINT0(LD_IO, "call to __kmpc_spmd_kernel_init\n");
setExecutionParameters(Spmd, RequiresOMPRuntime ? RuntimeInitialized
: RuntimeUninitialized);
int threadId = GetThreadIdInBlock();
if (threadId == 0) {
usedSlotIdx = smid() % MAX_SM;
parallelLevel[0] =
1 + (GetNumberOfThreadsInBlock() > 1 ? OMP_ACTIVE_PARALLEL_LEVEL : 0);
} else if (GetLaneId() == 0) {
parallelLevel[GetWarpId()] =
1 + (GetNumberOfThreadsInBlock() > 1 ? OMP_ACTIVE_PARALLEL_LEVEL : 0);
}
if (!RequiresOMPRuntime) {
// If OMP runtime is not required don't initialize OMP state.
setExecutionParameters(Spmd, RuntimeUninitialized);
if (GetThreadIdInBlock() == 0) {
parallelLevel = 0;
usedSlotIdx = smid() % MAX_SM;
}
// Runtime is not required - exit.
__SYNCTHREADS();
return;
}
setExecutionParameters(Spmd, RuntimeInitialized);
//
// Team Context Initialization.
//
// In SPMD mode there is no master thread so use any cuda thread for team
// context initialization.
int threadId = GetThreadIdInBlock();
if (threadId == 0) {
// Get a state object from the queue.
int slot = smid() % MAX_SM;
usedSlotIdx = slot;
omptarget_nvptx_threadPrivateContext =
omptarget_nvptx_device_State[slot].Dequeue();
omptarget_nvptx_device_State[usedSlotIdx].Dequeue();
omptarget_nvptx_TeamDescr &currTeamDescr = getMyTeamDescriptor();
omptarget_nvptx_WorkDescr &workDescr = getMyWorkDescriptor();
// init team context
currTeamDescr.InitTeamDescr(/*isSPMDExecutionMode=*/true);
currTeamDescr.InitTeamDescr();
}
// FIXME: use __syncthreads instead when the function copy is fixed in LLVM.
__SYNCTHREADS();
@@ -134,9 +137,7 @@ EXTERN void __kmpc_spmd_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime,
omptarget_nvptx_TaskDescr *newTaskDescr =
omptarget_nvptx_threadPrivateContext->Level1TaskDescr(threadId);
ASSERT0(LT_FUSSY, newTaskDescr, "expected a task descr");
newTaskDescr->InitLevelOneTaskDescr(ThreadLimit,
currTeamDescr.LevelZeroTaskDescr());
newTaskDescr->ThreadLimit() = ThreadLimit;
newTaskDescr->InitLevelOneTaskDescr(currTeamDescr.LevelZeroTaskDescr());
// install new top descriptor
omptarget_nvptx_threadPrivateContext->SetTopLevelTaskDescr(threadId,
newTaskDescr);
@@ -145,9 +146,9 @@ EXTERN void __kmpc_spmd_kernel_init(int ThreadLimit, int16_t RequiresOMPRuntime,
PRINT(LD_PAR,
"thread will execute parallel region with id %d in a team of "
"%d threads\n",
(int)newTaskDescr->ThreadId(), (int)newTaskDescr->ThreadsInTeam());
(int)newTaskDescr->ThreadId(), (int)ThreadLimit);
if (RequiresDataSharing && threadId % WARPSIZE == 0) {
if (RequiresDataSharing && GetLaneId() == 0) {
// Warp master innitializes data sharing environment.
unsigned WID = threadId / WARPSIZE;
__kmpc_data_sharing_slot *RootS = currTeamDescr.RootS(
@@ -1,9 +1,8 @@
//===---- omptarget-nvptx.h - NVPTX OpenMP GPU initialization ---- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -49,7 +48,9 @@
// Macros for Cuda intrinsics
// In Cuda 9.0, the *_sync() version takes an extra argument 'mask'.
// Also, __ballot(1) in Cuda 8.0 is replaced with __activemask().
#if defined(CUDART_VERSION) && CUDART_VERSION >= 9000
#ifndef CUDA_VERSION
#error CUDA_VERSION macro is undefined, something wrong with cuda.
#elif CUDA_VERSION >= 9000
#define __SHFL_SYNC(mask, var, srcLane) __shfl_sync((mask), (var), (srcLane))
#define __SHFL_DOWN_SYNC(mask, var, delta, width) \
__shfl_down_sync((mask), (var), (delta), (width))
@@ -59,10 +60,15 @@
#define __SHFL_DOWN_SYNC(mask, var, delta, width) \
__shfl_down((var), (delta), (width))
#define __ACTIVEMASK() __ballot(1)
#endif
#endif // CUDA_VERSION
#define __SYNCTHREADS_N(n) asm volatile("bar.sync %0;" : : "r"(n) : "memory");
// Use original __syncthreads if compiled by nvcc or clang >= 9.0.
#if !defined(__clang__) || __clang_major__ >= 9
#define __SYNCTHREADS() __syncthreads()
#else
#define __SYNCTHREADS() __SYNCTHREADS_N(0)
#endif
// arguments needed for L0 parallelism only.
class omptarget_nvptx_SharedArgs {
@@ -165,25 +171,20 @@ public:
}
INLINE int IsTaskConstruct() const { return !IsParallelConstruct(); }
// methods for other fields
INLINE uint16_t &NThreads() { return items.nthreads; }
INLINE uint16_t &ThreadLimit() { return items.threadlimit; }
INLINE uint16_t &ThreadId() { return items.threadId; }
INLINE uint16_t &ThreadsInTeam() { return items.threadsInTeam; }
INLINE uint64_t &RuntimeChunkSize() { return items.runtimeChunkSize; }
INLINE omptarget_nvptx_TaskDescr *GetPrevTaskDescr() const { return prev; }
INLINE void SetPrevTaskDescr(omptarget_nvptx_TaskDescr *taskDescr) {
prev = taskDescr;
}
// init & copy
INLINE void InitLevelZeroTaskDescr(bool isSPMDExecutionMode);
INLINE void InitLevelOneTaskDescr(uint16_t tnum,
omptarget_nvptx_TaskDescr *parentTaskDescr);
INLINE void InitLevelZeroTaskDescr();
INLINE void InitLevelOneTaskDescr(omptarget_nvptx_TaskDescr *parentTaskDescr);
INLINE void Copy(omptarget_nvptx_TaskDescr *sourceTaskDescr);
INLINE void CopyData(omptarget_nvptx_TaskDescr *sourceTaskDescr);
INLINE void CopyParent(omptarget_nvptx_TaskDescr *parentTaskDescr);
INLINE void CopyForExplicitTask(omptarget_nvptx_TaskDescr *parentTaskDescr);
INLINE void CopyToWorkDescr(omptarget_nvptx_TaskDescr *masterTaskDescr,
uint16_t tnum);
INLINE void CopyToWorkDescr(omptarget_nvptx_TaskDescr *masterTaskDescr);
INLINE void CopyFromWorkDescr(omptarget_nvptx_TaskDescr *workTaskDescr);
INLINE void CopyConvergentParent(omptarget_nvptx_TaskDescr *parentTaskDescr,
uint16_t tid, uint16_t tnum);
@@ -213,10 +214,7 @@ private:
struct TaskDescr_items {
uint8_t flags; // 6 bit used (see flag above)
uint8_t unused;
uint16_t nthreads; // thread num for subsequent parallel regions
uint16_t threadlimit; // thread limit ICV
uint16_t threadId; // thread id
uint16_t threadsInTeam; // threads in current team
uint64_t runtimeChunkSize; // runtime chunk size
} items;
omptarget_nvptx_TaskDescr *prev;
@@ -256,7 +254,7 @@ public:
INLINE uint64_t *getLastprivateIterBuffer() { return &lastprivateIterBuffer; }
// init
INLINE void InitTeamDescr(bool isSPMDExecutionMode);
INLINE void InitTeamDescr();
INLINE __kmpc_data_sharing_slot *RootS(int wid, bool IsMasterThread) {
// If this is invoked by the master thread of the master warp then intialize
@@ -407,7 +405,11 @@ extern __device__ omptarget_nvptx_SimpleMemoryManager
omptarget_nvptx_simpleMemoryManager;
extern __device__ __shared__ uint32_t usedMemIdx;
extern __device__ __shared__ uint32_t usedSlotIdx;
extern __device__ __shared__ uint8_t parallelLevel;
extern __device__ __shared__ uint8_t
parallelLevel[MAX_THREADS_PER_TEAM / WARPSIZE];
extern __device__ __shared__ uint16_t threadLimit;
extern __device__ __shared__ uint16_t threadsInTeam;
extern __device__ __shared__ uint16_t nThreads;
extern __device__ __shared__
omptarget_nvptx_ThreadPrivateContext *omptarget_nvptx_threadPrivateContext;
@@ -1,9 +1,8 @@
//===---- omptarget-nvptxi.h - NVPTX OpenMP GPU initialization --- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -32,7 +31,7 @@ INLINE void omptarget_nvptx_TaskDescr::SetRuntimeSched(omp_sched_t sched) {
}
INLINE void
omptarget_nvptx_TaskDescr::InitLevelZeroTaskDescr(bool isSPMDExecutionMode) {
omptarget_nvptx_TaskDescr::InitLevelZeroTaskDescr() {
// slow method
// flag:
// default sched is static,
@@ -40,17 +39,14 @@ omptarget_nvptx_TaskDescr::InitLevelZeroTaskDescr(bool isSPMDExecutionMode) {
// not in parallel
items.flags = 0;
items.nthreads = GetNumberOfProcsInTeam(isSPMDExecutionMode);
; // threads: whatever was alloc by kernel
items.threadId = 0; // is master
items.threadsInTeam = 1; // sequential
items.runtimeChunkSize = 1; // prefered chunking statik with chunk 1
}
// This is called when all threads are started together in SPMD mode.
// OMP directives include target parallel, target distribute parallel for, etc.
INLINE void omptarget_nvptx_TaskDescr::InitLevelOneTaskDescr(
uint16_t tnum, omptarget_nvptx_TaskDescr *parentTaskDescr) {
omptarget_nvptx_TaskDescr *parentTaskDescr) {
// slow method
// flag:
// default sched is static,
@@ -59,10 +55,8 @@ INLINE void omptarget_nvptx_TaskDescr::InitLevelOneTaskDescr(
items.flags =
TaskDescr_InPar | TaskDescr_IsParConstr; // set flag to parallel
items.nthreads = 0; // # threads for subsequent parallel region
items.threadId =
GetThreadIdInBlock(); // get ids from cuda (only called for 1st level)
items.threadsInTeam = tnum;
items.runtimeChunkSize = 1; // prefered chunking statik with chunk 1
prev = parentTaskDescr;
}
@@ -92,12 +86,11 @@ INLINE void omptarget_nvptx_TaskDescr::CopyForExplicitTask(
}
INLINE void omptarget_nvptx_TaskDescr::CopyToWorkDescr(
omptarget_nvptx_TaskDescr *masterTaskDescr, uint16_t tnum) {
omptarget_nvptx_TaskDescr *masterTaskDescr) {
CopyParent(masterTaskDescr);
// overrwrite specific items;
items.flags |=
TaskDescr_InPar | TaskDescr_IsParConstr; // set flag to parallel
items.threadsInTeam = tnum; // set number of threads
}
INLINE void omptarget_nvptx_TaskDescr::CopyFromWorkDescr(
@@ -122,7 +115,6 @@ INLINE void omptarget_nvptx_TaskDescr::CopyConvergentParent(
omptarget_nvptx_TaskDescr *parentTaskDescr, uint16_t tid, uint16_t tnum) {
CopyParent(parentTaskDescr);
items.flags |= TaskDescr_InParL2P; // In L2+ parallelism
items.threadsInTeam = tnum; // set number of threads
items.threadId = tid;
}
@@ -178,8 +170,8 @@ omptarget_nvptx_ThreadPrivateContext::InitThreadPrivateContext(int tid) {
// Team Descriptor
////////////////////////////////////////////////////////////////////////////////
INLINE void omptarget_nvptx_TeamDescr::InitTeamDescr(bool isSPMDExecutionMode) {
levelZeroTaskDescr.InitLevelZeroTaskDescr(isSPMDExecutionMode);
INLINE void omptarget_nvptx_TeamDescr::InitTeamDescr() {
levelZeroTaskDescr.InitLevelZeroTaskDescr();
}
////////////////////////////////////////////////////////////////////////////////
+5 -4
View File
@@ -1,9 +1,8 @@
//===------------ option.h - NVPTX OpenMP GPU options ------------ CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -45,6 +44,8 @@
#define MAX_SM 16
#endif
#define OMP_ACTIVE_PARALLEL_LEVEL 128
////////////////////////////////////////////////////////////////////////////////
// algo options
////////////////////////////////////////////////////////////////////////////////
+17 -36
View File
@@ -1,9 +1,8 @@
//===---- parallel.cu - NVPTX OpenMP parallel implementation ----- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -251,8 +250,7 @@ EXTERN void __kmpc_kernel_prepare_parallel(void *WorkFn,
omptarget_nvptx_threadPrivateContext->NumThreadsForNextParallel(threadId);
uint16_t NumThreads =
determineNumberOfThreads(NumThreadsClause, currTaskDescr->NThreads(),
currTaskDescr->ThreadLimit());
determineNumberOfThreads(NumThreadsClause, nThreads, threadLimit);
if (NumThreadsClause != 0) {
// Reset request to avoid propagating to successive #parallel
@@ -266,7 +264,8 @@ EXTERN void __kmpc_kernel_prepare_parallel(void *WorkFn,
// Set number of threads on work descriptor.
omptarget_nvptx_WorkDescr &workDescr = getMyWorkDescriptor();
workDescr.WorkTaskDescr()->CopyToWorkDescr(currTaskDescr, NumThreads);
workDescr.WorkTaskDescr()->CopyToWorkDescr(currTaskDescr);
threadsInTeam = NumThreads;
}
// All workers call this function. Deactivate those not needed.
@@ -296,7 +295,7 @@ EXTERN bool __kmpc_kernel_parallel(void **WorkFn,
// Set to true for workers participating in the parallel region.
bool isActive = false;
// Initialize state for active threads.
if (threadId < workDescr.WorkTaskDescr()->ThreadsInTeam()) {
if (threadId < threadsInTeam) {
// init work descriptor from workdesccr
omptarget_nvptx_TaskDescr *newTaskDescr =
omptarget_nvptx_threadPrivateContext->Level1TaskDescr(threadId);
@@ -309,9 +308,10 @@ EXTERN bool __kmpc_kernel_parallel(void **WorkFn,
PRINT(LD_PAR,
"thread will execute parallel region with id %d in a team of "
"%d threads\n",
(int)newTaskDescr->ThreadId(), (int)newTaskDescr->NThreads());
(int)newTaskDescr->ThreadId(), (int)nThreads);
isActive = true;
IncParallelLevel(threadsInTeam != 1);
}
return isActive;
@@ -328,6 +328,8 @@ EXTERN void __kmpc_kernel_end_parallel() {
omptarget_nvptx_TaskDescr *currTaskDescr = getMyTopTaskDescriptor(threadId);
omptarget_nvptx_threadPrivateContext->SetTopLevelTaskDescr(
threadId, currTaskDescr->GetPrevTaskDescr());
DecParallelLevel(threadsInTeam != 1);
}
////////////////////////////////////////////////////////////////////////////////
@@ -337,14 +339,11 @@ EXTERN void __kmpc_kernel_end_parallel() {
EXTERN void __kmpc_serialized_parallel(kmp_Ident *loc, uint32_t global_tid) {
PRINT0(LD_IO, "call to __kmpc_serialized_parallel\n");
IncParallelLevel(/*ActiveParallel=*/false);
if (checkRuntimeUninitialized(loc)) {
ASSERT0(LT_FUSSY, checkSPMDMode(loc),
"Expected SPMD mode with uninitialized runtime.");
__SYNCTHREADS();
if (GetThreadIdInBlock() == 0)
++parallelLevel;
__SYNCTHREADS();
return;
}
@@ -369,7 +368,6 @@ EXTERN void __kmpc_serialized_parallel(kmp_Ident *loc, uint32_t global_tid) {
// - each thread becomes ID 0 in its serialized parallel, and
// - there is only one thread per team
newTaskDescr->ThreadId() = 0;
newTaskDescr->ThreadsInTeam() = 1;
// set new task descriptor as top
omptarget_nvptx_threadPrivateContext->SetTopLevelTaskDescr(threadId,
@@ -380,13 +378,11 @@ EXTERN void __kmpc_end_serialized_parallel(kmp_Ident *loc,
uint32_t global_tid) {
PRINT0(LD_IO, "call to __kmpc_end_serialized_parallel\n");
DecParallelLevel(/*ActiveParallel=*/false);
if (checkRuntimeUninitialized(loc)) {
ASSERT0(LT_FUSSY, checkSPMDMode(loc),
"Expected SPMD mode with uninitialized runtime.");
__SYNCTHREADS();
if (GetThreadIdInBlock() == 0)
--parallelLevel;
__SYNCTHREADS();
return;
}
@@ -405,21 +401,7 @@ EXTERN void __kmpc_end_serialized_parallel(kmp_Ident *loc,
EXTERN uint16_t __kmpc_parallel_level(kmp_Ident *loc, uint32_t global_tid) {
PRINT0(LD_IO, "call to __kmpc_parallel_level\n");
if (checkRuntimeUninitialized(loc)) {
ASSERT0(LT_FUSSY, checkSPMDMode(loc),
"Expected SPMD mode with uninitialized runtime.");
return parallelLevel;
}
int threadId = GetLogicalThreadIdInBlock(checkSPMDMode(loc));
omptarget_nvptx_TaskDescr *currTaskDescr =
omptarget_nvptx_threadPrivateContext->GetTopLevelTaskDescr(threadId);
if (currTaskDescr->InL2OrHigherParallelRegion())
return 2;
else if (currTaskDescr->InParallelRegion())
return 1;
else
return 0;
return parallelLevel[GetWarpId()] & (OMP_ACTIVE_PARALLEL_LEVEL - 1);
}
// This kmpc call returns the thread id across all teams. It's value is
@@ -428,8 +410,7 @@ EXTERN uint16_t __kmpc_parallel_level(kmp_Ident *loc, uint32_t global_tid) {
// of this call.
EXTERN int32_t __kmpc_global_thread_num(kmp_Ident *loc) {
int tid = GetLogicalThreadIdInBlock(checkSPMDMode(loc));
return GetOmpThreadId(tid, checkSPMDMode(loc),
checkRuntimeUninitialized(loc));
return GetOmpThreadId(tid, checkSPMDMode(loc));
}
////////////////////////////////////////////////////////////////////////////////
+166 -87
View File
@@ -1,10 +1,9 @@
//===---- reduction.cu - NVPTX OpenMP reduction implementation ---- CUDA
//-*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -17,56 +16,6 @@
#include "omptarget-nvptx.h"
// may eventually remove this
EXTERN
int32_t __gpu_block_reduce() {
bool isSPMDExecutionMode = isSPMDMode();
int tid = GetLogicalThreadIdInBlock(isSPMDExecutionMode);
int nt =
GetNumberOfOmpThreads(tid, isSPMDExecutionMode, isRuntimeUninitialized());
if (nt != blockDim.x)
return 0;
unsigned tnum = __ACTIVEMASK();
if (tnum != (~0x0)) // assume swapSize is 32
return 0;
return 1;
}
EXTERN
int32_t __kmpc_reduce_gpu(kmp_Ident *loc, int32_t global_tid, int32_t num_vars,
size_t reduce_size, void *reduce_data,
void *reduce_array_size, kmp_ReductFctPtr *reductFct,
kmp_CriticalName *lck) {
int threadId = GetLogicalThreadIdInBlock(checkSPMDMode(loc));
omptarget_nvptx_TaskDescr *currTaskDescr = getMyTopTaskDescriptor(threadId);
int numthread;
if (currTaskDescr->IsParallelConstruct()) {
numthread =
GetNumberOfOmpThreads(threadId, checkSPMDMode(loc),
checkRuntimeUninitialized(loc));
} else {
numthread = GetNumberOfOmpTeams();
}
if (numthread == 1)
return 1;
if (!__gpu_block_reduce())
return 2;
if (threadIdx.x == 0)
return 1;
return 0;
}
EXTERN
int32_t __kmpc_reduce_combined(kmp_Ident *loc) {
return threadIdx.x == 0 ? 2 : 0;
}
EXTERN
int32_t __kmpc_reduce_simd(kmp_Ident *loc) {
return (threadIdx.x % 32 == 0) ? 1 : 0;
}
EXTERN
void __kmpc_nvptx_end_reduce(int32_t global_tid) {}
@@ -151,8 +100,7 @@ static int32_t nvptx_parallel_reduce_nowait(
kmp_ShuffleReductFctPtr shflFct, kmp_InterWarpCopyFctPtr cpyFct,
bool isSPMDExecutionMode, bool isRuntimeUninitialized) {
uint32_t BlockThreadId = GetLogicalThreadIdInBlock(isSPMDExecutionMode);
uint32_t NumThreads = GetNumberOfOmpThreads(
BlockThreadId, isSPMDExecutionMode, isRuntimeUninitialized);
uint32_t NumThreads = GetNumberOfOmpThreads(isSPMDExecutionMode);
if (NumThreads == 1)
return 1;
/*
@@ -237,10 +185,9 @@ static int32_t nvptx_parallel_reduce_nowait(
EXTERN __attribute__((deprecated)) int32_t __kmpc_nvptx_parallel_reduce_nowait(
int32_t global_tid, int32_t num_vars, size_t reduce_size, void *reduce_data,
kmp_ShuffleReductFctPtr shflFct, kmp_InterWarpCopyFctPtr cpyFct) {
return nvptx_parallel_reduce_nowait(
global_tid, num_vars, reduce_size, reduce_data, shflFct, cpyFct,
/*isSPMDExecutionMode=*/isSPMDMode(),
/*isRuntimeUninitialized=*/isRuntimeUninitialized());
return nvptx_parallel_reduce_nowait(global_tid, num_vars, reduce_size,
reduce_data, shflFct, cpyFct,
isSPMDMode(), isRuntimeUninitialized());
}
EXTERN
@@ -257,37 +204,35 @@ EXTERN
int32_t __kmpc_nvptx_parallel_reduce_nowait_simple_spmd(
int32_t global_tid, int32_t num_vars, size_t reduce_size, void *reduce_data,
kmp_ShuffleReductFctPtr shflFct, kmp_InterWarpCopyFctPtr cpyFct) {
return nvptx_parallel_reduce_nowait(global_tid, num_vars, reduce_size,
reduce_data, shflFct, cpyFct,
/*isSPMDExecutionMode=*/true,
/*isRuntimeUninitialized=*/true);
return nvptx_parallel_reduce_nowait(
global_tid, num_vars, reduce_size, reduce_data, shflFct, cpyFct,
/*isSPMDExecutionMode=*/true, /*isRuntimeUninitialized=*/true);
}
EXTERN
int32_t __kmpc_nvptx_parallel_reduce_nowait_simple_generic(
int32_t global_tid, int32_t num_vars, size_t reduce_size, void *reduce_data,
kmp_ShuffleReductFctPtr shflFct, kmp_InterWarpCopyFctPtr cpyFct) {
return nvptx_parallel_reduce_nowait(global_tid, num_vars, reduce_size,
reduce_data, shflFct, cpyFct,
/*isSPMDExecutionMode=*/false,
/*isRuntimeUninitialized=*/true);
return nvptx_parallel_reduce_nowait(
global_tid, num_vars, reduce_size, reduce_data, shflFct, cpyFct,
/*isSPMDExecutionMode=*/false, /*isRuntimeUninitialized=*/true);
}
INLINE
static int32_t nvptx_teams_reduce_nowait(
int32_t global_tid, int32_t num_vars, size_t reduce_size, void *reduce_data,
kmp_ShuffleReductFctPtr shflFct, kmp_InterWarpCopyFctPtr cpyFct,
kmp_CopyToScratchpadFctPtr scratchFct, kmp_LoadReduceFctPtr ldFct,
bool isSPMDExecutionMode, bool isRuntimeUninitialized) {
static int32_t nvptx_teams_reduce_nowait(int32_t global_tid, int32_t num_vars,
size_t reduce_size, void *reduce_data,
kmp_ShuffleReductFctPtr shflFct,
kmp_InterWarpCopyFctPtr cpyFct,
kmp_CopyToScratchpadFctPtr scratchFct,
kmp_LoadReduceFctPtr ldFct,
bool isSPMDExecutionMode) {
uint32_t ThreadId = GetLogicalThreadIdInBlock(isSPMDExecutionMode);
// In non-generic mode all workers participate in the teams reduction.
// In generic mode only the team master participates in the teams
// reduction because the workers are waiting for parallel work.
uint32_t NumThreads =
isSPMDExecutionMode
? GetNumberOfOmpThreads(ThreadId, /*isSPMDExecutionMode=*/true,
isRuntimeUninitialized)
: /*Master thread only*/ 1;
isSPMDExecutionMode ? GetNumberOfOmpThreads(/*isSPMDExecutionMode=*/true)
: /*Master thread only*/ 1;
uint32_t TeamId = GetBlockIdInKernel();
uint32_t NumTeams = GetNumberOfBlocksInKernel();
__shared__ volatile bool IsLastTeam;
@@ -407,10 +352,9 @@ int32_t __kmpc_nvptx_teams_reduce_nowait(int32_t global_tid, int32_t num_vars,
kmp_InterWarpCopyFctPtr cpyFct,
kmp_CopyToScratchpadFctPtr scratchFct,
kmp_LoadReduceFctPtr ldFct) {
return nvptx_teams_reduce_nowait(
global_tid, num_vars, reduce_size, reduce_data, shflFct, cpyFct,
scratchFct, ldFct, /*isSPMDExecutionMode=*/isSPMDMode(),
/*isRuntimeUninitialized=*/isRuntimeUninitialized());
return nvptx_teams_reduce_nowait(global_tid, num_vars, reduce_size,
reduce_data, shflFct, cpyFct, scratchFct,
ldFct, isSPMDMode());
}
EXTERN
@@ -420,9 +364,7 @@ int32_t __kmpc_nvptx_teams_reduce_nowait_simple_spmd(
kmp_CopyToScratchpadFctPtr scratchFct, kmp_LoadReduceFctPtr ldFct) {
return nvptx_teams_reduce_nowait(global_tid, num_vars, reduce_size,
reduce_data, shflFct, cpyFct, scratchFct,
ldFct,
/*isSPMDExecutionMode=*/true,
/*isRuntimeUninitialized=*/true);
ldFct, /*isSPMDExecutionMode=*/true);
}
EXTERN
@@ -432,9 +374,7 @@ int32_t __kmpc_nvptx_teams_reduce_nowait_simple_generic(
kmp_CopyToScratchpadFctPtr scratchFct, kmp_LoadReduceFctPtr ldFct) {
return nvptx_teams_reduce_nowait(global_tid, num_vars, reduce_size,
reduce_data, shflFct, cpyFct, scratchFct,
ldFct,
/*isSPMDExecutionMode=*/false,
/*isRuntimeUninitialized=*/true);
ldFct, /*isSPMDExecutionMode=*/false);
}
EXTERN int32_t __kmpc_nvptx_teams_reduce_nowait_simple(kmp_Ident *loc,
@@ -455,3 +395,142 @@ __kmpc_nvptx_teams_end_reduce_nowait_simple(kmp_Ident *loc, int32_t global_tid,
(void)atomicExch((uint32_t *)crit, 0);
}
INLINE static bool isMaster(kmp_Ident *loc, uint32_t ThreadId) {
return checkGenericMode(loc) || IsTeamMaster(ThreadId);
}
INLINE static uint32_t roundToWarpsize(uint32_t s) {
if (s < WARPSIZE)
return 1;
return (s & ~(unsigned)(WARPSIZE - 1));
}
__device__ static volatile uint32_t IterCnt = 0;
__device__ static volatile uint32_t Cnt = 0;
EXTERN int32_t __kmpc_nvptx_teams_reduce_nowait_v2(
kmp_Ident *loc, int32_t global_tid, void *global_buffer,
int32_t num_of_records, void *reduce_data, kmp_ShuffleReductFctPtr shflFct,
kmp_InterWarpCopyFctPtr cpyFct, kmp_ListGlobalFctPtr lgcpyFct,
kmp_ListGlobalFctPtr lgredFct, kmp_ListGlobalFctPtr glcpyFct,
kmp_ListGlobalFctPtr glredFct) {
// Terminate all threads in non-SPMD mode except for the master thread.
if (checkGenericMode(loc) && GetThreadIdInBlock() != GetMasterThreadID())
return 0;
uint32_t ThreadId = GetLogicalThreadIdInBlock(checkSPMDMode(loc));
// In non-generic mode all workers participate in the teams reduction.
// In generic mode only the team master participates in the teams
// reduction because the workers are waiting for parallel work.
uint32_t NumThreads =
checkSPMDMode(loc) ? GetNumberOfOmpThreads(/*isSPMDExecutionMode=*/true)
: /*Master thread only*/ 1;
uint32_t TeamId = GetBlockIdInKernel();
uint32_t NumTeams = GetNumberOfBlocksInKernel();
__shared__ unsigned Bound;
__shared__ unsigned ChunkTeamCount;
// Block progress for teams greater than the current upper
// limit. We always only allow a number of teams less or equal
// to the number of slots in the buffer.
bool IsMaster = isMaster(loc, ThreadId);
while (IsMaster) {
// Atomic read
Bound = atomicAdd((uint32_t *)&IterCnt, 0);
if (TeamId < Bound + num_of_records)
break;
}
if (IsMaster) {
int ModBockId = TeamId % num_of_records;
if (TeamId < num_of_records)
lgcpyFct(global_buffer, ModBockId, reduce_data);
else
lgredFct(global_buffer, ModBockId, reduce_data);
__threadfence_system();
// Increment team counter.
// This counter is incremented by all teams in the current
// BUFFER_SIZE chunk.
ChunkTeamCount = atomicInc((uint32_t *)&Cnt, num_of_records - 1);
}
// Synchronize
if (checkSPMDMode(loc))
__kmpc_barrier(loc, global_tid);
// reduce_data is global or shared so before being reduced within the
// warp we need to bring it in local memory:
// local_reduce_data = reduce_data[i]
//
// Example for 3 reduction variables a, b, c (of potentially different
// types):
//
// buffer layout (struct of arrays):
// a, a, ..., a, b, b, ... b, c, c, ... c
// |__________|
// num_of_records
//
// local_data_reduce layout (struct):
// a, b, c
//
// Each thread will have a local struct containing the values to be
// reduced:
// 1. do reduction within each warp.
// 2. do reduction across warps.
// 3. write the final result to the main reduction variable
// by returning 1 in the thread holding the reduction result.
// Check if this is the very last team.
unsigned NumRecs = min(NumTeams, num_of_records);
if (ChunkTeamCount == NumTeams - Bound - 1) {
//
// Last team processing.
//
if (ThreadId >= NumRecs)
return 0;
NumThreads = roundToWarpsize(min(NumThreads, NumRecs));
if (ThreadId >= NumThreads)
return 0;
// Load from buffer and reduce.
glcpyFct(global_buffer, ThreadId, reduce_data);
for (uint32_t i = NumThreads + ThreadId; i < NumRecs; i += NumThreads)
glredFct(global_buffer, i, reduce_data);
// Reduce across warps to the warp master.
if (NumThreads > 1) {
gpu_regular_warp_reduce(reduce_data, shflFct);
// When we have more than [warpsize] number of threads
// a block reduction is performed here.
uint32_t ActiveThreads = min(NumRecs, NumThreads);
if (ActiveThreads > WARPSIZE) {
uint32_t WarpsNeeded = (ActiveThreads + WARPSIZE - 1) / WARPSIZE;
// Gather all the reduced values from each warp
// to the first warp.
cpyFct(reduce_data, WarpsNeeded);
uint32_t WarpId = ThreadId / WARPSIZE;
if (WarpId == 0)
gpu_irregular_warp_reduce(reduce_data, shflFct, WarpsNeeded,
ThreadId);
}
}
if (IsMaster) {
Cnt = 0;
IterCnt = 0;
return 1;
}
return 0;
}
if (IsMaster && ChunkTeamCount == num_of_records - 1) {
// Allow SIZE number of teams to proceed writing their
// intermediate results to the global buffer.
atomicAdd((uint32_t *)&IterCnt, num_of_records);
}
return 0;
}
@@ -1,9 +1,8 @@
//===--------- statequeue.h - NVPTX OpenMP GPU State Queue ------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -1,9 +1,8 @@
//===------- state-queue.cu - NVPTX OpenMP GPU State Queue ------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
+13 -10
View File
@@ -1,9 +1,8 @@
//===--------- support.h - NVPTX OpenMP support functions -------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -41,6 +40,8 @@ INLINE int GetThreadIdInBlock();
INLINE int GetBlockIdInKernel();
INLINE int GetNumberOfBlocksInKernel();
INLINE int GetNumberOfThreadsInBlock();
INLINE unsigned GetWarpId();
INLINE unsigned GetLaneId();
// get global ids to locate tread/team info (constant regardless of OMP)
INLINE int GetLogicalThreadIdInBlock(bool isSPMDExecutionMode);
@@ -48,15 +49,13 @@ INLINE int GetMasterThreadID();
INLINE int GetNumberOfWorkersInTeam();
// get OpenMP thread and team ids
INLINE int GetOmpThreadId(int threadId, bool isSPMDExecutionMode,
bool isRuntimeUninitialized); // omp_thread_num
INLINE int GetOmpThreadId(int threadId,
bool isSPMDExecutionMode); // omp_thread_num
INLINE int GetOmpTeamId(); // omp_team_num
// get OpenMP number of threads and team
INLINE int
GetNumberOfOmpThreads(int threadId, bool isSPMDExecutionMode,
bool isRuntimeUninitialized); // omp_num_threads
INLINE int GetNumberOfOmpTeams(); // omp_num_teams
INLINE int GetNumberOfOmpThreads(bool isSPMDExecutionMode); // omp_num_threads
INLINE int GetNumberOfOmpTeams(); // omp_num_teams
// get OpenMP number of procs
INLINE int GetNumberOfProcsInTeam(bool isSPMDExecutionMode);
@@ -65,6 +64,10 @@ INLINE int GetNumberOfProcsInDevice(bool isSPMDExecutionMode);
// masters
INLINE int IsTeamMaster(int ompThreadId);
// Parallel level
INLINE void IncParallelLevel(bool ActiveParallel);
INLINE void DecParallelLevel(bool ActiveParallel);
////////////////////////////////////////////////////////////////////////////////
// Memory
////////////////////////////////////////////////////////////////////////////////
+45 -30
View File
@@ -1,9 +1,8 @@
//===--------- supporti.h - NVPTX OpenMP support functions ------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -103,6 +102,10 @@ INLINE int GetNumberOfBlocksInKernel() { return gridDim.x; }
INLINE int GetNumberOfThreadsInBlock() { return blockDim.x; }
INLINE unsigned GetWarpId() { return threadIdx.x / WARPSIZE; }
INLINE unsigned GetLaneId() { return threadIdx.x & (WARPSIZE - 1); }
////////////////////////////////////////////////////////////////////////////////
//
// Calls to the Generic Scheme Implementation Layer (assuming 1D layout)
@@ -146,45 +149,32 @@ INLINE int GetLogicalThreadIdInBlock(bool isSPMDExecutionMode) {
//
////////////////////////////////////////////////////////////////////////////////
INLINE int GetOmpThreadId(int threadId, bool isSPMDExecutionMode,
bool isRuntimeUninitialized) {
INLINE int GetOmpThreadId(int threadId, bool isSPMDExecutionMode) {
// omp_thread_num
int rc;
if (isRuntimeUninitialized) {
ASSERT0(LT_FUSSY, isSPMDExecutionMode,
"Uninitialized runtime with non-SPMD mode.");
// For level 2 parallelism all parallel regions are executed sequentially.
if (parallelLevel > 0)
rc = 0;
else
rc = GetThreadIdInBlock();
if ((parallelLevel[GetWarpId()] & (OMP_ACTIVE_PARALLEL_LEVEL - 1)) > 1) {
rc = 0;
} else if (isSPMDExecutionMode) {
rc = GetThreadIdInBlock();
} else {
omptarget_nvptx_TaskDescr *currTaskDescr =
omptarget_nvptx_threadPrivateContext->GetTopLevelTaskDescr(threadId);
ASSERT0(LT_FUSSY, currTaskDescr, "expected a top task descr");
rc = currTaskDescr->ThreadId();
}
return rc;
}
INLINE int GetNumberOfOmpThreads(int threadId, bool isSPMDExecutionMode,
bool isRuntimeUninitialized) {
INLINE int GetNumberOfOmpThreads(bool isSPMDExecutionMode) {
// omp_num_threads
int rc;
if (isRuntimeUninitialized) {
ASSERT0(LT_FUSSY, isSPMDExecutionMode,
"Uninitialized runtime with non-SPMD mode.");
// For level 2 parallelism all parallel regions are executed sequentially.
if (parallelLevel > 0)
rc = 1;
else
rc = GetNumberOfThreadsInBlock();
int Level = parallelLevel[GetWarpId()];
if (Level != OMP_ACTIVE_PARALLEL_LEVEL + 1) {
rc = 1;
} else if (isSPMDExecutionMode) {
rc = GetNumberOfThreadsInBlock();
} else {
omptarget_nvptx_TaskDescr *currTaskDescr =
omptarget_nvptx_threadPrivateContext->GetTopLevelTaskDescr(threadId);
ASSERT0(LT_FUSSY, currTaskDescr, "expected a top task descr");
rc = currTaskDescr->ThreadsInTeam();
rc = threadsInTeam;
}
return rc;
@@ -208,6 +198,31 @@ INLINE int GetNumberOfOmpTeams() {
INLINE int IsTeamMaster(int ompThreadId) { return (ompThreadId == 0); }
////////////////////////////////////////////////////////////////////////////////
// Parallel level
INLINE void IncParallelLevel(bool ActiveParallel) {
unsigned tnum = __ACTIVEMASK();
int leader = __ffs(tnum) - 1;
__SHFL_SYNC(tnum, leader, leader);
if (GetLaneId() == leader) {
parallelLevel[GetWarpId()] +=
(1 + (ActiveParallel ? OMP_ACTIVE_PARALLEL_LEVEL : 0));
}
__SHFL_SYNC(tnum, leader, leader);
}
INLINE void DecParallelLevel(bool ActiveParallel) {
unsigned tnum = __ACTIVEMASK();
int leader = __ffs(tnum) - 1;
__SHFL_SYNC(tnum, leader, leader);
if (GetLaneId() == leader) {
parallelLevel[GetWarpId()] -=
(1 + (ActiveParallel ? OMP_ACTIVE_PARALLEL_LEVEL : 0));
}
__SHFL_SYNC(tnum, leader, leader);
}
////////////////////////////////////////////////////////////////////////////////
// get OpenMP number of procs
+6 -9
View File
@@ -1,9 +1,8 @@
//===------------ sync.h - NVPTX OpenMP synchronizations --------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -47,10 +46,8 @@ EXTERN void __kmpc_barrier(kmp_Ident *loc_ref, int32_t tid) {
__kmpc_barrier_simple_spmd(loc_ref, tid);
} else {
tid = GetLogicalThreadIdInBlock(checkSPMDMode(loc_ref));
omptarget_nvptx_TaskDescr *currTaskDescr =
omptarget_nvptx_threadPrivateContext->GetTopLevelTaskDescr(tid);
int numberOfActiveOMPThreads = GetNumberOfOmpThreads(
tid, checkSPMDMode(loc_ref), /*isRuntimeUninitialized=*/false);
int numberOfActiveOMPThreads =
GetNumberOfOmpThreads(checkSPMDMode(loc_ref));
if (numberOfActiveOMPThreads > 1) {
if (checkSPMDMode(loc_ref)) {
__kmpc_barrier_simple_spmd(loc_ref, tid);
@@ -133,7 +130,7 @@ EXTERN void __kmpc_end_single(kmp_Ident *loc, int32_t global_tid) {
EXTERN void __kmpc_flush(kmp_Ident *loc) {
PRINT0(LD_IO, "call kmpc_flush\n");
__threadfence_system();
__threadfence();
}
////////////////////////////////////////////////////////////////////////////////
+3 -4
View File
@@ -1,9 +1,8 @@
//===------------- task.h - NVPTX OpenMP tasks support ----------- CUDA -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -0,0 +1,46 @@
// RUN: %compile-run-and-check
#include <omp.h>
#include <stdio.h>
int main(int argc, char *argv[]) {
int MaxThreadsL1 = -1, MaxThreadsL2 = -1;
#pragma omp declare reduction(unique:int \
: omp_out = (omp_in == 1 ? omp_in : omp_out)) \
initializer(omp_priv = -1)
// Non-SPMD mode.
#pragma omp target teams map(MaxThreadsL1, MaxThreadsL2) thread_limit(32) \
num_teams(1)
{
MaxThreadsL1 = omp_get_max_threads();
#pragma omp parallel reduction(unique : MaxThreadsL2)
{ MaxThreadsL2 = omp_get_max_threads(); }
}
// CHECK: Non-SPMD MaxThreadsL1 = 32
printf("Non-SPMD MaxThreadsL1 = %d\n", MaxThreadsL1);
// CHECK: Non-SPMD MaxThreadsL2 = 1
printf("Non-SPMD MaxThreadsL2 = %d\n", MaxThreadsL2);
// SPMD mode with full runtime
MaxThreadsL2 = -1;
#pragma omp target parallel reduction(unique : MaxThreadsL2)
{ MaxThreadsL2 = omp_get_max_threads(); }
// CHECK: SPMD with full runtime MaxThreadsL2 = 1
printf("SPMD with full runtime MaxThreadsL2 = %d\n", MaxThreadsL2);
// SPMD mode without runtime
MaxThreadsL2 = -1;
#pragma omp target parallel for reduction(unique : MaxThreadsL2)
for (int I = 0; I < 2; ++I) {
MaxThreadsL2 = omp_get_max_threads();
}
// CHECK: SPMD without runtime MaxThreadsL2 = 1
printf("SPMD without runtime MaxThreadsL2 = %d\n", MaxThreadsL2);
return 0;
}
@@ -0,0 +1,72 @@
// RUN: %compile-run-and-check
#include <omp.h>
#include <stdio.h>
int main(int argc, char *argv[]) {
int ThreadLimitL0 = -1, ThreadLimitL1 = -1, ThreadLimitL2 = -1;
#pragma omp declare reduction(unique64:int \
: omp_out = (omp_in == 64 ? omp_in : omp_out)) \
initializer(omp_priv = -1)
#pragma omp declare reduction(unique32:int \
: omp_out = (omp_in == 32 ? omp_in : omp_out)) \
initializer(omp_priv = -1)
// Non-SPMD mode.
#pragma omp target teams map(ThreadLimitL0, ThreadLimitL1, ThreadLimitL2) \
thread_limit(64) num_teams(1)
{
ThreadLimitL0 = omp_get_thread_limit();
#pragma omp parallel reduction(unique64 \
: ThreadLimitL1, ThreadLimitL2) num_threads(32)
{
ThreadLimitL1 = omp_get_thread_limit();
#pragma omp parallel reduction(unique64 : ThreadLimitL2)
{ ThreadLimitL2 = omp_get_thread_limit(); }
}
}
// CHECK: Non-SPMD ThreadLimitL0 = 64
printf("Non-SPMD ThreadLimitL0 = %d\n", ThreadLimitL0);
// CHECK: Non-SPMD ThreadLimitL1 = 64
printf("Non-SPMD ThreadLimitL1 = %d\n", ThreadLimitL1);
// CHECK: Non-SPMD ThreadLimitL2 = 64
printf("Non-SPMD ThreadLimitL2 = %d\n", ThreadLimitL2);
// SPMD mode with full runtime
ThreadLimitL1 = -1;
ThreadLimitL2 = -1;
#pragma omp target parallel reduction(unique32 \
: ThreadLimitL1, ThreadLimitL2) \
num_threads(32)
{
ThreadLimitL1 = omp_get_thread_limit();
#pragma omp parallel reduction(unique32 : ThreadLimitL2)
{ ThreadLimitL2 = omp_get_thread_limit(); }
}
// CHECK: SPMD with full runtime ThreadLimitL1 = 32
printf("SPMD with full runtime ThreadLimitL1 = %d\n", ThreadLimitL1);
// CHECK: SPMD with full runtime ThreadLimitL2 = 32
printf("SPMD with full runtime ThreadLimitL2 = %d\n", ThreadLimitL2);
// SPMD mode without runtime
ThreadLimitL1 = -1;
ThreadLimitL2 = -1;
#pragma omp target parallel for reduction(unique32 \
: ThreadLimitL1, ThreadLimitL2) \
num_threads(32)
for (int I = 0; I < 2; ++I) {
ThreadLimitL1 = omp_get_thread_limit();
#pragma omp parallel reduction(unique32 : ThreadLimitL2)
{ ThreadLimitL2 = omp_get_thread_limit(); }
}
// CHECK: SPMD without runtime ThreadLimitL1 = 32
printf("SPMD without runtime ThreadLimitL1 = %d\n", ThreadLimitL1);
// CHECK: SPMD without runtime ThreadLimitL2 = 32
printf("SPMD without runtime ThreadLimitL2 = %d\n", ThreadLimitL2);
return 0;
}
@@ -0,0 +1,35 @@
// RUN: %compile-run-and-check
#include <omp.h>
#include <stdio.h>
int main(int argc, char *argv[]) {
int data, out, flag = 0;
#pragma omp target parallel num_threads(64) map(tofrom \
: out, flag) map(to \
: data)
{
if (omp_get_thread_num() == 0) {
/* Write to the data buffer that will be read by thread */
data = 42;
/* Flush data to thread 32 */
#pragma omp flush(data)
/* Set flag to release thread 32 */
#pragma omp atomic write
flag = 1;
} else if (omp_get_thread_num() == 32) {
/* Loop until we see the update to the flag */
int val;
do {
#pragma omp atomic read
val = flag;
} while (val < 1);
out = data;
#pragma omp flush(out)
}
}
// CHECK: out=42.
/* Value of out will be 42 */
printf("out=%d.\n", out);
return !(out == 42);
}
@@ -5,6 +5,7 @@
const int MaxThreads = 1024;
const int NumThreads = 64;
const int NumThreads1 = 1;
int main(int argc, char *argv[]) {
int inParallel = -1, numThreads = -1, threadNum = -1;
@@ -14,20 +15,20 @@ int main(int argc, char *argv[]) {
check1[i] = check2[i] = 0;
}
#pragma omp target map(inParallel, numThreads, threadNum, check1[:], check2[:])
#pragma omp target map(inParallel, numThreads, threadNum, check1[:], check2[:])
{
inParallel = omp_in_parallel();
numThreads = omp_get_num_threads();
threadNum = omp_get_thread_num();
// Expecting active parallel region.
#pragma omp parallel num_threads(NumThreads)
// Expecting active parallel region.
#pragma omp parallel num_threads(NumThreads)
{
int id = omp_get_thread_num();
check1[id] += omp_get_num_threads() + omp_in_parallel();
// Expecting serialized parallel region.
#pragma omp parallel
// Expecting serialized parallel region.
#pragma omp parallel
{
// Expected to be 1.
int nestedInParallel = omp_in_parallel();
@@ -35,7 +36,7 @@ int main(int argc, char *argv[]) {
int nestedNumThreads = omp_get_num_threads();
// Expected to be 0.
int nestedThreadNum = omp_get_thread_num();
#pragma omp atomic
#pragma omp atomic
check2[id] += nestedInParallel + nestedNumThreads + nestedThreadNum;
}
}
@@ -52,7 +53,8 @@ int main(int argc, char *argv[]) {
int Expected = NumThreads + 1;
if (i < NumThreads) {
if (check1[i] != Expected) {
printf("invalid: check1[%d] should be %d, is %d\n", i, Expected, check1[i]);
printf("invalid: check1[%d] should be %d, is %d\n", i, Expected,
check1[i]);
}
} else if (check1[i] != 0) {
printf("invalid: check1[%d] should be 0, is %d\n", i, check1[i]);
@@ -68,5 +70,67 @@ int main(int argc, char *argv[]) {
}
}
inParallel = -1;
numThreads = -1;
threadNum = -1;
for (int i = 0; i < MaxThreads; i++) {
check1[i] = check2[i] = 0;
}
#pragma omp target map(inParallel, numThreads, threadNum, check1[:], check2[:])
{
inParallel = omp_in_parallel();
numThreads = omp_get_num_threads();
threadNum = omp_get_thread_num();
// Expecting active parallel region.
#pragma omp parallel num_threads(NumThreads1)
{
int id = omp_get_thread_num();
check1[id] += omp_get_num_threads() + omp_in_parallel();
// Expecting serialized parallel region.
#pragma omp parallel
{
// Expected to be 0.
int nestedInParallel = omp_in_parallel();
// Expected to be 1.
int nestedNumThreads = omp_get_num_threads();
// Expected to be 0.
int nestedThreadNum = omp_get_thread_num();
#pragma omp atomic
check2[id] += nestedInParallel + nestedNumThreads + nestedThreadNum;
}
}
}
// CHECK: target: inParallel = 0, numThreads = 1, threadNum = 0
printf("target: inParallel = %d, numThreads = %d, threadNum = %d\n",
inParallel, numThreads, threadNum);
// CHECK-NOT: invalid
for (int i = 0; i < MaxThreads; i++) {
// Check that all threads reported
// omp_get_num_threads() = 1, omp_in_parallel() = 0.
int Expected = 1;
if (i < NumThreads1) {
if (check1[i] != Expected) {
printf("invalid: check1[%d] should be %d, is %d\n", i, Expected,
check1[i]);
}
} else if (check1[i] != 0) {
printf("invalid: check1[%d] should be 0, is %d\n", i, check1[i]);
}
// Check serialized parallel region.
if (i < NumThreads1) {
if (check2[i] != 1) {
printf("invalid: check2[%d] should be 1, is %d\n", i, check2[i]);
}
} else if (check2[i] != 0) {
printf("invalid: check2[%d] should be 0, is %d\n", i, check2[i]);
}
}
return 0;
}
@@ -0,0 +1,51 @@
// RUN: %compilexx-run-and-check
#include <stdio.h>
#include <omp.h>
int main(void) {
int isHost = -1;
int ParallelLevel1 = -1, ParallelLevel2 = -1;
int Count = 0;
#pragma omp target parallel for map(tofrom \
: isHost, ParallelLevel1, ParallelLevel2), reduction(+: Count) schedule(static, 1)
for (int J = 0; J < 10; ++J) {
#pragma omp critical
{
isHost = (isHost < 0 || isHost == 0) ? omp_is_initial_device() : isHost;
ParallelLevel1 = (ParallelLevel1 < 0 || ParallelLevel1 == 1)
? omp_get_level()
: ParallelLevel1;
}
if (omp_get_thread_num() > 5) {
int L2;
#pragma omp parallel for schedule(dynamic) lastprivate(L2) reduction(+: Count)
for (int I = 0; I < 10; ++I) {
L2 = omp_get_level();
Count += omp_get_level(); // (10-6)*10*2 = 80
}
#pragma omp critical
ParallelLevel2 =
(ParallelLevel2 < 0 || ParallelLevel2 == 2) ? L2 : ParallelLevel2;
} else {
Count += omp_get_level(); // 6 * 1 = 6
}
}
if (isHost < 0) {
printf("Runtime error, isHost=%d\n", isHost);
}
// CHECK: Target region executed on the device
printf("Target region executed on the %s\n", isHost ? "host" : "device");
// CHECK: Parallel level in SPMD mode: L1 is 1, L2 is 2
printf("Parallel level in SPMD mode: L1 is %d, L2 is %d\n", ParallelLevel1,
ParallelLevel2);
// Final result of Count is (10-6)(num of loops)*10(num of iterations)*2(par
// level) + 6(num of iterations) * 1(par level)
// CHECK: Expected count = 86
printf("Expected count = %d\n", Count);
return isHost;
}
@@ -0,0 +1,22 @@
// RUN: %compile-run-and-check
#include <omp.h>
#include <stdio.h>
int main() {
int res = 0;
#pragma omp parallel num_threads(2) reduction(+:res)
{
int tid = omp_get_thread_num();
#pragma omp target teams distribute reduction(+:res)
for (int i = tid; i < 2; i++)
++res;
}
// The first thread makes 2 iterations, the second - 1. Expected result of the
// reduction res is 3.
// CHECK: res = 3.
printf("res = %d.\n", res);
return 0;
}
+21 -4
View File
@@ -1,9 +1,8 @@
//===-------- omptarget.h - Target independent OpenMP target RTL -- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -61,6 +60,21 @@ enum OpenMPOffloadingDeclareTargetFlags {
OMP_DECLARE_TARGET_DTOR = 0x04
};
enum OpenMPOffloadingRequiresDirFlags {
/// flag undefined.
OMP_REQ_UNDEFINED = 0x000,
/// no requires directive present.
OMP_REQ_NONE = 0x001,
/// reverse_offload clause.
OMP_REQ_REVERSE_OFFLOAD = 0x002,
/// unified_address clause.
OMP_REQ_UNIFIED_ADDRESS = 0x004,
/// unified_shared_memory clause.
OMP_REQ_UNIFIED_SHARED_MEMORY = 0x008,
/// dynamic_allocators clause.
OMP_REQ_DYNAMIC_ALLOCATORS = 0x010
};
/// This struct is a record of an entry point or global. For a function
/// entry point the size is expected to be zero
struct __tgt_offload_entry {
@@ -114,6 +128,9 @@ int omp_target_associate_ptr(void *host_ptr, void *device_ptr, size_t size,
size_t device_offset, int device_num);
int omp_target_disassociate_ptr(void *host_ptr, int device_num);
/// add the clauses of the requires directives in a given file
void __tgt_register_requires(int64_t flags);
/// adds a target shared library to the target execution image
void __tgt_register_lib(__tgt_bin_desc *desc);
+6 -4
View File
@@ -1,9 +1,8 @@
//===-- omptargetplugin.h - Target dependent OpenMP Plugin API --*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -32,6 +31,9 @@ int32_t __tgt_rtl_number_of_devices(void);
// having to load the library, which can be expensive.
int32_t __tgt_rtl_is_valid_binary(__tgt_device_image *Image);
// Initialize the requires flags for the device.
int64_t __tgt_rtl_init_requires(int64_t RequiresFlags);
// Initialize the specified device. In case of success return 0; otherwise
// return an error code.
int32_t __tgt_rtl_init_device(int32_t ID);
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
//===-- elf_common.c - Common ELF functionality -------------------*- C -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+35 -4
View File
@@ -1,9 +1,8 @@
//===----RTLs/cuda/src/rtl.cpp - Target RTLs Implementation ------- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -112,6 +111,9 @@ public:
int EnvNumTeams;
int EnvTeamLimit;
// OpenMP Requires Flags
int64_t RequiresFlags;
//static int EnvNumThreads;
static const int HardTeamLimit = 1<<16; // 64k
static const int HardThreadLimit = 1024;
@@ -228,6 +230,9 @@ public:
} else {
EnvNumTeams = -1;
}
// Default state.
RequiresFlags = OMP_REQ_UNDEFINED;
}
~RTLDeviceInfoTy() {
@@ -265,6 +270,12 @@ int32_t __tgt_rtl_is_valid_binary(__tgt_device_image *image) {
int32_t __tgt_rtl_number_of_devices() { return DeviceInfo.NumberOfDevices; }
int64_t __tgt_rtl_init_requires(int64_t RequiresFlags) {
DP("Init requires flags to %ld\n", RequiresFlags);
DeviceInfo.RequiresFlags = RequiresFlags;
return RequiresFlags;
}
int32_t __tgt_rtl_init_device(int32_t device_id) {
CUdevice cuDevice;
@@ -437,6 +448,26 @@ __tgt_target_table *__tgt_rtl_load_binary(int32_t device_id,
DPxPTR(e - HostBegin), e->name, DPxPTR(cuptr));
entry.addr = (void *)cuptr;
// Note: In the current implementation declare target variables
// can either be link or to. This means that once unified
// memory is activated via the requires directive, the variable
// can be used directly from the host in both cases.
// TODO: when variables types other than to or link are added,
// the below condition should be changed to explicitely
// check for to and link variables types:
// (DeviceInfo.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
// (e->flags & OMP_DECLARE_TARGET_LINK ||
// e->flags == OMP_DECLARE_TARGET_TO))
if (DeviceInfo.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY) {
// If unified memory is present any target link or to variables
// can access host addresses directly. There is no longer a
// need for device copies.
cuMemcpyHtoD(cuptr, e->addr, sizeof(void *));
DP("Copy linked variable host address (" DPxMOD ")"
"to device address (" DPxMOD ")\n",
DPxPTR(*((void**)e->addr)), DPxPTR(cuptr));
}
DeviceInfo.addOffloadEntry(device_id, entry);
continue;
+1
View File
@@ -2,6 +2,7 @@ VERS1.0 {
global:
__tgt_rtl_is_valid_binary;
__tgt_rtl_number_of_devices;
__tgt_rtl_init_requires;
__tgt_rtl_init_device;
__tgt_rtl_load_binary;
__tgt_rtl_data_alloc;
@@ -1,9 +1,8 @@
//===-RTLs/generic-64bit/src/rtl.cpp - Target RTLs Implementation - C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
##===----------------------------------------------------------------------===##
#
# The LLVM Compiler Infrastructure
#
# This file is dual licensed under the MIT and the University of Illinois Open
# Source Licenses. See LICENSE.txt for details.
# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
# See https://llvm.org/LICENSE.txt for license information.
# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#
##===----------------------------------------------------------------------===##
#
+3 -4
View File
@@ -1,9 +1,8 @@
//===----------- api.cpp - Target independent OpenMP target RTL -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
+7 -5
View File
@@ -1,9 +1,8 @@
//===--------- device.cpp - Target independent OpenMP target RTL ----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -153,7 +152,7 @@ LookupResult DeviceTy::lookupMapping(void *HstPtrBegin, int64_t Size) {
// Used by target_data_begin
// Return the target pointer begin (where the data will be moved).
// Allocate memory if this is the first occurrence if this mapping.
// Allocate memory if this is the first occurrence of this mapping.
// Increment the reference counter.
// If NULL is returned, then either data allocation failed or the user tried
// to do an illegal mapping.
@@ -276,6 +275,9 @@ int DeviceTy::deallocTgtPtr(void *HstPtrBegin, int64_t Size, bool ForceDelete) {
/// Init device, should not be called directly.
void DeviceTy::init() {
// Make call to init_requires if it exists for this plugin.
if (RTL->init_requires)
RTL->init_requires(RTLRequiresFlags);
int32_t rc = RTL->init_device(RTLDeviceID);
if (rc == OFFLOAD_SUCCESS) {
IsInit = true;
+13 -8
View File
@@ -1,9 +1,8 @@
//===----------- device.h - Target independent OpenMP target RTL ----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -97,13 +96,17 @@ struct DeviceTy {
std::mutex DataMapMtx, PendingGlobalsMtx, ShadowMtx;
uint64_t loopTripCnt;
// NOTE: Once libomp gains full target-task support, this state should be
// moved into the target task in libomp.
std::map<int32_t, uint64_t> LoopTripCnt;
int64_t RTLRequiresFlags;
DeviceTy(RTLInfoTy *RTL)
: DeviceID(-1), RTL(RTL), RTLDeviceID(-1), IsInit(false), InitFlag(),
HasPendingGlobals(false), HostDataToTargetMap(),
PendingCtorsDtors(), ShadowPtrMap(), DataMapMtx(), PendingGlobalsMtx(),
ShadowMtx(), loopTripCnt(0) {}
ShadowMtx(), RTLRequiresFlags(0) {}
// The existence of mutexes makes DeviceTy non-copyable. We need to
// provide a copy constructor and an assignment operator explicitly.
@@ -113,7 +116,8 @@ struct DeviceTy {
HostDataToTargetMap(d.HostDataToTargetMap),
PendingCtorsDtors(d.PendingCtorsDtors), ShadowPtrMap(d.ShadowPtrMap),
DataMapMtx(), PendingGlobalsMtx(),
ShadowMtx(), loopTripCnt(d.loopTripCnt) {}
ShadowMtx(), LoopTripCnt(d.LoopTripCnt),
RTLRequiresFlags(d.RTLRequiresFlags) {}
DeviceTy& operator=(const DeviceTy &d) {
DeviceID = d.DeviceID;
@@ -124,7 +128,8 @@ struct DeviceTy {
HostDataToTargetMap = d.HostDataToTargetMap;
PendingCtorsDtors = d.PendingCtorsDtors;
ShadowPtrMap = d.ShadowPtrMap;
loopTripCnt = d.loopTripCnt;
LoopTripCnt = d.LoopTripCnt;
RTLRequiresFlags = d.RTLRequiresFlags;
return *this;
}
+1
View File
@@ -1,5 +1,6 @@
VERS1.0 {
global:
__tgt_register_requires;
__tgt_register_lib;
__tgt_unregister_lib;
__tgt_target_data_begin;
+22 -16
View File
@@ -1,9 +1,8 @@
//===-------- interface.cpp - Target independent OpenMP target RTL --------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -34,11 +33,11 @@ static void HandleDefaultTargetOffload() {
if (TargetOffloadPolicy == tgt_default) {
if (omp_get_num_devices() > 0) {
DP("Default TARGET OFFLOAD policy is now mandatory "
"(devicew were found)\n");
"(devices were found)\n");
TargetOffloadPolicy = tgt_mandatory;
} else {
DP("Default TARGET OFFLOAD policy is now disabled "
"(devices were not found)\n");
"(no devices were found)\n");
TargetOffloadPolicy = tgt_disabled;
}
}
@@ -58,8 +57,8 @@ static void HandleTargetOutcome(bool success) {
}
break;
case tgt_default:
FATAL_MESSAGE0(1, "default offloading policy must switched to "
"mandatory or disabled");
FATAL_MESSAGE0(1, "default offloading policy must be switched to "
"mandatory or disabled");
break;
case tgt_mandatory:
if (!success) {
@@ -69,6 +68,12 @@ static void HandleTargetOutcome(bool success) {
}
}
////////////////////////////////////////////////////////////////////////////////
/// adds requires flags
EXTERN void __tgt_register_requires(int64_t flags) {
RTLs.RegisterRequires(flags);
}
////////////////////////////////////////////////////////////////////////////////
/// adds a target shared library to the target execution image
EXTERN void __tgt_register_lib(__tgt_bin_desc *desc) {
@@ -123,7 +128,7 @@ EXTERN void __tgt_target_data_begin_nowait(int64_t device_id, int32_t arg_num,
int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, 0);
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
__tgt_target_data_begin(device_id, arg_num, args_base, args, arg_sizes,
arg_types);
@@ -176,7 +181,7 @@ EXTERN void __tgt_target_data_end_nowait(int64_t device_id, int32_t arg_num,
int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, 0);
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
__tgt_target_data_end(device_id, arg_num, args_base, args, arg_sizes,
arg_types);
@@ -209,7 +214,7 @@ EXTERN void __tgt_target_data_update_nowait(
int64_t *arg_sizes, int64_t *arg_types, int32_t depNum, void *depList,
int32_t noAliasDepNum, void *noAliasDepList) {
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, 0);
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
__tgt_target_data_update(device_id, arg_num, args_base, args, arg_sizes,
arg_types);
@@ -250,7 +255,7 @@ EXTERN int __tgt_target_nowait(int64_t device_id, void *host_ptr,
int64_t *arg_types, int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, 0);
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
return __tgt_target(device_id, host_ptr, arg_num, args_base, args, arg_sizes,
arg_types);
@@ -293,14 +298,12 @@ EXTERN int __tgt_target_teams_nowait(int64_t device_id, void *host_ptr,
int64_t *arg_types, int32_t team_num, int32_t thread_limit, int32_t depNum,
void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, 0);
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
return __tgt_target_teams(device_id, host_ptr, arg_num, args_base, args,
arg_sizes, arg_types, team_num, thread_limit);
}
// The trip count mechanism will be revised - this scheme is not thread-safe.
EXTERN void __kmpc_push_target_tripcount(int64_t device_id,
uint64_t loop_tripcount) {
if (device_id == OFFLOAD_DEVICE_DEFAULT) {
@@ -315,5 +318,8 @@ EXTERN void __kmpc_push_target_tripcount(int64_t device_id,
DP("__kmpc_push_target_tripcount(%" PRId64 ", %" PRIu64 ")\n", device_id,
loop_tripcount);
Devices[device_id].loopTripCnt = loop_tripcount;
TblMapMtx.lock();
Devices[device_id].LoopTripCnt.emplace(__kmpc_global_thread_num(NULL),
loop_tripcount);
TblMapMtx.unlock();
}
+12 -6
View File
@@ -1,9 +1,8 @@
//===------ omptarget.cpp - Target independent OpenMP target RTL -- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -730,8 +729,15 @@ int target(int64_t device_id, void *host_ptr, int32_t arg_num,
"Size mismatch in arguments and offsets");
// Pop loop trip count
uint64_t ltc = Device.loopTripCnt;
Device.loopTripCnt = 0;
uint64_t ltc = 0;
TblMapMtx.lock();
auto I = Device.LoopTripCnt.find(__kmpc_global_thread_num(NULL));
if (I != Device.LoopTripCnt.end()) {
ltc = I->second;
Device.LoopTripCnt.erase(I);
DP("loop trip count is %lu.\n", ltc);
}
TblMapMtx.unlock();
// Launch device execution.
DP("Launching target execution %s with pointer " DPxMOD " (index=%d).\n",
+4 -4
View File
@@ -1,9 +1,8 @@
//===---------- private.h - Target independent OpenMP target RTL ----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -66,6 +65,7 @@ extern "C" {
// functions that extract info from libomp; keep in sync
int omp_get_default_device(void) __attribute__((weak));
int32_t __kmpc_omp_taskwait(void *loc_ref, int32_t gtid) __attribute__((weak));
int32_t __kmpc_global_thread_num(void *) __attribute__((weak));
int __kmpc_get_target_offload(void) __attribute__((weak));
#ifdef __cplusplus
}
+49 -4
View File
@@ -1,9 +1,8 @@
//===----------- rtl.cpp - Target independent OpenMP target RTL -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -108,6 +107,10 @@ void RTLsTy::LoadRTLs() {
dynlib_handle, "__tgt_rtl_run_target_team_region")))
continue;
// Optional functions
*((void**) &R.init_requires) = dlsym(
dynlib_handle, "__tgt_rtl_init_requires");
// No devices are supported by this RTL?
if (!(R.NumberOfDevices = R.number_of_devices())) {
DP("No devices supported in this RTL\n");
@@ -187,6 +190,46 @@ static void RegisterGlobalCtorsDtorsForImage(__tgt_bin_desc *desc,
}
}
void RTLsTy::RegisterRequires(int64_t flags) {
// TODO: add more elaborate check.
// Minimal check: only set requires flags if previous value
// is undefined. This ensures that only the first call to this
// function will set the requires flags. All subsequent calls
// will be checked for compatibility.
assert(flags != OMP_REQ_UNDEFINED &&
"illegal undefined flag for requires directive!");
if (RequiresFlags == OMP_REQ_UNDEFINED) {
RequiresFlags = flags;
return;
}
// If multiple compilation units are present enforce
// consistency across all of them for require clauses:
// - reverse_offload
// - unified_address
// - unified_shared_memory
if ((RequiresFlags & OMP_REQ_REVERSE_OFFLOAD) !=
(flags & OMP_REQ_REVERSE_OFFLOAD)) {
FATAL_MESSAGE0(1,
"'#pragma omp requires reverse_offload' not used consistently!");
}
if ((RequiresFlags & OMP_REQ_UNIFIED_ADDRESS) !=
(flags & OMP_REQ_UNIFIED_ADDRESS)) {
FATAL_MESSAGE0(1,
"'#pragma omp requires unified_address' not used consistently!");
}
if ((RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY) !=
(flags & OMP_REQ_UNIFIED_SHARED_MEMORY)) {
FATAL_MESSAGE0(1,
"'#pragma omp requires unified_shared_memory' not used consistently!");
}
// TODO: insert any other missing checks
DP("New requires flags %ld compatible with existing %ld!\n",
flags, RequiresFlags);
}
void RTLsTy::RegisterLib(__tgt_bin_desc *desc) {
// Attempt to load all plugins available in the system.
std::call_once(initFlag, &RTLsTy::LoadRTLs, this);
@@ -223,6 +266,8 @@ void RTLsTy::RegisterLib(__tgt_bin_desc *desc) {
Devices[start + device_id].DeviceID = start + device_id;
// RTL local device ID
Devices[start + device_id].RTLDeviceID = device_id;
// RTL requires flags
Devices[start + device_id].RTLRequiresFlags = RequiresFlags;
}
// Initialize the index of this RTL and save it in the used RTLs.
+13 -6
View File
@@ -1,9 +1,8 @@
//===------------ rtl.h - Target independent OpenMP target RTL ------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
@@ -37,6 +36,7 @@ struct RTLInfoTy {
int32_t);
typedef int32_t(run_team_region_ty)(int32_t, void *, void **, ptrdiff_t *,
int32_t, int32_t, int32_t, uint64_t);
typedef int64_t(init_requires_ty)(int64_t);
int32_t Idx; // RTL index, index is the number of devices
// of other RTLs that were registered before,
@@ -61,6 +61,7 @@ struct RTLInfoTy {
data_delete_ty *data_delete;
run_region_ty *run_region;
run_team_region_ty *run_team_region;
init_requires_ty *init_requires;
// Are there images associated with this RTL.
bool isUsed;
@@ -79,8 +80,8 @@ struct RTLInfoTy {
#endif
is_valid_binary(0), number_of_devices(0), init_device(0),
load_binary(0), data_alloc(0), data_submit(0), data_retrieve(0),
data_delete(0), run_region(0), run_team_region(0), isUsed(false),
Mtx() {}
data_delete(0), run_region(0), run_team_region(0),
init_requires(0), isUsed(false), Mtx() {}
RTLInfoTy(const RTLInfoTy &r) : Mtx() {
Idx = r.Idx;
@@ -99,6 +100,7 @@ struct RTLInfoTy {
data_delete = r.data_delete;
run_region = r.run_region;
run_team_region = r.run_team_region;
init_requires = r.init_requires;
isUsed = r.isUsed;
}
};
@@ -119,8 +121,13 @@ public:
// binaries.
std::vector<RTLInfoTy *> UsedRTLs;
int64_t RequiresFlags;
explicit RTLsTy() {}
// Register the clauses of the requires directive.
void RegisterRequires(int64_t flags);
// Register a shared library with all (compatible) RTLs.
void RegisterLib(__tgt_bin_desc *desc);
+1 -1
View File
@@ -6,7 +6,7 @@ if(NOT OPENMP_TEST_COMPILER_ID STREQUAL "Clang" OR
return()
endif()
if(LIBOMPTARGET_CMAKE_BUILD_TYPE MATCHES debug)
if(LIBOMPTARGET_ENABLE_DEBUG)
set(LIBOMPTARGET_DEBUG True)
else()
set(LIBOMPTARGET_DEBUG False)
@@ -0,0 +1,36 @@
// RUN: %libomptarget-compile-aarch64-unknown-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-aarch64-unknown-linux-gnu 2>&1 | %fcheck-aarch64-unknown-linux-gnu -allow-empty -check-prefix=DEBUG
// RUN: %libomptarget-compile-powerpc64-ibm-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-powerpc64-ibm-linux-gnu 2>&1 | %fcheck-powerpc64-ibm-linux-gnu -allow-empty -check-prefix=DEBUG
// RUN: %libomptarget-compile-powerpc64le-ibm-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-powerpc64le-ibm-linux-gnu 2>&1 | %fcheck-powerpc64le-ibm-linux-gnu -allow-empty -check-prefix=DEBUG
// RUN: %libomptarget-compile-x86_64-pc-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-x86_64-pc-linux-gnu 2>&1 | %fcheck-x86_64-pc-linux-gnu -allow-empty -check-prefix=DEBUG
// REQUIRES: libomptarget-debug
/*
Test for looptripcount being popped from runtime stack.
*/
#include <stdio.h>
#include <omp.h>
int main()
{
int N = 128;
int NN = 1024;
int num_teams[NN];
int num_threads[NN];
printf("#pragma omp target teams distribute parallel for thread_limit(4)\n");
#pragma omp target teams distribute parallel for thread_limit(4)
for (int j = 0; j< N; j++) {
num_threads[j] = omp_get_num_threads();
num_teams[j] = omp_get_num_teams();
}
printf("num_threads %d num_teams %d\n", num_threads[0], num_teams[0]);
// DEBUG: loop trip count is 128
printf("#pragma omp target teams distribute parallel for\n");
#pragma omp target teams distribute parallel for
for (int j = 0; j< N; j++) {
num_threads[j] = omp_get_num_threads();
num_teams[j] = omp_get_num_teams();
}
printf("num_threads %d num_teams %d\n", num_threads[0], num_teams[0]);
// DEBUG: loop trip count is 128
return 0;
}
+46
View File
@@ -0,0 +1,46 @@
// RUN: %libomptarget-compile-aarch64-unknown-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-aarch64-unknown-linux-gnu 2>&1 | %fcheck-aarch64-unknown-linux-gnu -allow-empty -check-prefix=DEBUG
// RUN: %libomptarget-compile-powerpc64-ibm-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-powerpc64-ibm-linux-gnu 2>&1 | %fcheck-powerpc64-ibm-linux-gnu -allow-empty -check-prefix=DEBUG
// RUN: %libomptarget-compile-powerpc64le-ibm-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-powerpc64le-ibm-linux-gnu 2>&1 | %fcheck-powerpc64le-ibm-linux-gnu -allow-empty -check-prefix=DEBUG
// RUN: %libomptarget-compile-x86_64-pc-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-x86_64-pc-linux-gnu 2>&1 | %fcheck-x86_64-pc-linux-gnu -allow-empty -check-prefix=DEBUG
// REQUIRES: libomptarget-debug
/*
Test for the 'requires' clause check.
When a target region is used, the requires flags are set in the
runtime for the entire compilation unit. If the flags are set again,
(for whatever reason) the set must be consistent with previously
set values.
*/
#include <stdio.h>
#include <omp.h>
// ---------------------------------------------------------------------------
// Various definitions copied from OpenMP RTL
extern void __tgt_register_requires(int64_t);
// End of definitions copied from OpenMP RTL.
// ---------------------------------------------------------------------------
void run_reg_requires() {
// Before the target region is registered, the requires registers the status
// of the requires clauses. Since there are no requires clauses in this file
// the flags state can only be OMP_REQ_NONE i.e. 1.
// This is the 2nd time this function is called so it should print the debug
// info belonging to the check.
__tgt_register_requires(1);
__tgt_register_requires(1);
// DEBUG: New requires flags 1 compatible with existing 1!
}
// ---------------------------------------------------------------------------
int main() {
run_reg_requires();
// This also runs reg requires for the first time.
#pragma omp target
{}
return 0;
}
@@ -0,0 +1,62 @@
// RUN: %libomptarget-compilexx-run-and-check-aarch64-unknown-linux-gnu
// RUN: %libomptarget-compilexx-run-and-check-powerpc64-ibm-linux-gnu
// RUN: %libomptarget-compilexx-run-and-check-powerpc64le-ibm-linux-gnu
// RUN: %libomptarget-compilexx-run-and-check-x86_64-pc-linux-gnu
#include <omp.h>
#include <stdio.h>
#define N 1024
int A[N];
int B[N];
int C[N];
int main() {
for (int i = 0; i < N; i++)
A[i] = B[i] = i;
#pragma omp parallel num_threads(2)
{
if (omp_get_thread_num() == 1) {
// map data A & B and move to
#pragma omp target enter data map(to : A, B) depend(out : A[0]) nowait
// no data move since already mapped
#pragma omp target map(A, B) depend(out : A[0]) nowait
{
for (int i = 0; i < N; i++)
++A[i];
for (int i = 0; i < N; i++)
++B[i];
}
// no data move since already mapped
#pragma omp target teams num_teams(1) map(A, B) depend(out : A[0]) nowait
{
for (int i = 0; i < N; i++)
++A[i];
for (int i = 0; i < N; i++)
++B[i];
}
// A updated via update
#pragma omp target update from(A) depend(out : A[0]) nowait
// B updated via exit, A just released
#pragma omp target exit data map(release \
: A) map(from \
: B) depend(out \
: A[0]) nowait
} // if
} // parallel
int Sum = 0;
for (int i = 0; i < N; i++)
Sum += A[i] + B[i];
// Sum is 2 * N * (2 + N - 1 + 2) / 2
// CHECK: Sum = 1051648.
printf("Sum = %d.\n", Sum);
return Sum != 2 * N * (2 + N - 1 + 2) / 2;
}
+6 -24
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -70,21 +69,8 @@ libomp_check_variable(LIBOMP_ARCH 32e x86_64 32 i386 arm ppc64 ppc64le aarch64 m
set(LIBOMP_LIB_TYPE normal CACHE STRING
"Performance,Profiling,Stubs library (normal/profile/stubs)")
libomp_check_variable(LIBOMP_LIB_TYPE normal profile stubs)
set(LIBOMP_OMP_VERSION 50 CACHE STRING
"The OpenMP version (50/45/40/30)")
libomp_check_variable(LIBOMP_OMP_VERSION 50 45 40 30)
# Set the OpenMP Year and Month assiociated with version
if(${LIBOMP_OMP_VERSION} GREATER 50 OR ${LIBOMP_OMP_VERSION} EQUAL 50)
set(LIBOMP_OMP_YEAR_MONTH 201611)
elseif(${LIBOMP_OMP_VERSION} GREATER 45 OR ${LIBOMP_OMP_VERSION} EQUAL 45)
set(LIBOMP_OMP_YEAR_MONTH 201511)
elseif(${LIBOMP_OMP_VERSION} GREATER 40 OR ${LIBOMP_OMP_VERSION} EQUAL 40)
set(LIBOMP_OMP_YEAR_MONTH 201307)
elseif(${LIBOMP_OMP_VERSION} GREATER 30 OR ${LIBOMP_OMP_VERSION} EQUAL 30)
set(LIBOMP_OMP_YEAR_MONTH 201107)
else()
set(LIBOMP_OMP_YEAR_MONTH 200505)
endif()
set(LIBOMP_OMP_YEAR_MONTH 201611)
set(LIBOMP_MIC_ARCH knc CACHE STRING
"Intel(R) Many Integrated Core Architecture (Intel(R) MIC Architecture) (knf/knc). Ignored if not Intel(R) MIC Architecture build.")
if("${LIBOMP_ARCH}" STREQUAL "mic")
@@ -214,7 +200,7 @@ endif()
set(LIBOMP_BASE_DIR ${CMAKE_CURRENT_SOURCE_DIR})
set(LIBOMP_SRC_DIR ${LIBOMP_BASE_DIR}/src)
set(LIBOMP_TOOLS_DIR ${LIBOMP_BASE_DIR}/tools)
set(LIBOMP_INC_DIR ${LIBOMP_SRC_DIR}/include/${LIBOMP_OMP_VERSION})
set(LIBOMP_INC_DIR ${LIBOMP_SRC_DIR}/include)
set(LIBOMP_BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR})
# Enabling Fortran if it is needed
@@ -302,7 +288,7 @@ endif()
# OMPT-support defaults to ON for OpenMP 5.0+ and if the requirements in
# cmake/config-ix.cmake are fulfilled.
set(OMPT_DEFAULT FALSE)
if ((${LIBOMP_OMP_VERSION} GREATER 49) AND (LIBOMP_HAVE_OMPT_SUPPORT) AND (NOT WIN32))
if ((LIBOMP_HAVE_OMPT_SUPPORT) AND (NOT WIN32))
set(OMPT_DEFAULT TRUE)
endif()
set(LIBOMP_OMPT_SUPPORT ${OMPT_DEFAULT} CACHE BOOL
@@ -315,9 +301,6 @@ set(LIBOMP_OMPT_OPTIONAL TRUE CACHE BOOL
if(LIBOMP_OMPT_SUPPORT AND (NOT LIBOMP_HAVE_OMPT_SUPPORT))
libomp_error_say("OpenMP Tools Interface requested but not available in this implementation")
endif()
if(LIBOMP_OMPT_SUPPORT AND (${LIBOMP_OMP_VERSION} LESS 50))
libomp_error_say("OpenMP Tools Interface only available with OpenMP 5.0, LIBOMP_OMP_VERSION is ${LIBOMP_OMP_VERSION}")
endif()
# TSAN-support
set(LIBOMP_TSAN_SUPPORT FALSE CACHE BOOL
@@ -369,7 +352,6 @@ if(${OPENMP_STANDALONE_BUILD})
libomp_say("Intel(R) MIC Architecture -- ${LIBOMP_MIC_ARCH}")
endif()
libomp_say("Build Type -- ${CMAKE_BUILD_TYPE}")
libomp_say("OpenMP Version -- ${LIBOMP_OMP_VERSION}")
libomp_say("Library Kind -- ${LIBOMP_LIBRARY_KIND}")
libomp_say("Library Type -- ${LIBOMP_LIB_TYPE}")
libomp_say("Fortran Modules -- ${LIBOMP_FORTRAN_MODULES}")
+3 -4
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
+3 -4
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
+3 -5
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -29,4 +28,3 @@ function(libomp_get_definitions_flags cppflags)
# CMake doesn't include CPPFLAGS from environment, but we will.
set(${cppflags} ${cppflags_local} ${LIBOMP_CPPFLAGS} $ENV{CPPFLAGS} PARENT_SCOPE)
endfunction()
+6 -11
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -14,16 +13,13 @@
# Create the suffix for the export directory
# - Only add to suffix when not a default value
# - Example suffix: .deb.30.s1
# final export directory: exports/lin_32e.deb.30.s1/lib
# - These suffixes imply the build is a Debug, OpenMP 3.0, Stats-Gathering version of the library
# - Example suffix: .deb.s1
# final export directory: exports/lin_32e.deb.s1/lib
# - These suffixes imply the build is a Debug, Stats-Gathering version of the library
set(libomp_suffix)
libomp_append(libomp_suffix .deb DEBUG_BUILD)
libomp_append(libomp_suffix .dia RELWITHDEBINFO_BUILD)
libomp_append(libomp_suffix .min MINSIZEREL_BUILD)
if(NOT "${LIBOMP_OMP_VERSION}" STREQUAL "45")
libomp_append(libomp_suffix .${LIBOMP_OMP_VERSION})
endif()
libomp_append(libomp_suffix .s1 LIBOMP_STATS)
libomp_append(libomp_suffix .ompt LIBOMP_OMPT_SUPPORT)
if(${LIBOMP_OMPT_SUPPORT})
@@ -96,4 +92,3 @@ if(WIN32)
COMMAND ${CMAKE_COMMAND} -E copy ${LIBOMPIMP_OUTPUT_DIRECTORY}/${LIBOMP_IMP_LIB_FILE} ${LIBOMP_EXPORTS_LIB_DIR}
)
endif()
+3 -4
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
+6 -20
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -159,14 +158,13 @@ function(libomp_get_libflags libflags)
if(${IA32})
libomp_append(libflags_local -lirc_pic LIBOMP_HAVE_IRC_PIC_LIBRARY)
endif()
IF(${CMAKE_SYSTEM_NAME} MATCHES "DragonFly")
if(${CMAKE_SYSTEM_NAME} MATCHES "DragonFly")
libomp_append(libflags_local "-Wl,--no-as-needed" LIBOMP_HAVE_AS_NEEDED_FLAG)
libomp_append(libflags_local "-lm")
libomp_append(libflags_local "-Wl,--as-needed" LIBOMP_HAVE_AS_NEEDED_FLAG)
ENDIF(${CMAKE_SYSTEM_NAME} MATCHES "DragonFly")
IF(${CMAKE_SYSTEM_NAME} MATCHES "NetBSD")
elseif(${CMAKE_SYSTEM_NAME} MATCHES "(Free|Net)BSD")
libomp_append(libflags_local -lm)
ENDIF(${CMAKE_SYSTEM_NAME} MATCHES "NetBSD")
endif()
set(libflags_local ${libflags_local} ${LIBOMP_LIBFLAGS})
libomp_setup_flags(libflags_local)
set(${libflags} ${libflags_local} PARENT_SCOPE)
@@ -200,18 +198,6 @@ function(libomp_get_gdflags gdflags)
libomp_append(gdflags_local "-D stub" STUBS_LIBRARY)
libomp_append(gdflags_local "-D HAVE_QUAD" LIBOMP_USE_QUAD_PRECISION)
libomp_append(gdflags_local "-D USE_DEBUGGER" LIBOMP_USE_DEBUGGER)
if(${LIBOMP_OMP_VERSION} GREATER 50 OR ${LIBOMP_OMP_VERSION} EQUAL 50)
libomp_append(gdflags_local "-D OMP_50")
endif()
if(${LIBOMP_OMP_VERSION} GREATER 45 OR ${LIBOMP_OMP_VERSION} EQUAL 45)
libomp_append(gdflags_local "-D OMP_45")
endif()
if(${LIBOMP_OMP_VERSION} GREATER 40 OR ${LIBOMP_OMP_VERSION} EQUAL 40)
libomp_append(gdflags_local "-D OMP_40")
endif()
if(${LIBOMP_OMP_VERSION} GREATER 30 OR ${LIBOMP_OMP_VERSION} EQUAL 30)
libomp_append(gdflags_local "-D OMP_30")
endif()
if(${DEBUG_BUILD} OR ${RELWITHDEBINFO_BUILD})
libomp_append(gdflags_local "-D KMP_DEBUG")
endif()
+4 -5
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -171,7 +170,7 @@ add_custom_command(
add_custom_target(libomp-test-deps DEPENDS test-deps/.success)
set(libomp_expected_library_deps)
if(CMAKE_SYSTEM_NAME MATCHES "FreeBSD")
set(libomp_expected_library_deps libc.so.7 libthr.so.3)
set(libomp_expected_library_deps libc.so.7 libthr.so.3 libm.so.5)
libomp_append(libomp_expected_library_deps libhwloc.so.5 LIBOMP_USE_HWLOC)
elseif(CMAKE_SYSTEM_NAME MATCHES "NetBSD")
set(libomp_expected_library_deps libc.so.12 libpthread.so.1 libm.so.0)
+3 -4
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
+3 -4
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
+3 -4
View File
@@ -4,10 +4,9 @@
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
+13 -12
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -74,7 +73,6 @@ else()
kmp_settings.cpp
kmp_str.cpp
kmp_tasking.cpp
kmp_taskq.cpp
kmp_threadprivate.cpp
kmp_utility.cpp
kmp_barrier.cpp
@@ -99,10 +97,8 @@ else()
libomp_append(LIBOMP_CXXFILES kmp_debugger.cpp LIBOMP_USE_DEBUGGER)
libomp_append(LIBOMP_CXXFILES kmp_stats.cpp LIBOMP_STATS)
libomp_append(LIBOMP_CXXFILES kmp_stats_timing.cpp LIBOMP_STATS)
if(${LIBOMP_OMP_VERSION} GREATER 40 OR ${LIBOMP_OMP_VERSION} EQUAL 40)
libomp_append(LIBOMP_CXXFILES kmp_taskdeps.cpp)
libomp_append(LIBOMP_CXXFILES kmp_cancel.cpp)
endif()
libomp_append(LIBOMP_CXXFILES kmp_taskdeps.cpp)
libomp_append(LIBOMP_CXXFILES kmp_cancel.cpp)
endif()
# Files common to stubs and normal library
libomp_append(LIBOMP_CXXFILES kmp_ftn_cdecl.cpp)
@@ -241,6 +237,11 @@ if(${LIBOMP_FORTRAN_MODULES})
configure_file(${LIBOMP_INC_DIR}/omp_lib.h.var omp_lib.h @ONLY)
configure_file(${LIBOMP_INC_DIR}/omp_lib.f.var omp_lib.f @ONLY)
configure_file(${LIBOMP_INC_DIR}/omp_lib.f90.var omp_lib.f90 @ONLY)
# Workaround for gfortran to build modules with the
# omp_sched_monotonic integer parameter
if (CMAKE_Fortran_COMPILER_ID STREQUAL "GNU")
set(ADDITIONAL_Fortran_FLAGS "-fno-range-check")
endif()
add_custom_target(libomp-mod ALL DEPENDS omp_lib.mod omp_lib_kinds.mod)
libomp_get_fflags(LIBOMP_CONFIGURED_FFLAGS)
if(CMAKE_Fortran_COMPILER_SUPPORTS_F90)
@@ -250,7 +251,8 @@ if(${LIBOMP_FORTRAN_MODULES})
endif()
add_custom_command(
OUTPUT omp_lib.mod omp_lib_kinds.mod
COMMAND ${CMAKE_Fortran_COMPILER} -c ${LIBOMP_CONFIGURED_FFLAGS} ${LIBOMP_FORTRAN_SOURCE_FILE}
COMMAND ${CMAKE_Fortran_COMPILER} -c ${ADDITIONAL_Fortran_FLAGS}
${LIBOMP_CONFIGURED_FFLAGS} ${LIBOMP_FORTRAN_SOURCE_FILE}
DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/${LIBOMP_FORTRAN_SOURCE_FILE}
${CMAKE_CURRENT_BINARY_DIR}/omp_lib.h
)
@@ -297,7 +299,7 @@ if(WIN32)
install(CODE "execute_process(COMMAND \"\${CMAKE_COMMAND}\" -E copy \"${LIBOMP_LIB_FILE}\"
\"${alias}${LIBOMP_LIBRARY_SUFFIX}\" WORKING_DIRECTORY \${CMAKE_INSTALL_PREFIX}/bin)")
install(CODE "execute_process(COMMAND \"\${CMAKE_COMMAND}\" -E copy \"${LIBOMP_IMP_LIB_FILE}\"
\"${alias}${LIBOMP_LIBRARY_SUFFIX}\" WORKING_DIRECTORY \${CMAKE_INSTALL_PREFIX}/${OPENMP_INSTALL_LIBDIR})")
\"${alias}${CMAKE_STATIC_LIBRARY_SUFFIX}\" WORKING_DIRECTORY \${CMAKE_INSTALL_PREFIX}/${OPENMP_INSTALL_LIBDIR})")
endforeach()
else()
@@ -331,4 +333,3 @@ if(${LIBOMP_FORTRAN_MODULES})
DESTINATION ${LIBOMP_HEADERS_INSTALL_PATH}
)
endif()
+39 -59
View File
@@ -1,10 +1,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -159,7 +158,7 @@
#
# Regular entry points
__kmp_wait_yield_4
__kmp_wait_4
__kmp_fork_call
__kmp_invoke_microtask
%ifdef KMP_USE_MONITOR
@@ -182,7 +181,6 @@
__kmp_printf
%endif
%ifdef USE_DEBUGGER
__kmp_debugging DATA
__kmp_omp_debug_struct_info DATA
@@ -191,14 +189,9 @@
# Symbols for MS mutual detection:
_You_must_link_with_exactly_one_OpenMP_library DATA
_You_must_link_with_Intel_OpenMP_library DATA
%ifdef msvc_compat
_You_must_link_with_Microsoft_OpenMP_library DATA
%endif
__kmp_wait_64
__kmp_release_64
# VT_getthid 1
# vtgthid 2
@@ -228,8 +221,8 @@
__kmpc_end_ordered 125
__kmpc_end_serialized_parallel 126
__kmpc_end_single 127
__kmpc_end_taskq 128
__kmpc_end_taskq_task 129
# __kmpc_end_taskq 128
# __kmpc_end_taskq_task 129
__kmpc_flush 130
__kmpc_for_static_fini 135
__kmpc_for_static_init_4 136
@@ -246,10 +239,10 @@
__kmpc_push_num_threads 148
__kmpc_serialized_parallel 150
__kmpc_single 151
__kmpc_task 152
__kmpc_task_buffer 153
__kmpc_taskq 154
__kmpc_taskq_task 155
# __kmpc_task 152
# __kmpc_task_buffer 153
# __kmpc_taskq 154
# __kmpc_taskq_task 155
__kmpc_threadprivate 156
__kmpc_threadprivate_cached 157
__kmpc_threadprivate_register 158
@@ -286,16 +279,12 @@
__kmpc_reduce 189
__kmpc_end_reduce 190
# OpenMP 3.0
%ifdef OMP_30
__kmpc_omp_task_alloc 191
__kmpc_omp_task 192
__kmpc_omp_taskwait 193
__kmpc_omp_task_begin_if0 196
__kmpc_omp_task_complete_if0 197
__kmpc_omp_task_parts 198
%endif # OMP_30
# __omp_collector_api 199
@@ -327,9 +316,7 @@ kmpc_set_stacksize_s 222
# kmpc_set_stats 217
kmpc_set_defaults 224
# OMP 3.0 entry points for unsigned loop iteration variables
%ifndef stub
%ifdef OMP_30
__kmpc_for_static_init_8u 225
__kmpc_dispatch_init_8u 226
__kmpc_dispatch_next_8u 227
@@ -338,7 +325,6 @@ kmpc_set_defaults 224
__kmpc_dispatch_init_4u 230
__kmpc_dispatch_next_4u 231
__kmpc_dispatch_fini_4u 232
%endif # OMP_30
%endif
%ifndef stub
@@ -346,17 +332,12 @@ kmpc_set_defaults 224
__kmpc_get_parent_taskid 234
%endif
# OpenMP 3.1 entry points
%ifndef stub
%ifdef OMP_30
__kmpc_omp_taskyield 235
%endif # OMP_30
# __kmpc_place_threads 236
%endif
# OpenMP 4.0 entry points
%ifndef stub
%ifdef OMP_40
__kmpc_push_proc_bind 237
__kmpc_taskgroup 238
__kmpc_end_taskgroup 239
@@ -379,12 +360,9 @@ kmpc_set_defaults 224
__kmpc_team_static_init_4u 256
__kmpc_team_static_init_8 257
__kmpc_team_static_init_8u 258
%endif # OMP_40
%endif
# OpenMP 4.5 entry points
%ifndef stub
%ifdef OMP_45
__kmpc_proxy_task_completed 259
__kmpc_proxy_task_completed_ooo 260
__kmpc_doacross_init 261
@@ -393,20 +371,22 @@ kmpc_set_defaults 224
__kmpc_doacross_fini 264
__kmpc_taskloop 266
__kmpc_critical_with_hint 270
%endif
%endif
kmpc_aligned_malloc 265
kmpc_set_disp_num_buffers 267
# OpenMP 5.0 entry points
%ifndef stub
%ifdef OMP_50
__kmpc_task_reduction_init 268
__kmpc_task_reduction_get_th_data 269
# USED FOR 4.5 __kmpc_critical_with_hint 270
# USED ABOVE __kmpc_critical_with_hint 270
__kmpc_get_target_offload 271
__kmpc_omp_reg_task_with_affinity 272
%endif
__kmpc_omp_reg_task_with_affinity 272
__kmpc_pause_resource 273
__kmpc_task_reduction_modifier_init 274
__kmpc_task_reduction_modifier_fini 275
__kmpc_task_allow_completion_event 276
__kmpc_taskred_init 277
__kmpc_taskred_modifier_init 278
%endif
# User API entry points that have both lower- and upper- case versions for Fortran.
@@ -464,7 +444,6 @@ kmp_aligned_malloc 747
kmp_set_warnings_on 779
kmp_set_warnings_off 780
%ifdef OMP_30
omp_get_active_level 789
omp_get_level 790
omp_get_ancestor_thread_num 791
@@ -489,17 +468,9 @@ kmp_set_warnings_off 780
kmpc_unset_affinity_mask_proc 858
kmp_get_affinity_mask_proc 859
kmpc_get_affinity_mask_proc 860
%endif # OMP_30
# OpenMP 3.1
%ifdef OMP_30
omp_in_final 861
%endif # OMP_30
# OpenMP 40
%ifdef OMP_40
omp_get_proc_bind 862
#omp_set_proc_bind 863
#omp_curr_proc_bind 864
@@ -511,11 +482,7 @@ kmp_set_warnings_off 780
omp_set_default_device 879
omp_get_default_device 880
omp_get_num_devices 881
%endif # OMP_40
# OpenMP 45
%ifdef OMP_45
omp_init_lock_with_hint 870
omp_init_nest_lock_with_hint 871
omp_get_max_task_priority 872
@@ -535,17 +502,25 @@ kmp_set_warnings_off 780
omp_target_associate_ptr 888
omp_target_disassociate_ptr 889
%endif
%endif # OMP_45
kmp_set_disp_num_buffers 890
%ifdef OMP_50
omp_control_tool 891
omp_set_default_allocator 892
omp_get_default_allocator 893
omp_alloc 894
omp_free 895
omp_get_device_num 896
omp_init_allocator 897
omp_destroy_allocator 898
%ifndef stub
__kmpc_set_default_allocator
__kmpc_get_default_allocator
__kmpc_alloc
__kmpc_free
__kmpc_init_allocator
__kmpc_destroy_allocator
%endif
omp_set_affinity_format 748
omp_get_affinity_format 749
omp_display_affinity 750
@@ -554,8 +529,12 @@ kmp_set_disp_num_buffers 890
ompc_get_affinity_format 753
ompc_display_affinity 754
ompc_capture_affinity 755
omp_pause_resource 756
omp_pause_resource_all 757
omp_get_supported_active_levels 758
omp_fulfill_event 759
OMP_NULL_ALLOCATOR DATA
omp_null_allocator DATA
omp_default_mem_alloc DATA
omp_large_cap_mem_alloc DATA
omp_const_mem_alloc DATA
@@ -564,7 +543,12 @@ kmp_set_disp_num_buffers 890
omp_cgroup_mem_alloc DATA
omp_pteam_mem_alloc DATA
omp_thread_mem_alloc DATA
%endif # OMP_50
omp_default_mem_space DATA
omp_large_cap_mem_space DATA
omp_const_mem_space DATA
omp_high_bw_mem_space DATA
omp_low_lat_mem_space DATA
%ifndef stub
# Ordinals between 900 and 999 are reserved
@@ -1014,8 +998,6 @@ kmp_set_disp_num_buffers 890
__kmpc_atomic_float10_div_cpt_fp
%endif
%ifdef OMP_40
# ATOMIC extensions for OpenMP 4.0 spec (x86 and x64 only)
__kmpc_atomic_fixed1_swp 2412
@@ -1190,8 +1172,6 @@ kmp_set_disp_num_buffers 890
__kmpc_atomic_float10_sub_cpt_rev_fp
__kmpc_atomic_float10_div_cpt_rev_fp
%endif
%endif # OMP_40
%endif # arch_64
+4 -7
View File
@@ -3,10 +3,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -39,7 +38,6 @@ VERSION {
_You_must_link_with_*; # Mutual detection/MS compatibility symbols.
#
# Debugger support.
#
@@ -55,7 +53,6 @@ VERSION {
___kmp_allocate;
___kmp_free;
__kmp_thread_pool;
__kmp_thread_pool_nth;
__kmp_reset_stats;
@@ -84,7 +81,7 @@ VERSION {
__kmp_reap_worker;
__kmp_release_64;
__kmp_wait_64;
__kmp_wait_yield_4;
__kmp_wait_4;
# ittnotify symbols to be used by debugger
__kmp_itt_fini_ittlib;
+3 -4
View File
@@ -4,10 +4,9 @@
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
+4 -6
View File
@@ -3,10 +3,9 @@
#
#//===----------------------------------------------------------------------===//
#//
#// The LLVM Compiler Infrastructure
#//
#// This file is dual licensed under the MIT and the University of Illinois Open
#// Source Licenses. See LICENSE.txt for details.
#// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
#// See https://llvm.org/LICENSE.txt for license information.
#// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
#//
#//===----------------------------------------------------------------------===//
#
@@ -426,7 +425,7 @@ AffHWSubsetManyTiles "KMP_HW_SUBSET ignored: too many L2 Caches requeste
AffHWSubsetManyProcs "KMP_HW_SUBSET ignored: too many Procs requested."
HierSchedInvalid "Hierarchy ignored: unsupported level: %1$s."
AffFormatDefault "OMP: pid %1$s tid %2$s thread %3$s bound to OS proc set {%4$s}"
APIDeprecated "%1$s routine deprecated, please use %2$s instead."
# --------------------------------------------------------------------------------------------------
-*- HINTS -*-
@@ -490,4 +489,3 @@ SystemLimitOnThreads "System-related limit on the number of threads."
# --------------------------------------------------------------------------------------------------
# end of file #
# --------------------------------------------------------------------------------------------------
-165
View File
@@ -1,165 +0,0 @@
/*
* include/30/omp.h.var
*/
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
//
//===----------------------------------------------------------------------===//
#ifndef __OMP_H
# define __OMP_H
# define KMP_VERSION_MAJOR @LIBOMP_VERSION_MAJOR@
# define KMP_VERSION_MINOR @LIBOMP_VERSION_MINOR@
# define KMP_VERSION_BUILD @LIBOMP_VERSION_BUILD@
# define KMP_BUILD_DATE "@LIBOMP_BUILD_DATE@"
# ifdef __cplusplus
extern "C" {
# endif
# define omp_set_num_threads ompc_set_num_threads
# define omp_set_dynamic ompc_set_dynamic
# define omp_set_nested ompc_set_nested
# define omp_set_max_active_levels ompc_set_max_active_levels
# define omp_set_schedule ompc_set_schedule
# define omp_get_ancestor_thread_num ompc_get_ancestor_thread_num
# define omp_get_team_size ompc_get_team_size
# define kmp_set_stacksize kmpc_set_stacksize
# define kmp_set_stacksize_s kmpc_set_stacksize_s
# define kmp_set_blocktime kmpc_set_blocktime
# define kmp_set_library kmpc_set_library
# define kmp_set_defaults kmpc_set_defaults
# define kmp_set_affinity_mask_proc kmpc_set_affinity_mask_proc
# define kmp_unset_affinity_mask_proc kmpc_unset_affinity_mask_proc
# define kmp_get_affinity_mask_proc kmpc_get_affinity_mask_proc
# define kmp_malloc kmpc_malloc
# define kmp_calloc kmpc_calloc
# define kmp_realloc kmpc_realloc
# define kmp_free kmpc_free
# if defined(_WIN32)
# define __KAI_KMPC_CONVENTION __cdecl
# else
# define __KAI_KMPC_CONVENTION
# endif
/* schedule kind constants */
typedef enum omp_sched_t {
omp_sched_static = 1,
omp_sched_dynamic = 2,
omp_sched_guided = 3,
omp_sched_auto = 4
} omp_sched_t;
/* set API functions */
extern void __KAI_KMPC_CONVENTION omp_set_num_threads (int);
extern void __KAI_KMPC_CONVENTION omp_set_dynamic (int);
extern void __KAI_KMPC_CONVENTION omp_set_nested (int);
extern void __KAI_KMPC_CONVENTION omp_set_max_active_levels (int);
extern void __KAI_KMPC_CONVENTION omp_set_schedule (omp_sched_t, int);
/* query API functions */
extern int __KAI_KMPC_CONVENTION omp_get_num_threads (void);
extern int __KAI_KMPC_CONVENTION omp_get_dynamic (void);
extern int __KAI_KMPC_CONVENTION omp_get_nested (void);
extern int __KAI_KMPC_CONVENTION omp_get_max_threads (void);
extern int __KAI_KMPC_CONVENTION omp_get_thread_num (void);
extern int __KAI_KMPC_CONVENTION omp_get_num_procs (void);
extern int __KAI_KMPC_CONVENTION omp_in_parallel (void);
extern int __KAI_KMPC_CONVENTION omp_in_final (void);
extern int __KAI_KMPC_CONVENTION omp_get_active_level (void);
extern int __KAI_KMPC_CONVENTION omp_get_level (void);
extern int __KAI_KMPC_CONVENTION omp_get_ancestor_thread_num (int);
extern int __KAI_KMPC_CONVENTION omp_get_team_size (int);
extern int __KAI_KMPC_CONVENTION omp_get_thread_limit (void);
extern int __KAI_KMPC_CONVENTION omp_get_max_active_levels (void);
extern void __KAI_KMPC_CONVENTION omp_get_schedule (omp_sched_t *, int *);
/* lock API functions */
typedef struct omp_lock_t {
void * _lk;
} omp_lock_t;
extern void __KAI_KMPC_CONVENTION omp_init_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_set_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_unset_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_destroy_lock (omp_lock_t *);
extern int __KAI_KMPC_CONVENTION omp_test_lock (omp_lock_t *);
/* nested lock API functions */
typedef struct omp_nest_lock_t {
void * _lk;
} omp_nest_lock_t;
extern void __KAI_KMPC_CONVENTION omp_init_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_set_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_unset_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_destroy_nest_lock (omp_nest_lock_t *);
extern int __KAI_KMPC_CONVENTION omp_test_nest_lock (omp_nest_lock_t *);
/* time API functions */
extern double __KAI_KMPC_CONVENTION omp_get_wtime (void);
extern double __KAI_KMPC_CONVENTION omp_get_wtick (void);
# include <stdlib.h>
/* kmp API functions */
extern int __KAI_KMPC_CONVENTION kmp_get_stacksize (void);
extern void __KAI_KMPC_CONVENTION kmp_set_stacksize (int);
extern size_t __KAI_KMPC_CONVENTION kmp_get_stacksize_s (void);
extern void __KAI_KMPC_CONVENTION kmp_set_stacksize_s (size_t);
extern int __KAI_KMPC_CONVENTION kmp_get_blocktime (void);
extern int __KAI_KMPC_CONVENTION kmp_get_library (void);
extern void __KAI_KMPC_CONVENTION kmp_set_blocktime (int);
extern void __KAI_KMPC_CONVENTION kmp_set_library (int);
extern void __KAI_KMPC_CONVENTION kmp_set_library_serial (void);
extern void __KAI_KMPC_CONVENTION kmp_set_library_turnaround (void);
extern void __KAI_KMPC_CONVENTION kmp_set_library_throughput (void);
extern void __KAI_KMPC_CONVENTION kmp_set_defaults (char const *);
/* affinity API functions */
typedef void * kmp_affinity_mask_t;
extern int __KAI_KMPC_CONVENTION kmp_set_affinity (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity_max_proc (void);
extern void __KAI_KMPC_CONVENTION kmp_create_affinity_mask (kmp_affinity_mask_t *);
extern void __KAI_KMPC_CONVENTION kmp_destroy_affinity_mask (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_set_affinity_mask_proc (int, kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_unset_affinity_mask_proc (int, kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity_mask_proc (int, kmp_affinity_mask_t *);
extern void * __KAI_KMPC_CONVENTION kmp_malloc (size_t);
extern void * __KAI_KMPC_CONVENTION kmp_aligned_malloc (size_t, size_t);
extern void * __KAI_KMPC_CONVENTION kmp_calloc (size_t, size_t);
extern void * __KAI_KMPC_CONVENTION kmp_realloc (void *, size_t);
extern void __KAI_KMPC_CONVENTION kmp_free (void *);
extern void __KAI_KMPC_CONVENTION kmp_set_warnings_on(void);
extern void __KAI_KMPC_CONVENTION kmp_set_warnings_off(void);
# undef __KAI_KMPC_CONVENTION
/* Warning:
The following typedefs are not standard, deprecated and will be removed in a future release.
*/
typedef int omp_int_t;
typedef double omp_wtime_t;
# ifdef __cplusplus
}
# endif
#endif /* __OMP_H */
-644
View File
@@ -1,644 +0,0 @@
! include/30/omp_lib.f.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
!***
!*** Some of the directives for the following routine extend past column 72,
!*** so process this file in 132-column mode.
!***
!dec$ fixedformlinesize:132
module omp_lib_kinds
integer, parameter :: omp_integer_kind = 4
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = 4
integer, parameter :: omp_lock_kind = int_ptr_kind()
integer, parameter :: omp_nest_lock_kind = int_ptr_kind()
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = int_ptr_kind()
integer, parameter :: kmp_size_t_kind = int_ptr_kind()
integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
end module omp_lib_kinds
module omp_lib
use omp_lib_kinds
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*), parameter :: kmp_build_date = '@LIBOMP_BUILD_DATE@'
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(nthreads)
use omp_lib_kinds
integer (kind=omp_integer_kind) nthreads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(enable)
use omp_lib_kinds
logical (kind=omp_logical_kind) enable
end subroutine omp_set_dynamic
subroutine omp_set_nested(enable)
use omp_lib_kinds
logical (kind=omp_logical_kind) enable
end subroutine omp_set_nested
function omp_get_num_threads()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_get_dynamic()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels)
use omp_lib_kinds
integer (kind=omp_integer_kind) max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level)
use omp_lib_kinds
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
end function omp_get_ancestor_thread_num
function omp_get_team_size(level)
use omp_lib_kinds
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_team_size
end function omp_get_team_size
subroutine omp_set_schedule(kind, modifier)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) modifier
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, modifier)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) modifier
end subroutine omp_get_schedule
function omp_get_wtime()
double precision omp_get_wtime
end function omp_get_wtime
function omp_get_wtick ()
double precision omp_get_wtick
end function omp_get_wtick
subroutine omp_init_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_init_lock
subroutine omp_destroy_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_destroy_lock
subroutine omp_set_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_set_lock
subroutine omp_unset_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_unset_lock
function omp_test_lock(lockvar)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) lockvar
end function omp_test_lock
subroutine omp_init_nest_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(lockvar)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) lockvar
end function omp_test_nest_lock
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size)
use omp_lib_kinds
integer (kind=omp_integer_kind) size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size)
use omp_lib_kinds
integer (kind=kmp_size_t_kind) size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec)
use omp_lib_kinds
integer (kind=omp_integer_kind) msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial()
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround()
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput()
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum)
use omp_lib_kinds
integer (kind=omp_integer_kind) libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string)
character*(*) string
end subroutine kmp_set_defaults
function kmp_get_stacksize()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s()
use omp_lib_kinds
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
function kmp_set_affinity(mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind) size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind) size
integer (kind=kmp_size_t_kind) alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind) nelem
integer (kind=kmp_size_t_kind) elsize
end function kmp_calloc
function kmp_realloc(ptr, size)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind) ptr
integer (kind=kmp_size_t_kind) size
end function kmp_realloc
subroutine kmp_free(ptr)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on()
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off()
end subroutine kmp_set_warnings_off
end interface
!dec$ if defined(_WIN32)
!dec$ if defined(_WIN64) .or. defined(_M_AMD64)
!***
!*** The Fortran entry points must be in uppercase, even if the /Qlowercase
!*** option is specified. The alias attribute ensures that the specified
!*** string is used as the entry point.
!***
!*** On the Windows* OS IA-32 architecture, the Fortran entry points have an
!*** underscore prepended. On the Windows* OS Intel(R) 64
!*** architecture, no underscore is prepended.
!***
!dec$ attributes alias:'OMP_SET_NUM_THREADS' :: omp_set_num_threads
!dec$ attributes alias:'OMP_SET_DYNAMIC' :: omp_set_dynamic
!dec$ attributes alias:'OMP_SET_NESTED' :: omp_set_nested
!dec$ attributes alias:'OMP_GET_NUM_THREADS' :: omp_get_num_threads
!dec$ attributes alias:'OMP_GET_MAX_THREADS' :: omp_get_max_threads
!dec$ attributes alias:'OMP_GET_THREAD_NUM' :: omp_get_thread_num
!dec$ attributes alias:'OMP_GET_NUM_PROCS' :: omp_get_num_procs
!dec$ attributes alias:'OMP_IN_PARALLEL' :: omp_in_parallel
!dec$ attributes alias:'OMP_GET_DYNAMIC' :: omp_get_dynamic
!dec$ attributes alias:'OMP_GET_NESTED' :: omp_get_nested
!dec$ attributes alias:'OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
!dec$ attributes alias:'OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
!dec$ attributes alias:'OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
!dec$ attributes alias:'OMP_GET_LEVEL' :: omp_get_level
!dec$ attributes alias:'OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
!dec$ attributes alias:'OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
!dec$ attributes alias:'OMP_GET_TEAM_SIZE' :: omp_get_team_size
!dec$ attributes alias:'OMP_SET_SCHEDULE' :: omp_set_schedule
!dec$ attributes alias:'OMP_GET_SCHEDULE' :: omp_get_schedule
!dec$ attributes alias:'OMP_GET_WTIME' :: omp_get_wtime
!dec$ attributes alias:'OMP_GET_WTICK' :: omp_get_wtick
!dec$ attributes alias:'omp_init_lock' :: omp_init_lock
!dec$ attributes alias:'omp_destroy_lock' :: omp_destroy_lock
!dec$ attributes alias:'omp_set_lock' :: omp_set_lock
!dec$ attributes alias:'omp_unset_lock' :: omp_unset_lock
!dec$ attributes alias:'omp_test_lock' :: omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock' :: omp_init_nest_lock
!dec$ attributes alias:'omp_destroy_nest_lock' :: omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock' :: omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock' :: omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock' :: omp_test_nest_lock
!dec$ attributes alias:'KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'KMP_FREE'::kmp_free
!dec$ attributes alias:'KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ else
!***
!*** On Windows* OS IA-32 architecture, the Fortran entry points have an underscore prepended.
!***
!dec$ attributes alias:'_OMP_SET_NUM_THREADS' :: omp_set_num_threads
!dec$ attributes alias:'_OMP_SET_DYNAMIC' :: omp_set_dynamic
!dec$ attributes alias:'_OMP_SET_NESTED' :: omp_set_nested
!dec$ attributes alias:'_OMP_GET_NUM_THREADS' :: omp_get_num_threads
!dec$ attributes alias:'_OMP_GET_MAX_THREADS' :: omp_get_max_threads
!dec$ attributes alias:'_OMP_GET_THREAD_NUM' :: omp_get_thread_num
!dec$ attributes alias:'_OMP_GET_NUM_PROCS' :: omp_get_num_procs
!dec$ attributes alias:'_OMP_IN_PARALLEL' :: omp_in_parallel
!dec$ attributes alias:'_OMP_GET_DYNAMIC' :: omp_get_dynamic
!dec$ attributes alias:'_OMP_GET_NESTED' :: omp_get_nested
!dec$ attributes alias:'_OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
!dec$ attributes alias:'_OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
!dec$ attributes alias:'_OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
!dec$ attributes alias:'_OMP_GET_LEVEL' :: omp_get_level
!dec$ attributes alias:'_OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
!dec$ attributes alias:'_OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
!dec$ attributes alias:'_OMP_GET_TEAM_SIZE' :: omp_get_team_size
!dec$ attributes alias:'_OMP_SET_SCHEDULE' :: omp_set_schedule
!dec$ attributes alias:'_OMP_GET_SCHEDULE' :: omp_get_schedule
!dec$ attributes alias:'_OMP_GET_WTIME' :: omp_get_wtime
!dec$ attributes alias:'_OMP_GET_WTICK' :: omp_get_wtick
!dec$ attributes alias:'_omp_init_lock' :: omp_init_lock
!dec$ attributes alias:'_omp_destroy_lock' :: omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock' :: omp_set_lock
!dec$ attributes alias:'_omp_unset_lock' :: omp_unset_lock
!dec$ attributes alias:'_omp_test_lock' :: omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock' :: omp_init_nest_lock
!dec$ attributes alias:'_omp_destroy_nest_lock' :: omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock' :: omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock' :: omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock' :: omp_test_nest_lock
!dec$ attributes alias:'_KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'_KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'_KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'_KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'_KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'_KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'_KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'_KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'_KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'_KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'_KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'_KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'_KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'_KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'_KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'_KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'_KMP_FREE'::kmp_free
!dec$ attributes alias:'_KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'_KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ endif
!dec$ endif
!dec$ if defined(__linux)
!***
!*** The Linux* OS entry points are in lowercase, with an underscore appended.
!***
!dec$ attributes alias:'omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'omp_get_level_'::omp_get_level
!dec$ attributes alias:'omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'kmp_free_'::kmp_free
!dec$ attributes alias:'kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ endif
!dec$ if defined(__APPLE__)
!***
!*** The Mac entry points are in lowercase, with an both an underscore
!*** appended and an underscore prepended.
!***
!dec$ attributes alias:'_omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'_omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'_omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'_omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'_omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'_omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'_omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'_omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'_omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'_omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'_omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'_omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'_omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'_omp_get_level_'::omp_get_level
!dec$ attributes alias:'_omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'_omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'_omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'_omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'_omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'_omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'_omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'_omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'_omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'_omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'_omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'_omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'_kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'_kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'_kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'_kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'_kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'_kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'_kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'_kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'_kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'_kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'_kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'_kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'_kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'_kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'_kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'_kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'_kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'_kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'_kmp_free_'::kmp_free
!dec$ attributes alias:'_kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'_kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ endif
end module omp_lib
-365
View File
@@ -1,365 +0,0 @@
! include/30/omp_lib.f90.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
module omp_lib_kinds
use, intrinsic :: iso_c_binding
integer, parameter :: omp_integer_kind = c_int
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = c_float
integer, parameter :: kmp_double_kind = c_double
integer, parameter :: omp_lock_kind = c_intptr_t
integer, parameter :: omp_nest_lock_kind = c_intptr_t
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = c_intptr_t
integer, parameter :: kmp_size_t_kind = c_size_t
integer, parameter :: kmp_affinity_mask_kind = c_intptr_t
end module omp_lib_kinds
module omp_lib
use omp_lib_kinds
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*) kmp_build_date
parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(nthreads) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: nthreads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(enable) bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind), value :: enable
end subroutine omp_set_dynamic
subroutine omp_set_nested(enable) bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind), value :: enable
end subroutine omp_set_nested
function omp_get_num_threads() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) :: omp_get_level
end function omp_get_level
function omp_get_active_level() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) :: omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
integer (kind=omp_integer_kind), value :: level
end function omp_get_ancestor_thread_num
function omp_get_team_size(level) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_team_size
integer (kind=omp_integer_kind), value :: level
end function omp_get_team_size
subroutine omp_set_schedule(kind, modifier) bind(c)
use omp_lib_kinds
integer (kind=omp_sched_kind), value :: kind
integer (kind=omp_integer_kind), value :: modifier
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, modifier) bind(c)
use omp_lib_kinds
integer (kind=omp_sched_kind) :: kind
integer (kind=omp_integer_kind) :: modifier
end subroutine omp_get_schedule
function omp_get_wtime() bind(c)
use omp_lib_kinds
real (kind=kmp_double_kind) omp_get_wtime
end function omp_get_wtime
function omp_get_wtick() bind(c)
use omp_lib_kinds
real (kind=kmp_double_kind) omp_get_wtick
end function omp_get_wtick
subroutine omp_init_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_init_lock
subroutine omp_destroy_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_destroy_lock
subroutine omp_set_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_set_lock
subroutine omp_unset_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_lock_kind) lockvar
end subroutine omp_unset_lock
function omp_test_lock(lockvar) bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) lockvar
end function omp_test_lock
subroutine omp_init_nest_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(lockvar) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) lockvar
end function omp_test_nest_lock
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size) bind(c)
use omp_lib_kinds
integer (kind=kmp_size_t_kind), value :: size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial() bind(c)
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround() bind(c)
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput() bind(c)
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string) bind(c)
use, intrinsic :: iso_c_binding
character (kind=c_char) :: string(*)
end subroutine kmp_set_defaults
function kmp_get_stacksize() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s() bind(c)
use omp_lib_kinds
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
function kmp_set_affinity(mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask) bind(c)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask) bind(c)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind), value :: size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind), value :: size
integer (kind=kmp_size_t_kind), value :: alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind), value :: nelem
integer (kind=kmp_size_t_kind), value :: elsize
end function kmp_calloc
function kmp_realloc(ptr, size) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind), value :: ptr
integer (kind=kmp_size_t_kind), value :: size
end function kmp_realloc
subroutine kmp_free(ptr) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind), value :: ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on() bind(c)
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off() bind(c)
end subroutine kmp_set_warnings_off
end interface
end module omp_lib
-649
View File
@@ -1,649 +0,0 @@
! include/30/omp_lib.h.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
!***
!*** Some of the directives for the following routine extend past column 72,
!*** so process this file in 132-column mode.
!***
!dec$ fixedformlinesize:132
integer, parameter :: omp_integer_kind = 4
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = 4
integer, parameter :: omp_lock_kind = int_ptr_kind()
integer, parameter :: omp_nest_lock_kind = int_ptr_kind()
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = int_ptr_kind()
integer, parameter :: kmp_size_t_kind = int_ptr_kind()
integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*) kmp_build_date
parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(nthreads)
import
integer (kind=omp_integer_kind) nthreads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(enable)
import
logical (kind=omp_logical_kind) enable
end subroutine omp_set_dynamic
subroutine omp_set_nested(enable)
import
logical (kind=omp_logical_kind) enable
end subroutine omp_set_nested
function omp_get_num_threads()
import
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads()
import
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num()
import
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs()
import
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel()
import
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final()
import
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic()
import
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested()
import
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit()
import
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels)
import
integer (kind=omp_integer_kind) max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels()
import
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level()
import
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level()
import
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level)
import
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
end function omp_get_ancestor_thread_num
function omp_get_team_size(level)
import
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_team_size
end function omp_get_team_size
subroutine omp_set_schedule(kind, modifier)
import
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) modifier
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, modifier)
import
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) modifier
end subroutine omp_get_schedule
function omp_get_wtime()
double precision omp_get_wtime
end function omp_get_wtime
function omp_get_wtick ()
double precision omp_get_wtick
end function omp_get_wtick
subroutine omp_init_lock(lockvar)
import
integer (kind=omp_lock_kind) lockvar
end subroutine omp_init_lock
subroutine omp_destroy_lock(lockvar)
import
integer (kind=omp_lock_kind) lockvar
end subroutine omp_destroy_lock
subroutine omp_set_lock(lockvar)
import
integer (kind=omp_lock_kind) lockvar
end subroutine omp_set_lock
subroutine omp_unset_lock(lockvar)
import
integer (kind=omp_lock_kind) lockvar
end subroutine omp_unset_lock
function omp_test_lock(lockvar)
import
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) lockvar
end function omp_test_lock
subroutine omp_init_nest_lock(lockvar)
import
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(lockvar)
import
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(lockvar)
import
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(lockvar)
import
integer (kind=omp_nest_lock_kind) lockvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(lockvar)
import
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) lockvar
end function omp_test_nest_lock
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size)
import
integer (kind=omp_integer_kind) size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size)
import
integer (kind=kmp_size_t_kind) size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec)
import
integer (kind=omp_integer_kind) msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial()
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround()
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput()
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum)
import
integer (kind=omp_integer_kind) libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string)
character*(*) string
end subroutine kmp_set_defaults
function kmp_get_stacksize()
import
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s()
import
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime()
import
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library()
import
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
function kmp_set_affinity(mask)
import
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask)
import
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc()
import
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask)
import
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask)
import
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask)
import
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask)
import
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask)
import
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size)
import
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind) size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment)
import
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind) size
integer (kind=kmp_size_t_kind) alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize)
import
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind) nelem
integer (kind=kmp_size_t_kind) elsize
end function kmp_calloc
function kmp_realloc(ptr, size)
import
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind) ptr
integer (kind=kmp_size_t_kind) size
end function kmp_realloc
subroutine kmp_free(ptr)
import
integer (kind=kmp_pointer_kind) ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on()
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off()
end subroutine kmp_set_warnings_off
end interface
!dec$ if defined(_WIN32)
!dec$ if defined(_WIN64) .or. defined(_M_AMD64)
!***
!*** The Fortran entry points must be in uppercase, even if the /Qlowercase
!*** option is specified. The alias attribute ensures that the specified
!*** string is used as the entry point.
!***
!*** On the Windows* OS IA-32 architecture, the Fortran entry points have an
!*** underscore prepended. On the Windows* OS Intel(R) 64
!*** architecture, no underscore is prepended.
!***
!dec$ attributes alias:'OMP_SET_NUM_THREADS'::omp_set_num_threads
!dec$ attributes alias:'OMP_SET_DYNAMIC'::omp_set_dynamic
!dec$ attributes alias:'OMP_SET_NESTED'::omp_set_nested
!dec$ attributes alias:'OMP_GET_NUM_THREADS'::omp_get_num_threads
!dec$ attributes alias:'OMP_GET_MAX_THREADS'::omp_get_max_threads
!dec$ attributes alias:'OMP_GET_THREAD_NUM'::omp_get_thread_num
!dec$ attributes alias:'OMP_GET_NUM_PROCS'::omp_get_num_procs
!dec$ attributes alias:'OMP_IN_PARALLEL'::omp_in_parallel
!dec$ attributes alias:'OMP_IN_FINAL'::omp_in_final
!dec$ attributes alias:'OMP_GET_DYNAMIC'::omp_get_dynamic
!dec$ attributes alias:'OMP_GET_NESTED'::omp_get_nested
!dec$ attributes alias:'OMP_GET_THREAD_LIMIT'::omp_get_thread_limit
!dec$ attributes alias:'OMP_SET_MAX_ACTIVE_LEVELS'::omp_set_max_active_levels
!dec$ attributes alias:'OMP_GET_MAX_ACTIVE_LEVELS'::omp_get_max_active_levels
!dec$ attributes alias:'OMP_GET_LEVEL'::omp_get_level
!dec$ attributes alias:'OMP_GET_ACTIVE_LEVEL'::omp_get_active_level
!dec$ attributes alias:'OMP_GET_ANCESTOR_THREAD_NUM'::omp_get_ancestor_thread_num
!dec$ attributes alias:'OMP_GET_TEAM_SIZE'::omp_get_team_size
!dec$ attributes alias:'OMP_SET_SCHEDULE'::omp_set_schedule
!dec$ attributes alias:'OMP_GET_SCHEDULE'::omp_get_schedule
!dec$ attributes alias:'OMP_GET_WTIME'::omp_get_wtime
!dec$ attributes alias:'OMP_GET_WTICK'::omp_get_wtick
!dec$ attributes alias:'omp_init_lock'::omp_init_lock
!dec$ attributes alias:'omp_destroy_lock'::omp_destroy_lock
!dec$ attributes alias:'omp_set_lock'::omp_set_lock
!dec$ attributes alias:'omp_unset_lock'::omp_unset_lock
!dec$ attributes alias:'omp_test_lock'::omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock'::omp_init_nest_lock
!dec$ attributes alias:'omp_destroy_nest_lock'::omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock'::omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock'::omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock'::omp_test_nest_lock
!dec$ attributes alias:'KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'KMP_SET_DEFAULTS'::kmp_set_defaults
!dec$ attributes alias:'KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'KMP_FREE'::kmp_free
!dec$ attributes alias:'KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ else
!***
!*** On Windows* OS IA-32 architecture, the Fortran entry points have an underscore prepended.
!***
!dec$ attributes alias:'_OMP_SET_NUM_THREADS'::omp_set_num_threads
!dec$ attributes alias:'_OMP_SET_DYNAMIC'::omp_set_dynamic
!dec$ attributes alias:'_OMP_SET_NESTED'::omp_set_nested
!dec$ attributes alias:'_OMP_GET_NUM_THREADS'::omp_get_num_threads
!dec$ attributes alias:'_OMP_GET_MAX_THREADS'::omp_get_max_threads
!dec$ attributes alias:'_OMP_GET_THREAD_NUM'::omp_get_thread_num
!dec$ attributes alias:'_OMP_GET_NUM_PROCS'::omp_get_num_procs
!dec$ attributes alias:'_OMP_IN_PARALLEL'::omp_in_parallel
!dec$ attributes alias:'_OMP_IN_FINAL'::omp_in_final
!dec$ attributes alias:'_OMP_GET_DYNAMIC'::omp_get_dynamic
!dec$ attributes alias:'_OMP_GET_NESTED'::omp_get_nested
!dec$ attributes alias:'_OMP_GET_THREAD_LIMIT'::omp_get_thread_limit
!dec$ attributes alias:'_OMP_SET_MAX_ACTIVE_LEVELS'::omp_set_max_active_levels
!dec$ attributes alias:'_OMP_GET_MAX_ACTIVE_LEVELS'::omp_get_max_active_levels
!dec$ attributes alias:'_OMP_GET_LEVEL'::omp_get_level
!dec$ attributes alias:'_OMP_GET_ACTIVE_LEVEL'::omp_get_active_level
!dec$ attributes alias:'_OMP_GET_ANCESTOR_THREAD_NUM'::omp_get_ancestor_thread_num
!dec$ attributes alias:'_OMP_GET_TEAM_SIZE'::omp_get_team_size
!dec$ attributes alias:'_OMP_SET_SCHEDULE'::omp_set_schedule
!dec$ attributes alias:'_OMP_GET_SCHEDULE'::omp_get_schedule
!dec$ attributes alias:'_OMP_GET_WTIME'::omp_get_wtime
!dec$ attributes alias:'_OMP_GET_WTICK'::omp_get_wtick
!dec$ attributes alias:'_omp_init_lock'::omp_init_lock
!dec$ attributes alias:'_omp_destroy_lock'::omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock'::omp_set_lock
!dec$ attributes alias:'_omp_unset_lock'::omp_unset_lock
!dec$ attributes alias:'_omp_test_lock'::omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock'::omp_init_nest_lock
!dec$ attributes alias:'_omp_destroy_nest_lock'::omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock'::omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock'::omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock'::omp_test_nest_lock
!dec$ attributes alias:'_KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'_KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'_KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'_KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'_KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'_KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'_KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'_KMP_SET_DEFAULTS'::kmp_set_defaults
!dec$ attributes alias:'_KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'_KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'_KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'_KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'_KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'_KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'_KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'_KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'_KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'_KMP_FREE'::kmp_free
!dec$ attributes alias:'_KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'_KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ endif
!dec$ endif
!dec$ if defined(__linux)
!***
!*** The Linux* OS entry points are in lowercase, with an underscore appended.
!***
!dec$ attributes alias:'omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'omp_in_final_'::omp_in_final
!dec$ attributes alias:'omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'omp_get_level_'::omp_get_level
!dec$ attributes alias:'omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'kmp_set_defaults_'::kmp_set_defaults
!dec$ attributes alias:'kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'kmp_free_'::kmp_free
!dec$ attributes alias:'kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ endif
!dec$ if defined(__APPLE__)
!***
!*** The Mac entry points are in lowercase, with an both an underscore
!*** appended and an underscore prepended.
!***
!dec$ attributes alias:'_omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'_omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'_omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'_omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'_omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'_omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'_omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'_omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'_omp_in_final_'::omp_in_final
!dec$ attributes alias:'_omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'_omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'_omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'_omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'_omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'_omp_get_level_'::omp_get_level
!dec$ attributes alias:'_omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'_omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'_omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'_omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'_omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'_omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'_omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'_omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'_omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'_omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'_omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'_omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'_kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'_kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'_kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'_kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'_kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'_kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'_kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'_kmp_set_defaults_'::kmp_set_defaults
!dec$ attributes alias:'_kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'_kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'_kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'_kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'_kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'_kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'_kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'_kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'_kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'_kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'_kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'_kmp_free_'::kmp_free
!dec$ attributes alias:'_kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'_kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ endif
-161
View File
@@ -1,161 +0,0 @@
/*
* include/40/omp.h.var
*/
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
//
//===----------------------------------------------------------------------===//
#ifndef __OMP_H
# define __OMP_H
# define KMP_VERSION_MAJOR @LIBOMP_VERSION_MAJOR@
# define KMP_VERSION_MINOR @LIBOMP_VERSION_MINOR@
# define KMP_VERSION_BUILD @LIBOMP_VERSION_BUILD@
# define KMP_BUILD_DATE "@LIBOMP_BUILD_DATE@"
# ifdef __cplusplus
extern "C" {
# endif
# if defined(_WIN32)
# define __KAI_KMPC_CONVENTION __cdecl
# else
# define __KAI_KMPC_CONVENTION
# endif
/* schedule kind constants */
typedef enum omp_sched_t {
omp_sched_static = 1,
omp_sched_dynamic = 2,
omp_sched_guided = 3,
omp_sched_auto = 4
} omp_sched_t;
/* set API functions */
extern void __KAI_KMPC_CONVENTION omp_set_num_threads (int);
extern void __KAI_KMPC_CONVENTION omp_set_dynamic (int);
extern void __KAI_KMPC_CONVENTION omp_set_nested (int);
extern void __KAI_KMPC_CONVENTION omp_set_max_active_levels (int);
extern void __KAI_KMPC_CONVENTION omp_set_schedule (omp_sched_t, int);
/* query API functions */
extern int __KAI_KMPC_CONVENTION omp_get_num_threads (void);
extern int __KAI_KMPC_CONVENTION omp_get_dynamic (void);
extern int __KAI_KMPC_CONVENTION omp_get_nested (void);
extern int __KAI_KMPC_CONVENTION omp_get_max_threads (void);
extern int __KAI_KMPC_CONVENTION omp_get_thread_num (void);
extern int __KAI_KMPC_CONVENTION omp_get_num_procs (void);
extern int __KAI_KMPC_CONVENTION omp_in_parallel (void);
extern int __KAI_KMPC_CONVENTION omp_in_final (void);
extern int __KAI_KMPC_CONVENTION omp_get_active_level (void);
extern int __KAI_KMPC_CONVENTION omp_get_level (void);
extern int __KAI_KMPC_CONVENTION omp_get_ancestor_thread_num (int);
extern int __KAI_KMPC_CONVENTION omp_get_team_size (int);
extern int __KAI_KMPC_CONVENTION omp_get_thread_limit (void);
extern int __KAI_KMPC_CONVENTION omp_get_max_active_levels (void);
extern void __KAI_KMPC_CONVENTION omp_get_schedule (omp_sched_t *, int *);
/* lock API functions */
typedef struct omp_lock_t {
void * _lk;
} omp_lock_t;
extern void __KAI_KMPC_CONVENTION omp_init_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_set_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_unset_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_destroy_lock (omp_lock_t *);
extern int __KAI_KMPC_CONVENTION omp_test_lock (omp_lock_t *);
/* nested lock API functions */
typedef struct omp_nest_lock_t {
void * _lk;
} omp_nest_lock_t;
extern void __KAI_KMPC_CONVENTION omp_init_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_set_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_unset_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_destroy_nest_lock (omp_nest_lock_t *);
extern int __KAI_KMPC_CONVENTION omp_test_nest_lock (omp_nest_lock_t *);
/* time API functions */
extern double __KAI_KMPC_CONVENTION omp_get_wtime (void);
extern double __KAI_KMPC_CONVENTION omp_get_wtick (void);
/* OpenMP 4.0 */
extern int __KAI_KMPC_CONVENTION omp_get_default_device (void);
extern void __KAI_KMPC_CONVENTION omp_set_default_device (int);
extern int __KAI_KMPC_CONVENTION omp_is_initial_device (void);
extern int __KAI_KMPC_CONVENTION omp_get_num_devices (void);
extern int __KAI_KMPC_CONVENTION omp_get_num_teams (void);
extern int __KAI_KMPC_CONVENTION omp_get_team_num (void);
extern int __KAI_KMPC_CONVENTION omp_get_cancellation (void);
# include <stdlib.h>
/* kmp API functions */
extern int __KAI_KMPC_CONVENTION kmp_get_stacksize (void);
extern void __KAI_KMPC_CONVENTION kmp_set_stacksize (int);
extern size_t __KAI_KMPC_CONVENTION kmp_get_stacksize_s (void);
extern void __KAI_KMPC_CONVENTION kmp_set_stacksize_s (size_t);
extern int __KAI_KMPC_CONVENTION kmp_get_blocktime (void);
extern int __KAI_KMPC_CONVENTION kmp_get_library (void);
extern void __KAI_KMPC_CONVENTION kmp_set_blocktime (int);
extern void __KAI_KMPC_CONVENTION kmp_set_library (int);
extern void __KAI_KMPC_CONVENTION kmp_set_library_serial (void);
extern void __KAI_KMPC_CONVENTION kmp_set_library_turnaround (void);
extern void __KAI_KMPC_CONVENTION kmp_set_library_throughput (void);
extern void __KAI_KMPC_CONVENTION kmp_set_defaults (char const *);
/* Intel affinity API */
typedef void * kmp_affinity_mask_t;
extern int __KAI_KMPC_CONVENTION kmp_set_affinity (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity_max_proc (void);
extern void __KAI_KMPC_CONVENTION kmp_create_affinity_mask (kmp_affinity_mask_t *);
extern void __KAI_KMPC_CONVENTION kmp_destroy_affinity_mask (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_set_affinity_mask_proc (int, kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_unset_affinity_mask_proc (int, kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity_mask_proc (int, kmp_affinity_mask_t *);
/* OpenMP 4.0 affinity API */
typedef enum omp_proc_bind_t {
omp_proc_bind_false = 0,
omp_proc_bind_true = 1,
omp_proc_bind_master = 2,
omp_proc_bind_close = 3,
omp_proc_bind_spread = 4
} omp_proc_bind_t;
extern omp_proc_bind_t __KAI_KMPC_CONVENTION omp_get_proc_bind (void);
extern void * __KAI_KMPC_CONVENTION kmp_malloc (size_t);
extern void * __KAI_KMPC_CONVENTION kmp_aligned_malloc (size_t, size_t);
extern void * __KAI_KMPC_CONVENTION kmp_calloc (size_t, size_t);
extern void * __KAI_KMPC_CONVENTION kmp_realloc (void *, size_t);
extern void __KAI_KMPC_CONVENTION kmp_free (void *);
extern void __KAI_KMPC_CONVENTION kmp_set_warnings_on(void);
extern void __KAI_KMPC_CONVENTION kmp_set_warnings_off(void);
# undef __KAI_KMPC_CONVENTION
/* Warning:
The following typedefs are not standard, deprecated and will be removed in a future release.
*/
typedef int omp_int_t;
typedef double omp_wtime_t;
# ifdef __cplusplus
}
# endif
#endif /* __OMP_H */
-774
View File
@@ -1,774 +0,0 @@
! include/40/omp_lib.f.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
!***
!*** Some of the directives for the following routine extend past column 72,
!*** so process this file in 132-column mode.
!***
!dec$ fixedformlinesize:132
module omp_lib_kinds
integer, parameter :: omp_integer_kind = 4
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = 4
integer, parameter :: omp_lock_kind = int_ptr_kind()
integer, parameter :: omp_nest_lock_kind = int_ptr_kind()
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: omp_proc_bind_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = int_ptr_kind()
integer, parameter :: kmp_size_t_kind = int_ptr_kind()
integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
integer, parameter :: kmp_cancel_kind = omp_integer_kind
end module omp_lib_kinds
module omp_lib
use omp_lib_kinds
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*), parameter :: kmp_build_date = '@LIBOMP_BUILD_DATE@'
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_parallel = 1
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_loop = 2
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_sections = 3
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_taskgroup = 4
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(num_threads)
use omp_lib_kinds
integer (kind=omp_integer_kind) num_threads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(dynamic_threads)
use omp_lib_kinds
logical (kind=omp_logical_kind) dynamic_threads
end subroutine omp_set_dynamic
subroutine omp_set_nested(nested)
use omp_lib_kinds
logical (kind=omp_logical_kind) nested
end subroutine omp_set_nested
function omp_get_num_threads()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels)
use omp_lib_kinds
integer (kind=omp_integer_kind) max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level)
use omp_lib_kinds
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
end function omp_get_ancestor_thread_num
function omp_get_team_size(level)
use omp_lib_kinds
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_team_size
end function omp_get_team_size
subroutine omp_set_schedule(kind, chunk_size)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, chunk_size)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_get_schedule
function omp_get_proc_bind()
use omp_lib_kinds
integer (kind=omp_proc_bind_kind) omp_get_proc_bind
end function omp_get_proc_bind
function omp_get_wtime()
double precision omp_get_wtime
end function omp_get_wtime
function omp_get_wtick ()
double precision omp_get_wtick
end function omp_get_wtick
function omp_get_default_device()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_default_device
end function omp_get_default_device
subroutine omp_set_default_device(device_num)
use omp_lib_kinds
integer (kind=omp_integer_kind) device_num
end subroutine omp_set_default_device
function omp_get_num_devices()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_devices
end function omp_get_num_devices
function omp_get_num_teams()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_teams
end function omp_get_num_teams
function omp_get_team_num()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_team_num
end function omp_get_team_num
function omp_get_cancellation()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_cancellation
end function omp_get_cancellation
function omp_is_initial_device()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_is_initial_device
end function omp_is_initial_device
subroutine omp_init_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_init_lock
subroutine omp_destroy_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_destroy_lock
subroutine omp_set_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_set_lock
subroutine omp_unset_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_unset_lock
function omp_test_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_lock
!DIR$ ENDIF
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) svar
end function omp_test_lock
subroutine omp_init_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) nvar
end function omp_test_nest_lock
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size)
use omp_lib_kinds
integer (kind=omp_integer_kind) size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size)
use omp_lib_kinds
integer (kind=kmp_size_t_kind) size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec)
use omp_lib_kinds
integer (kind=omp_integer_kind) msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial()
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround()
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput()
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum)
use omp_lib_kinds
integer (kind=omp_integer_kind) libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string)
character*(*) string
end subroutine kmp_set_defaults
function kmp_get_stacksize()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s()
use omp_lib_kinds
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
function kmp_set_affinity(mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind) size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind) size
integer (kind=kmp_size_t_kind) alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind) nelem
integer (kind=kmp_size_t_kind) elsize
end function kmp_calloc
function kmp_realloc(ptr, size)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind) ptr
integer (kind=kmp_size_t_kind) size
end function kmp_realloc
subroutine kmp_free(ptr)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on()
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off()
end subroutine kmp_set_warnings_off
function kmp_get_cancellation_status(cancelkind)
use omp_lib_kinds
integer (kind=kmp_cancel_kind) cancelkind
logical (kind=omp_logical_kind) kmp_get_cancellation_status
end function kmp_get_cancellation_status
end interface
!dec$ if defined(_WIN32)
!dec$ if defined(_WIN64) .or. defined(_M_AMD64)
!***
!*** The Fortran entry points must be in uppercase, even if the /Qlowercase
!*** option is specified. The alias attribute ensures that the specified
!*** string is used as the entry point.
!***
!*** On the Windows* OS IA-32 architecture, the Fortran entry points have an
!*** underscore prepended. On the Windows* OS Intel(R) 64
!*** architecture, no underscore is prepended.
!***
!dec$ attributes alias:'OMP_SET_NUM_THREADS' :: omp_set_num_threads
!dec$ attributes alias:'OMP_SET_DYNAMIC' :: omp_set_dynamic
!dec$ attributes alias:'OMP_SET_NESTED' :: omp_set_nested
!dec$ attributes alias:'OMP_GET_NUM_THREADS' :: omp_get_num_threads
!dec$ attributes alias:'OMP_GET_MAX_THREADS' :: omp_get_max_threads
!dec$ attributes alias:'OMP_GET_THREAD_NUM' :: omp_get_thread_num
!dec$ attributes alias:'OMP_GET_NUM_PROCS' :: omp_get_num_procs
!dec$ attributes alias:'OMP_IN_PARALLEL' :: omp_in_parallel
!dec$ attributes alias:'OMP_GET_DYNAMIC' :: omp_get_dynamic
!dec$ attributes alias:'OMP_GET_NESTED' :: omp_get_nested
!dec$ attributes alias:'OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
!dec$ attributes alias:'OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
!dec$ attributes alias:'OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
!dec$ attributes alias:'OMP_GET_LEVEL' :: omp_get_level
!dec$ attributes alias:'OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
!dec$ attributes alias:'OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
!dec$ attributes alias:'OMP_GET_TEAM_SIZE' :: omp_get_team_size
!dec$ attributes alias:'OMP_SET_SCHEDULE' :: omp_set_schedule
!dec$ attributes alias:'OMP_GET_SCHEDULE' :: omp_get_schedule
!dec$ attributes alias:'OMP_GET_PROC_BIND' :: omp_get_proc_bind
!dec$ attributes alias:'OMP_GET_WTIME' :: omp_get_wtime
!dec$ attributes alias:'OMP_GET_WTICK' :: omp_get_wtick
!dec$ attributes alias:'OMP_GET_DEFAULT_DEVICE' :: omp_get_default_device
!dec$ attributes alias:'OMP_SET_DEFAULT_DEVICE' :: omp_set_default_device
!dec$ attributes alias:'OMP_GET_NUM_DEVICES' :: omp_get_num_devices
!dec$ attributes alias:'OMP_GET_NUM_TEAMS' :: omp_get_num_teams
!dec$ attributes alias:'OMP_GET_TEAM_NUM' :: omp_get_team_num
!dec$ attributes alias:'OMP_GET_CANCELLATION' :: omp_get_cancellation
!dec$ attributes alias:'OMP_IS_INITIAL_DEVICE' :: omp_is_initial_device
!dec$ attributes alias:'omp_init_lock' :: omp_init_lock
!dec$ attributes alias:'omp_destroy_lock' :: omp_destroy_lock
!dec$ attributes alias:'omp_set_lock' :: omp_set_lock
!dec$ attributes alias:'omp_unset_lock' :: omp_unset_lock
!dec$ attributes alias:'omp_test_lock' :: omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock' :: omp_init_nest_lock
!dec$ attributes alias:'omp_destroy_nest_lock' :: omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock' :: omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock' :: omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock' :: omp_test_nest_lock
!dec$ attributes alias:'KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'KMP_FREE'::kmp_free
!dec$ attributes alias:'KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ attributes alias:'KMP_GET_CANCELLATION_STATUS' :: kmp_get_cancellation_status
!dec$ else
!***
!*** On Windows* OS IA-32 architecture, the Fortran entry points have an underscore prepended.
!***
!dec$ attributes alias:'_OMP_SET_NUM_THREADS' :: omp_set_num_threads
!dec$ attributes alias:'_OMP_SET_DYNAMIC' :: omp_set_dynamic
!dec$ attributes alias:'_OMP_SET_NESTED' :: omp_set_nested
!dec$ attributes alias:'_OMP_GET_NUM_THREADS' :: omp_get_num_threads
!dec$ attributes alias:'_OMP_GET_MAX_THREADS' :: omp_get_max_threads
!dec$ attributes alias:'_OMP_GET_THREAD_NUM' :: omp_get_thread_num
!dec$ attributes alias:'_OMP_GET_NUM_PROCS' :: omp_get_num_procs
!dec$ attributes alias:'_OMP_IN_PARALLEL' :: omp_in_parallel
!dec$ attributes alias:'_OMP_GET_DYNAMIC' :: omp_get_dynamic
!dec$ attributes alias:'_OMP_GET_NESTED' :: omp_get_nested
!dec$ attributes alias:'_OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
!dec$ attributes alias:'_OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
!dec$ attributes alias:'_OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
!dec$ attributes alias:'_OMP_GET_LEVEL' :: omp_get_level
!dec$ attributes alias:'_OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
!dec$ attributes alias:'_OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
!dec$ attributes alias:'_OMP_GET_TEAM_SIZE' :: omp_get_team_size
!dec$ attributes alias:'_OMP_SET_SCHEDULE' :: omp_set_schedule
!dec$ attributes alias:'_OMP_GET_SCHEDULE' :: omp_get_schedule
!dec$ attributes alias:'_OMP_GET_PROC_BIND' :: omp_get_proc_bind
!dec$ attributes alias:'_OMP_GET_WTIME' :: omp_get_wtime
!dec$ attributes alias:'_OMP_GET_WTICK' :: omp_get_wtick
!dec$ attributes alias:'_OMP_GET_DEFAULT_DEVICE' :: omp_get_default_device
!dec$ attributes alias:'_OMP_SET_DEFAULT_DEVICE' :: omp_set_default_device
!dec$ attributes alias:'_OMP_GET_NUM_DEVICES' :: omp_get_num_devices
!dec$ attributes alias:'_OMP_GET_NUM_TEAMS' :: omp_get_num_teams
!dec$ attributes alias:'_OMP_GET_TEAM_NUM' :: omp_get_team_num
!dec$ attributes alias:'_OMP_GET_CANCELLATION' :: omp_get_cancellation
!dec$ attributes alias:'_OMP_IS_INITIAL_DEVICE' :: omp_is_initial_device
!dec$ attributes alias:'_omp_init_lock' :: omp_init_lock
!dec$ attributes alias:'_omp_destroy_lock' :: omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock' :: omp_set_lock
!dec$ attributes alias:'_omp_unset_lock' :: omp_unset_lock
!dec$ attributes alias:'_omp_test_lock' :: omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock' :: omp_init_nest_lock
!dec$ attributes alias:'_omp_destroy_nest_lock' :: omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock' :: omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock' :: omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock' :: omp_test_nest_lock
!dec$ attributes alias:'_KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'_KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'_KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'_KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'_KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'_KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'_KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'_KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'_KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'_KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'_KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'_KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'_KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'_KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'_KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'_KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'_KMP_FREE'::kmp_free
!dec$ attributes alias:'_KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'_KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ attributes alias:'_KMP_GET_CANCELLATION_STATUS' :: kmp_get_cancellation_status
!dec$ endif
!dec$ endif
!dec$ if defined(__linux)
!***
!*** The Linux* OS entry points are in lowercase, with an underscore appended.
!***
!dec$ attributes alias:'omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'omp_get_level_'::omp_get_level
!dec$ attributes alias:'omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'omp_get_proc_bind_' :: omp_get_proc_bind
!dec$ attributes alias:'omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'omp_get_default_device_'::omp_get_default_device
!dec$ attributes alias:'omp_set_default_device_'::omp_set_default_device
!dec$ attributes alias:'omp_get_num_devices_'::omp_get_num_devices
!dec$ attributes alias:'omp_get_num_teams_'::omp_get_num_teams
!dec$ attributes alias:'omp_get_team_num_'::omp_get_team_num
!dec$ attributes alias:'omp_get_cancellation_'::omp_get_cancellation
!dec$ attributes alias:'omp_is_initial_device_'::omp_is_initial_device
!dec$ attributes alias:'omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'kmp_free_'::kmp_free
!dec$ attributes alias:'kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ attributes alias:'kmp_get_cancellation_status_'::kmp_get_cancellation_status
!dec$ endif
!dec$ if defined(__APPLE__)
!***
!*** The Mac entry points are in lowercase, with an both an underscore
!*** appended and an underscore prepended.
!***
!dec$ attributes alias:'_omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'_omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'_omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'_omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'_omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'_omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'_omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'_omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'_omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'_omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'_omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'_omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'_omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'_omp_get_level_'::omp_get_level
!dec$ attributes alias:'_omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'_omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'_omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'_omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'_omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'_omp_get_proc_bind_' :: omp_get_proc_bind
!dec$ attributes alias:'_omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'_omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'_omp_get_num_teams_'::omp_get_num_teams
!dec$ attributes alias:'_omp_get_team_num_'::omp_get_team_num
!dec$ attributes alias:'_omp_get_cancellation_'::omp_get_cancellation
!dec$ attributes alias:'_omp_is_initial_device_'::omp_is_initial_device
!dec$ attributes alias:'_omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'_omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'_omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'_omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'_omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'_kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'_kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'_kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'_kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'_kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'_kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'_kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'_kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'_kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'_kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'_kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'_kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'_kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'_kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'_kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'_kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'_kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'_kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'_kmp_free_'::kmp_free
!dec$ attributes alias:'_kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'_kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ attributes alias:'_kmp_get_cancellation_status_'::kmp_get_cancellation_status
!dec$ endif
end module omp_lib
-455
View File
@@ -1,455 +0,0 @@
! include/40/omp_lib.f90.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
module omp_lib_kinds
use, intrinsic :: iso_c_binding
integer, parameter :: omp_integer_kind = c_int
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = c_float
integer, parameter :: kmp_double_kind = c_double
integer, parameter :: omp_lock_kind = c_intptr_t
integer, parameter :: omp_nest_lock_kind = c_intptr_t
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: omp_proc_bind_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = c_intptr_t
integer, parameter :: kmp_size_t_kind = c_size_t
integer, parameter :: kmp_affinity_mask_kind = c_intptr_t
integer, parameter :: kmp_cancel_kind = omp_integer_kind
end module omp_lib_kinds
module omp_lib
use omp_lib_kinds
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*) kmp_build_date
parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_parallel = 1
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_loop = 2
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_sections = 3
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_taskgroup = 4
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(num_threads) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: num_threads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(dynamic_threads) bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind), value :: dynamic_threads
end subroutine omp_set_dynamic
subroutine omp_set_nested(nested) bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind), value :: nested
end subroutine omp_set_nested
function omp_get_num_threads() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
integer (kind=omp_integer_kind), value :: level
end function omp_get_ancestor_thread_num
function omp_get_team_size(level) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_team_size
integer (kind=omp_integer_kind), value :: level
end function omp_get_team_size
subroutine omp_set_schedule(kind, chunk_size) bind(c)
use omp_lib_kinds
integer (kind=omp_sched_kind), value :: kind
integer (kind=omp_integer_kind), value :: chunk_size
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, chunk_size) bind(c)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_get_schedule
function omp_get_proc_bind() bind(c)
use omp_lib_kinds
integer (kind=omp_proc_bind_kind) omp_get_proc_bind
end function omp_get_proc_bind
function omp_get_wtime() bind(c)
use omp_lib_kinds
real (kind=kmp_double_kind) omp_get_wtime
end function omp_get_wtime
function omp_get_wtick() bind(c)
use omp_lib_kinds
real (kind=kmp_double_kind) omp_get_wtick
end function omp_get_wtick
function omp_get_default_device() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_default_device
end function omp_get_default_device
subroutine omp_set_default_device(device_num) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: device_num
end subroutine omp_set_default_device
function omp_get_num_devices() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_devices
end function omp_get_num_devices
function omp_get_num_teams() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_teams
end function omp_get_num_teams
function omp_get_team_num() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_team_num
end function omp_get_team_num
function omp_get_cancellation() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_cancellation
end function omp_get_cancellation
function omp_is_initial_device() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_is_initial_device
end function omp_is_initial_device
subroutine omp_init_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_init_lock
subroutine omp_destroy_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_destroy_lock
subroutine omp_set_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_set_lock
subroutine omp_unset_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_unset_lock
function omp_test_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_lock
!DIR$ ENDIF
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) svar
end function omp_test_lock
subroutine omp_init_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) nvar
end function omp_test_nest_lock
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size) bind(c)
use omp_lib_kinds
integer (kind=kmp_size_t_kind), value :: size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial() bind(c)
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround() bind(c)
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput() bind(c)
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string) bind(c)
use, intrinsic :: iso_c_binding
character (kind=c_char) :: string(*)
end subroutine kmp_set_defaults
function kmp_get_stacksize() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s() bind(c)
use omp_lib_kinds
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
function kmp_set_affinity(mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask) bind(c)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask) bind(c)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind), value :: size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind), value :: size
integer (kind=kmp_size_t_kind), value :: alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind), value :: nelem
integer (kind=kmp_size_t_kind), value :: elsize
end function kmp_calloc
function kmp_realloc(ptr, size) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind), value :: ptr
integer (kind=kmp_size_t_kind), value :: size
end function kmp_realloc
subroutine kmp_free(ptr) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind), value :: ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on() bind(c)
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off() bind(c)
end subroutine kmp_set_warnings_off
function kmp_get_cancellation_status(cancelkind) bind(c)
use omp_lib_kinds
integer (kind=kmp_cancel_kind), value :: cancelkind
logical (kind=omp_logical_kind) kmp_get_cancellation_status
end function kmp_get_cancellation_status
end interface
end module omp_lib
-567
View File
@@ -1,567 +0,0 @@
! include/40/omp_lib.h.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
!***
!*** Some of the directives for the following routine extend past column 72,
!*** so process this file in 132-column mode.
!***
!DIR$ fixedformlinesize:132
integer, parameter :: omp_integer_kind = 4
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = 4
integer, parameter :: omp_lock_kind = int_ptr_kind()
integer, parameter :: omp_nest_lock_kind = int_ptr_kind()
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: omp_proc_bind_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = int_ptr_kind()
integer, parameter :: kmp_size_t_kind = int_ptr_kind()
integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*) kmp_build_date
parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(num_threads) bind(c)
import
integer (kind=omp_integer_kind), value :: num_threads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(dynamic_threads) bind(c)
import
logical (kind=omp_logical_kind), value :: dynamic_threads
end subroutine omp_set_dynamic
subroutine omp_set_nested(nested) bind(c)
import
logical (kind=omp_logical_kind), value :: nested
end subroutine omp_set_nested
function omp_get_num_threads() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads() bind(c)
import
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num() bind(c)
import
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel() bind(c)
import
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final() bind(c)
import
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic() bind(c)
import
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested() bind(c)
import
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit() bind(c)
import
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels) bind(c)
import
integer (kind=omp_integer_kind), value :: max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels() bind(c)
import
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level() bind(c)
import
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level() bind(c)
import
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level) bind(c)
import
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
integer (kind=omp_integer_kind), value :: level
end function omp_get_ancestor_thread_num
function omp_get_team_size(level) bind(c)
import
integer (kind=omp_integer_kind) omp_get_team_size
integer (kind=omp_integer_kind), value :: level
end function omp_get_team_size
subroutine omp_set_schedule(kind, chunk_size) bind(c)
import
integer (kind=omp_sched_kind), value :: kind
integer (kind=omp_integer_kind), value :: chunk_size
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, chunk_size) bind(c)
import
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_get_schedule
function omp_get_proc_bind() bind(c)
import
integer (kind=omp_proc_bind_kind) omp_get_proc_bind
end function omp_get_proc_bind
function omp_get_wtime() bind(c)
double precision omp_get_wtime
end function omp_get_wtime
function omp_get_wtick() bind(c)
double precision omp_get_wtick
end function omp_get_wtick
function omp_get_default_device() bind(c)
import
integer (kind=omp_integer_kind) omp_get_default_device
end function omp_get_default_device
subroutine omp_set_default_device(device_num) bind(c)
import
integer (kind=omp_integer_kind), value :: device_num
end subroutine omp_set_default_device
function omp_get_num_devices() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_devices
end function omp_get_num_devices
function omp_get_num_teams() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_teams
end function omp_get_num_teams
function omp_get_team_num() bind(c)
import
integer (kind=omp_integer_kind) omp_get_team_num
end function omp_get_team_num
function omp_is_initial_device() bind(c)
import
logical (kind=omp_logical_kind) omp_is_initial_device
end function omp_is_initial_device
subroutine omp_init_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_init_lock
subroutine omp_destroy_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_destroy_lock
subroutine omp_set_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_set_lock
subroutine omp_unset_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_unset_lock
function omp_test_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_lock
!DIR$ ENDIF
import
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) svar
end function omp_test_lock
subroutine omp_init_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) nvar
end function omp_test_nest_lock
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size) bind(c)
import
integer (kind=omp_integer_kind), value :: size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size) bind(c)
import
integer (kind=kmp_size_t_kind), value :: size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec) bind(c)
import
integer (kind=omp_integer_kind), value :: msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial() bind(c)
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround() bind(c)
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput() bind(c)
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum) bind(c)
import
integer (kind=omp_integer_kind), value :: libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string) bind(c)
character string(*)
end subroutine kmp_set_defaults
function kmp_get_stacksize() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s() bind(c)
import
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
function kmp_set_affinity(mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask) bind(c)
import
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask) bind(c)
import
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind), value :: size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind), value :: size
integer (kind=kmp_size_t_kind), value :: alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind), value :: nelem
integer (kind=kmp_size_t_kind), value :: elsize
end function kmp_calloc
function kmp_realloc(ptr, size) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind), value :: ptr
integer (kind=kmp_size_t_kind), value :: size
end function kmp_realloc
subroutine kmp_free(ptr) bind(c)
import
integer (kind=kmp_pointer_kind), value :: ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on() bind(c)
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off() bind(c)
end subroutine kmp_set_warnings_off
end interface
!DIR$ IF DEFINED (__INTEL_OFFLOAD)
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_num_threads
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_dynamic
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_nested
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_threads
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_threads
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_thread_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_procs
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_in_parallel
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_in_final
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_dynamic
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_nested
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_thread_limit
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_max_active_levels
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_active_levels
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_level
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_active_level
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_ancestor_thread_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_team_size
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_schedule
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_schedule
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_proc_bind
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_wtime
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_wtick
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_default_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_default_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_is_initial_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_devices
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_teams
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_team_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_destroy_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_unset_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_test_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_destroy_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_unset_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_test_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_stacksize
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_stacksize_s
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_blocktime
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_serial
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_turnaround
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_throughput
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_defaults
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_stacksize
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_stacksize_s
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_blocktime
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_library
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_affinity
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity_max_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_create_affinity_mask
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_destroy_affinity_mask
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_affinity_mask_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_unset_affinity_mask_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity_mask_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_malloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_aligned_malloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_calloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_realloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_free
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_warnings_on
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_warnings_off
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!$omp declare target(omp_set_num_threads )
!$omp declare target(omp_set_dynamic )
!$omp declare target(omp_set_nested )
!$omp declare target(omp_get_num_threads )
!$omp declare target(omp_get_max_threads )
!$omp declare target(omp_get_thread_num )
!$omp declare target(omp_get_num_procs )
!$omp declare target(omp_in_parallel )
!$omp declare target(omp_in_final )
!$omp declare target(omp_get_dynamic )
!$omp declare target(omp_get_nested )
!$omp declare target(omp_get_thread_limit )
!$omp declare target(omp_set_max_active_levels )
!$omp declare target(omp_get_max_active_levels )
!$omp declare target(omp_get_level )
!$omp declare target(omp_get_active_level )
!$omp declare target(omp_get_ancestor_thread_num )
!$omp declare target(omp_get_team_size )
!$omp declare target(omp_set_schedule )
!$omp declare target(omp_get_schedule )
!$omp declare target(omp_get_proc_bind )
!$omp declare target(omp_get_wtime )
!$omp declare target(omp_get_wtick )
!$omp declare target(omp_get_default_device )
!$omp declare target(omp_set_default_device )
!$omp declare target(omp_is_initial_device )
!$omp declare target(omp_get_num_devices )
!$omp declare target(omp_get_num_teams )
!$omp declare target(omp_get_team_num )
!$omp declare target(omp_init_lock )
!$omp declare target(omp_destroy_lock )
!$omp declare target(omp_set_lock )
!$omp declare target(omp_unset_lock )
!$omp declare target(omp_test_lock )
!$omp declare target(omp_init_nest_lock )
!$omp declare target(omp_destroy_nest_lock )
!$omp declare target(omp_set_nest_lock )
!$omp declare target(omp_unset_nest_lock )
!$omp declare target(omp_test_nest_lock )
!$omp declare target(kmp_set_stacksize )
!$omp declare target(kmp_set_stacksize_s )
!$omp declare target(kmp_set_blocktime )
!$omp declare target(kmp_set_library_serial )
!$omp declare target(kmp_set_library_turnaround )
!$omp declare target(kmp_set_library_throughput )
!$omp declare target(kmp_set_library )
!$omp declare target(kmp_set_defaults )
!$omp declare target(kmp_get_stacksize )
!$omp declare target(kmp_get_stacksize_s )
!$omp declare target(kmp_get_blocktime )
!$omp declare target(kmp_get_library )
!$omp declare target(kmp_set_affinity )
!$omp declare target(kmp_get_affinity )
!$omp declare target(kmp_get_affinity_max_proc )
!$omp declare target(kmp_create_affinity_mask )
!$omp declare target(kmp_destroy_affinity_mask )
!$omp declare target(kmp_set_affinity_mask_proc )
!$omp declare target(kmp_unset_affinity_mask_proc )
!$omp declare target(kmp_get_affinity_mask_proc )
!$omp declare target(kmp_malloc )
!$omp declare target(kmp_aligned_malloc )
!$omp declare target(kmp_calloc )
!$omp declare target(kmp_realloc )
!$omp declare target(kmp_free )
!$omp declare target(kmp_set_warnings_on )
!$omp declare target(kmp_set_warnings_off )
!DIR$ ENDIF
!DIR$ ENDIF
-197
View File
@@ -1,197 +0,0 @@
/*
* include/45/omp.h.var
*/
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
//
//===----------------------------------------------------------------------===//
#ifndef __OMP_H
# define __OMP_H
# define KMP_VERSION_MAJOR @LIBOMP_VERSION_MAJOR@
# define KMP_VERSION_MINOR @LIBOMP_VERSION_MINOR@
# define KMP_VERSION_BUILD @LIBOMP_VERSION_BUILD@
# define KMP_BUILD_DATE "@LIBOMP_BUILD_DATE@"
# ifdef __cplusplus
extern "C" {
# endif
# if defined(_WIN32)
# define __KAI_KMPC_CONVENTION __cdecl
# else
# define __KAI_KMPC_CONVENTION
# endif
/* schedule kind constants */
typedef enum omp_sched_t {
omp_sched_static = 1,
omp_sched_dynamic = 2,
omp_sched_guided = 3,
omp_sched_auto = 4
} omp_sched_t;
/* set API functions */
extern void __KAI_KMPC_CONVENTION omp_set_num_threads (int);
extern void __KAI_KMPC_CONVENTION omp_set_dynamic (int);
extern void __KAI_KMPC_CONVENTION omp_set_nested (int);
extern void __KAI_KMPC_CONVENTION omp_set_max_active_levels (int);
extern void __KAI_KMPC_CONVENTION omp_set_schedule (omp_sched_t, int);
/* query API functions */
extern int __KAI_KMPC_CONVENTION omp_get_num_threads (void);
extern int __KAI_KMPC_CONVENTION omp_get_dynamic (void);
extern int __KAI_KMPC_CONVENTION omp_get_nested (void);
extern int __KAI_KMPC_CONVENTION omp_get_max_threads (void);
extern int __KAI_KMPC_CONVENTION omp_get_thread_num (void);
extern int __KAI_KMPC_CONVENTION omp_get_num_procs (void);
extern int __KAI_KMPC_CONVENTION omp_in_parallel (void);
extern int __KAI_KMPC_CONVENTION omp_in_final (void);
extern int __KAI_KMPC_CONVENTION omp_get_active_level (void);
extern int __KAI_KMPC_CONVENTION omp_get_level (void);
extern int __KAI_KMPC_CONVENTION omp_get_ancestor_thread_num (int);
extern int __KAI_KMPC_CONVENTION omp_get_team_size (int);
extern int __KAI_KMPC_CONVENTION omp_get_thread_limit (void);
extern int __KAI_KMPC_CONVENTION omp_get_max_active_levels (void);
extern void __KAI_KMPC_CONVENTION omp_get_schedule (omp_sched_t *, int *);
extern int __KAI_KMPC_CONVENTION omp_get_max_task_priority (void);
/* lock API functions */
typedef struct omp_lock_t {
void * _lk;
} omp_lock_t;
extern void __KAI_KMPC_CONVENTION omp_init_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_set_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_unset_lock (omp_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_destroy_lock (omp_lock_t *);
extern int __KAI_KMPC_CONVENTION omp_test_lock (omp_lock_t *);
/* nested lock API functions */
typedef struct omp_nest_lock_t {
void * _lk;
} omp_nest_lock_t;
extern void __KAI_KMPC_CONVENTION omp_init_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_set_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_unset_nest_lock (omp_nest_lock_t *);
extern void __KAI_KMPC_CONVENTION omp_destroy_nest_lock (omp_nest_lock_t *);
extern int __KAI_KMPC_CONVENTION omp_test_nest_lock (omp_nest_lock_t *);
/* lock hint type for dynamic user lock */
typedef enum omp_lock_hint_t {
omp_lock_hint_none = 0,
omp_lock_hint_uncontended = 1,
omp_lock_hint_contended = (1<<1 ),
omp_lock_hint_nonspeculative = (1<<2 ),
omp_lock_hint_speculative = (1<<3 ),
kmp_lock_hint_hle = (1<<16),
kmp_lock_hint_rtm = (1<<17),
kmp_lock_hint_adaptive = (1<<18)
} omp_lock_hint_t;
/* hinted lock initializers */
extern void __KAI_KMPC_CONVENTION omp_init_lock_with_hint(omp_lock_t *, omp_lock_hint_t);
extern void __KAI_KMPC_CONVENTION omp_init_nest_lock_with_hint(omp_nest_lock_t *, omp_lock_hint_t);
/* time API functions */
extern double __KAI_KMPC_CONVENTION omp_get_wtime (void);
extern double __KAI_KMPC_CONVENTION omp_get_wtick (void);
/* OpenMP 4.0 */
extern int __KAI_KMPC_CONVENTION omp_get_default_device (void);
extern void __KAI_KMPC_CONVENTION omp_set_default_device (int);
extern int __KAI_KMPC_CONVENTION omp_is_initial_device (void);
extern int __KAI_KMPC_CONVENTION omp_get_num_devices (void);
extern int __KAI_KMPC_CONVENTION omp_get_num_teams (void);
extern int __KAI_KMPC_CONVENTION omp_get_team_num (void);
extern int __KAI_KMPC_CONVENTION omp_get_cancellation (void);
# include <stdlib.h>
/* OpenMP 4.5 */
extern int __KAI_KMPC_CONVENTION omp_get_initial_device (void);
extern void* __KAI_KMPC_CONVENTION omp_target_alloc(size_t, int);
extern void __KAI_KMPC_CONVENTION omp_target_free(void *, int);
extern int __KAI_KMPC_CONVENTION omp_target_is_present(void *, int);
extern int __KAI_KMPC_CONVENTION omp_target_memcpy(void *, void *, size_t, size_t, size_t, int, int);
extern int __KAI_KMPC_CONVENTION omp_target_memcpy_rect(void *, void *, size_t, int, const size_t *,
const size_t *, const size_t *, const size_t *, const size_t *, int, int);
extern int __KAI_KMPC_CONVENTION omp_target_associate_ptr(void *, void *, size_t, size_t, int);
extern int __KAI_KMPC_CONVENTION omp_target_disassociate_ptr(void *, int);
/* kmp API functions */
extern int __KAI_KMPC_CONVENTION kmp_get_stacksize (void);
extern void __KAI_KMPC_CONVENTION kmp_set_stacksize (int);
extern size_t __KAI_KMPC_CONVENTION kmp_get_stacksize_s (void);
extern void __KAI_KMPC_CONVENTION kmp_set_stacksize_s (size_t);
extern int __KAI_KMPC_CONVENTION kmp_get_blocktime (void);
extern int __KAI_KMPC_CONVENTION kmp_get_library (void);
extern void __KAI_KMPC_CONVENTION kmp_set_blocktime (int);
extern void __KAI_KMPC_CONVENTION kmp_set_library (int);
extern void __KAI_KMPC_CONVENTION kmp_set_library_serial (void);
extern void __KAI_KMPC_CONVENTION kmp_set_library_turnaround (void);
extern void __KAI_KMPC_CONVENTION kmp_set_library_throughput (void);
extern void __KAI_KMPC_CONVENTION kmp_set_defaults (char const *);
extern void __KAI_KMPC_CONVENTION kmp_set_disp_num_buffers (int);
/* Intel affinity API */
typedef void * kmp_affinity_mask_t;
extern int __KAI_KMPC_CONVENTION kmp_set_affinity (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity_max_proc (void);
extern void __KAI_KMPC_CONVENTION kmp_create_affinity_mask (kmp_affinity_mask_t *);
extern void __KAI_KMPC_CONVENTION kmp_destroy_affinity_mask (kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_set_affinity_mask_proc (int, kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_unset_affinity_mask_proc (int, kmp_affinity_mask_t *);
extern int __KAI_KMPC_CONVENTION kmp_get_affinity_mask_proc (int, kmp_affinity_mask_t *);
/* OpenMP 4.0 affinity API */
typedef enum omp_proc_bind_t {
omp_proc_bind_false = 0,
omp_proc_bind_true = 1,
omp_proc_bind_master = 2,
omp_proc_bind_close = 3,
omp_proc_bind_spread = 4
} omp_proc_bind_t;
extern omp_proc_bind_t __KAI_KMPC_CONVENTION omp_get_proc_bind (void);
/* OpenMP 4.5 affinity API */
extern int __KAI_KMPC_CONVENTION omp_get_num_places (void);
extern int __KAI_KMPC_CONVENTION omp_get_place_num_procs (int);
extern void __KAI_KMPC_CONVENTION omp_get_place_proc_ids (int, int *);
extern int __KAI_KMPC_CONVENTION omp_get_place_num (void);
extern int __KAI_KMPC_CONVENTION omp_get_partition_num_places (void);
extern void __KAI_KMPC_CONVENTION omp_get_partition_place_nums (int *);
extern void * __KAI_KMPC_CONVENTION kmp_malloc (size_t);
extern void * __KAI_KMPC_CONVENTION kmp_aligned_malloc (size_t, size_t);
extern void * __KAI_KMPC_CONVENTION kmp_calloc (size_t, size_t);
extern void * __KAI_KMPC_CONVENTION kmp_realloc (void *, size_t);
extern void __KAI_KMPC_CONVENTION kmp_free (void *);
extern void __KAI_KMPC_CONVENTION kmp_set_warnings_on(void);
extern void __KAI_KMPC_CONVENTION kmp_set_warnings_off(void);
# undef __KAI_KMPC_CONVENTION
/* Warning:
The following typedefs are not standard, deprecated and will be removed in a future release.
*/
typedef int omp_int_t;
typedef double omp_wtime_t;
# ifdef __cplusplus
}
# endif
#endif /* __OMP_H */
-861
View File
@@ -1,861 +0,0 @@
! include/45/omp_lib.f.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
!***
!*** Some of the directives for the following routine extend past column 72,
!*** so process this file in 132-column mode.
!***
!dec$ fixedformlinesize:132
module omp_lib_kinds
integer, parameter :: omp_integer_kind = 4
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = 4
integer, parameter :: omp_lock_kind = int_ptr_kind()
integer, parameter :: omp_nest_lock_kind = int_ptr_kind()
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: omp_proc_bind_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = int_ptr_kind()
integer, parameter :: kmp_size_t_kind = int_ptr_kind()
integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
integer, parameter :: kmp_cancel_kind = omp_integer_kind
integer, parameter :: omp_lock_hint_kind = omp_integer_kind
end module omp_lib_kinds
module omp_lib
use omp_lib_kinds
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*), parameter :: kmp_build_date = '@LIBOMP_BUILD_DATE@'
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_parallel = 1
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_loop = 2
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_sections = 3
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_taskgroup = 4
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_none = 0
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_uncontended = 1
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_contended = 2
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_nonspeculative = 4
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_speculative = 8
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_hle = 65536
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_rtm = 131072
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_adaptive = 262144
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(num_threads)
use omp_lib_kinds
integer (kind=omp_integer_kind) num_threads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(dynamic_threads)
use omp_lib_kinds
logical (kind=omp_logical_kind) dynamic_threads
end subroutine omp_set_dynamic
subroutine omp_set_nested(nested)
use omp_lib_kinds
logical (kind=omp_logical_kind) nested
end subroutine omp_set_nested
function omp_get_num_threads()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels)
use omp_lib_kinds
integer (kind=omp_integer_kind) max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level)
use omp_lib_kinds
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
end function omp_get_ancestor_thread_num
function omp_get_team_size(level)
use omp_lib_kinds
integer (kind=omp_integer_kind) level
integer (kind=omp_integer_kind) omp_get_team_size
end function omp_get_team_size
subroutine omp_set_schedule(kind, chunk_size)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, chunk_size)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_get_schedule
function omp_get_proc_bind()
use omp_lib_kinds
integer (kind=omp_proc_bind_kind) omp_get_proc_bind
end function omp_get_proc_bind
function omp_get_num_places()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_places
end function omp_get_num_places
function omp_get_place_num_procs(place_num)
use omp_lib_kinds
integer (kind=omp_integer_kind) place_num
integer (kind=omp_integer_kind) omp_get_place_num_procs
end function omp_get_place_num_procs
subroutine omp_get_place_proc_ids(place_num, ids)
use omp_lib_kinds
integer (kind=omp_integer_kind) place_num
integer (kind=omp_integer_kind) ids(*)
end subroutine omp_get_place_proc_ids
function omp_get_place_num()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_place_num
end function omp_get_place_num
function omp_get_partition_num_places()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_partition_num_places
end function omp_get_partition_num_places
subroutine omp_get_partition_place_nums(place_nums)
use omp_lib_kinds
integer (kind=omp_integer_kind) place_nums(*)
end subroutine omp_get_partition_place_nums
function omp_get_wtime()
double precision omp_get_wtime
end function omp_get_wtime
function omp_get_wtick ()
double precision omp_get_wtick
end function omp_get_wtick
function omp_get_default_device()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_default_device
end function omp_get_default_device
subroutine omp_set_default_device(device_num)
use omp_lib_kinds
integer (kind=omp_integer_kind) device_num
end subroutine omp_set_default_device
function omp_get_num_devices()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_devices
end function omp_get_num_devices
function omp_get_num_teams()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_teams
end function omp_get_num_teams
function omp_get_team_num()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_team_num
end function omp_get_team_num
function omp_get_cancellation()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_cancellation
end function omp_get_cancellation
function omp_is_initial_device()
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_is_initial_device
end function omp_is_initial_device
function omp_get_initial_device()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_initial_device
end function omp_get_initial_device
subroutine omp_init_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_init_lock
subroutine omp_destroy_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_destroy_lock
subroutine omp_set_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_set_lock
subroutine omp_unset_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_unset_lock
function omp_test_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_lock
!DIR$ ENDIF
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) svar
end function omp_test_lock
subroutine omp_init_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(nvar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) nvar
end function omp_test_nest_lock
function omp_get_max_task_priority()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_task_priority
end function omp_get_max_task_priority
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size)
use omp_lib_kinds
integer (kind=omp_integer_kind) size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size)
use omp_lib_kinds
integer (kind=kmp_size_t_kind) size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec)
use omp_lib_kinds
integer (kind=omp_integer_kind) msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial()
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround()
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput()
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum)
use omp_lib_kinds
integer (kind=omp_integer_kind) libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string)
character*(*) string
end subroutine kmp_set_defaults
function kmp_get_stacksize()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s()
use omp_lib_kinds
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
subroutine kmp_set_disp_num_buffers(num)
use omp_lib_kinds
integer (kind=omp_integer_kind) num
end subroutine kmp_set_disp_num_buffers
function kmp_set_affinity(mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc()
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind) proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind) size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind) size
integer (kind=kmp_size_t_kind) alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind) nelem
integer (kind=kmp_size_t_kind) elsize
end function kmp_calloc
function kmp_realloc(ptr, size)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind) ptr
integer (kind=kmp_size_t_kind) size
end function kmp_realloc
subroutine kmp_free(ptr)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on()
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off()
end subroutine kmp_set_warnings_off
function kmp_get_cancellation_status(cancelkind)
use omp_lib_kinds
integer (kind=kmp_cancel_kind) cancelkind
logical (kind=omp_logical_kind) kmp_get_cancellation_status
end function kmp_get_cancellation_status
subroutine omp_init_lock_with_hint(svar, hint)
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
integer (kind=omp_lock_hint_kind) hint
end subroutine omp_init_lock_with_hint
subroutine omp_init_nest_lock_with_hint(nvar, hint)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
integer (kind=omp_lock_hint_kind) hint
end subroutine omp_init_nest_lock_with_hint
end interface
!dec$ if defined(_WIN32)
!dec$ if defined(_WIN64) .or. defined(_M_AMD64)
!***
!*** The Fortran entry points must be in uppercase, even if the /Qlowercase
!*** option is specified. The alias attribute ensures that the specified
!*** string is used as the entry point.
!***
!*** On the Windows* OS IA-32 architecture, the Fortran entry points have an
!*** underscore prepended. On the Windows* OS Intel(R) 64
!*** architecture, no underscore is prepended.
!***
!dec$ attributes alias:'OMP_SET_NUM_THREADS' :: omp_set_num_threads
!dec$ attributes alias:'OMP_SET_DYNAMIC' :: omp_set_dynamic
!dec$ attributes alias:'OMP_SET_NESTED' :: omp_set_nested
!dec$ attributes alias:'OMP_GET_NUM_THREADS' :: omp_get_num_threads
!dec$ attributes alias:'OMP_GET_MAX_THREADS' :: omp_get_max_threads
!dec$ attributes alias:'OMP_GET_THREAD_NUM' :: omp_get_thread_num
!dec$ attributes alias:'OMP_GET_NUM_PROCS' :: omp_get_num_procs
!dec$ attributes alias:'OMP_IN_PARALLEL' :: omp_in_parallel
!dec$ attributes alias:'OMP_GET_DYNAMIC' :: omp_get_dynamic
!dec$ attributes alias:'OMP_GET_NESTED' :: omp_get_nested
!dec$ attributes alias:'OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
!dec$ attributes alias:'OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
!dec$ attributes alias:'OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
!dec$ attributes alias:'OMP_GET_LEVEL' :: omp_get_level
!dec$ attributes alias:'OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
!dec$ attributes alias:'OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
!dec$ attributes alias:'OMP_GET_TEAM_SIZE' :: omp_get_team_size
!dec$ attributes alias:'OMP_SET_SCHEDULE' :: omp_set_schedule
!dec$ attributes alias:'OMP_GET_SCHEDULE' :: omp_get_schedule
!dec$ attributes alias:'OMP_GET_PROC_BIND' :: omp_get_proc_bind
!dec$ attributes alias:'OMP_GET_WTIME' :: omp_get_wtime
!dec$ attributes alias:'OMP_GET_WTICK' :: omp_get_wtick
!dec$ attributes alias:'OMP_GET_DEFAULT_DEVICE' :: omp_get_default_device
!dec$ attributes alias:'OMP_SET_DEFAULT_DEVICE' :: omp_set_default_device
!dec$ attributes alias:'OMP_GET_NUM_DEVICES' :: omp_get_num_devices
!dec$ attributes alias:'OMP_GET_NUM_TEAMS' :: omp_get_num_teams
!dec$ attributes alias:'OMP_GET_TEAM_NUM' :: omp_get_team_num
!dec$ attributes alias:'OMP_GET_CANCELLATION' :: omp_get_cancellation
!dec$ attributes alias:'OMP_IS_INITIAL_DEVICE' :: omp_is_initial_device
!dec$ attributes alias:'OMP_GET_INITIAL_DEVICE' :: omp_get_initial_device
!dec$ attributes alias:'OMP_GET_MAX_TASK_PRIORITY' :: omp_get_max_task_priority
!dec$ attributes alias:'omp_init_lock' :: omp_init_lock
!dec$ attributes alias:'omp_init_lock_with_hint' :: omp_init_lock_with_hint
!dec$ attributes alias:'omp_destroy_lock' :: omp_destroy_lock
!dec$ attributes alias:'omp_set_lock' :: omp_set_lock
!dec$ attributes alias:'omp_unset_lock' :: omp_unset_lock
!dec$ attributes alias:'omp_test_lock' :: omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock' :: omp_init_nest_lock
!dec$ attributes alias:'omp_init_nest_lock_with_hint' :: omp_init_nest_lock_with_hint
!dec$ attributes alias:'omp_destroy_nest_lock' :: omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock' :: omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock' :: omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock' :: omp_test_nest_lock
!dec$ attributes alias:'KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'KMP_FREE'::kmp_free
!dec$ attributes alias:'KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ attributes alias:'KMP_GET_CANCELLATION_STATUS' :: kmp_get_cancellation_status
!dec$ else
!***
!*** On Windows* OS IA-32 architecture, the Fortran entry points have an underscore prepended.
!***
!dec$ attributes alias:'_OMP_SET_NUM_THREADS' :: omp_set_num_threads
!dec$ attributes alias:'_OMP_SET_DYNAMIC' :: omp_set_dynamic
!dec$ attributes alias:'_OMP_SET_NESTED' :: omp_set_nested
!dec$ attributes alias:'_OMP_GET_NUM_THREADS' :: omp_get_num_threads
!dec$ attributes alias:'_OMP_GET_MAX_THREADS' :: omp_get_max_threads
!dec$ attributes alias:'_OMP_GET_THREAD_NUM' :: omp_get_thread_num
!dec$ attributes alias:'_OMP_GET_NUM_PROCS' :: omp_get_num_procs
!dec$ attributes alias:'_OMP_IN_PARALLEL' :: omp_in_parallel
!dec$ attributes alias:'_OMP_GET_DYNAMIC' :: omp_get_dynamic
!dec$ attributes alias:'_OMP_GET_NESTED' :: omp_get_nested
!dec$ attributes alias:'_OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
!dec$ attributes alias:'_OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
!dec$ attributes alias:'_OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
!dec$ attributes alias:'_OMP_GET_LEVEL' :: omp_get_level
!dec$ attributes alias:'_OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
!dec$ attributes alias:'_OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
!dec$ attributes alias:'_OMP_GET_TEAM_SIZE' :: omp_get_team_size
!dec$ attributes alias:'_OMP_SET_SCHEDULE' :: omp_set_schedule
!dec$ attributes alias:'_OMP_GET_SCHEDULE' :: omp_get_schedule
!dec$ attributes alias:'_OMP_GET_PROC_BIND' :: omp_get_proc_bind
!dec$ attributes alias:'_OMP_GET_WTIME' :: omp_get_wtime
!dec$ attributes alias:'_OMP_GET_WTICK' :: omp_get_wtick
!dec$ attributes alias:'_OMP_GET_DEFAULT_DEVICE' :: omp_get_default_device
!dec$ attributes alias:'_OMP_SET_DEFAULT_DEVICE' :: omp_set_default_device
!dec$ attributes alias:'_OMP_GET_NUM_DEVICES' :: omp_get_num_devices
!dec$ attributes alias:'_OMP_GET_NUM_TEAMS' :: omp_get_num_teams
!dec$ attributes alias:'_OMP_GET_TEAM_NUM' :: omp_get_team_num
!dec$ attributes alias:'_OMP_GET_CANCELLATION' :: omp_get_cancellation
!dec$ attributes alias:'_OMP_IS_INITIAL_DEVICE' :: omp_is_initial_device
!dec$ attributes alias:'_OMP_GET_INITIAL_DEVICE' :: omp_get_initial_device
!dec$ attributes alias:'_OMP_GET_MAX_TASK_PRIORTY' :: omp_get_max_task_priority
!dec$ attributes alias:'_omp_init_lock' :: omp_init_lock
!dec$ attributes alias:'_omp_init_lock_with_hint' :: omp_init_lock_with_hint
!dec$ attributes alias:'_omp_destroy_lock' :: omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock' :: omp_set_lock
!dec$ attributes alias:'_omp_unset_lock' :: omp_unset_lock
!dec$ attributes alias:'_omp_test_lock' :: omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock' :: omp_init_nest_lock
!dec$ attributes alias:'_omp_init_nest_lock_with_hint' :: omp_init_nest_lock_with_hint
!dec$ attributes alias:'_omp_destroy_nest_lock' :: omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock' :: omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock' :: omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock' :: omp_test_nest_lock
!dec$ attributes alias:'_KMP_SET_STACKSIZE'::kmp_set_stacksize
!dec$ attributes alias:'_KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
!dec$ attributes alias:'_KMP_SET_BLOCKTIME'::kmp_set_blocktime
!dec$ attributes alias:'_KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
!dec$ attributes alias:'_KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
!dec$ attributes alias:'_KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
!dec$ attributes alias:'_KMP_SET_LIBRARY'::kmp_set_library
!dec$ attributes alias:'_KMP_GET_STACKSIZE'::kmp_get_stacksize
!dec$ attributes alias:'_KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
!dec$ attributes alias:'_KMP_GET_BLOCKTIME'::kmp_get_blocktime
!dec$ attributes alias:'_KMP_GET_LIBRARY'::kmp_get_library
!dec$ attributes alias:'_KMP_SET_AFFINITY'::kmp_set_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY'::kmp_get_affinity
!dec$ attributes alias:'_KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
!dec$ attributes alias:'_KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_KMP_MALLOC'::kmp_malloc
!dec$ attributes alias:'_KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
!dec$ attributes alias:'_KMP_CALLOC'::kmp_calloc
!dec$ attributes alias:'_KMP_REALLOC'::kmp_realloc
!dec$ attributes alias:'_KMP_FREE'::kmp_free
!dec$ attributes alias:'_KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
!dec$ attributes alias:'_KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
!dec$ attributes alias:'_KMP_GET_CANCELLATION_STATUS' :: kmp_get_cancellation_status
!dec$ endif
!dec$ endif
!dec$ if defined(__linux)
!***
!*** The Linux* OS entry points are in lowercase, with an underscore appended.
!***
!dec$ attributes alias:'omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'omp_get_level_'::omp_get_level
!dec$ attributes alias:'omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'omp_get_proc_bind_' :: omp_get_proc_bind
!dec$ attributes alias:'omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'omp_get_default_device_'::omp_get_default_device
!dec$ attributes alias:'omp_set_default_device_'::omp_set_default_device
!dec$ attributes alias:'omp_get_num_devices_'::omp_get_num_devices
!dec$ attributes alias:'omp_get_num_teams_'::omp_get_num_teams
!dec$ attributes alias:'omp_get_team_num_'::omp_get_team_num
!dec$ attributes alias:'omp_get_cancellation_'::omp_get_cancellation
!dec$ attributes alias:'omp_is_initial_device_'::omp_is_initial_device
!dec$ attributes alias:'omp_get_initial_device_'::omp_get_initial_device
!dec$ attributes alias:'omp_get_max_task_priority_'::omp_get_max_task_priority
!dec$ attributes alias:'omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'omp_init_lock_with_hint_'::omp_init_lock_with_hint
!dec$ attributes alias:'omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'omp_init_nest_lock_with_hint_'::omp_init_nest_lock_with_hint
!dec$ attributes alias:'omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'kmp_free_'::kmp_free
!dec$ attributes alias:'kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ attributes alias:'kmp_get_cancellation_status_'::kmp_get_cancellation_status
!dec$ endif
!dec$ if defined(__APPLE__)
!***
!*** The Mac entry points are in lowercase, with an both an underscore
!*** appended and an underscore prepended.
!***
!dec$ attributes alias:'_omp_set_num_threads_'::omp_set_num_threads
!dec$ attributes alias:'_omp_set_dynamic_'::omp_set_dynamic
!dec$ attributes alias:'_omp_set_nested_'::omp_set_nested
!dec$ attributes alias:'_omp_get_num_threads_'::omp_get_num_threads
!dec$ attributes alias:'_omp_get_max_threads_'::omp_get_max_threads
!dec$ attributes alias:'_omp_get_thread_num_'::omp_get_thread_num
!dec$ attributes alias:'_omp_get_num_procs_'::omp_get_num_procs
!dec$ attributes alias:'_omp_in_parallel_'::omp_in_parallel
!dec$ attributes alias:'_omp_get_dynamic_'::omp_get_dynamic
!dec$ attributes alias:'_omp_get_nested_'::omp_get_nested
!dec$ attributes alias:'_omp_get_thread_limit_'::omp_get_thread_limit
!dec$ attributes alias:'_omp_set_max_active_levels_'::omp_set_max_active_levels
!dec$ attributes alias:'_omp_get_max_active_levels_'::omp_get_max_active_levels
!dec$ attributes alias:'_omp_get_level_'::omp_get_level
!dec$ attributes alias:'_omp_get_active_level_'::omp_get_active_level
!dec$ attributes alias:'_omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
!dec$ attributes alias:'_omp_get_team_size_'::omp_get_team_size
!dec$ attributes alias:'_omp_set_schedule_'::omp_set_schedule
!dec$ attributes alias:'_omp_get_schedule_'::omp_get_schedule
!dec$ attributes alias:'_omp_get_proc_bind_' :: omp_get_proc_bind
!dec$ attributes alias:'_omp_get_wtime_'::omp_get_wtime
!dec$ attributes alias:'_omp_get_wtick_'::omp_get_wtick
!dec$ attributes alias:'_omp_get_default_device_'::omp_get_default_device
!dec$ attributes alias:'_omp_set_default_device_'::omp_set_default_device
!dec$ attributes alias:'_omp_get_num_devices_'::omp_get_num_devices
!dec$ attributes alias:'_omp_get_num_teams_'::omp_get_num_teams
!dec$ attributes alias:'_omp_get_team_num_'::omp_get_team_num
!dec$ attributes alias:'_omp_get_cancellation_'::omp_get_cancellation
!dec$ attributes alias:'_omp_is_initial_device_'::omp_is_initial_device
!dec$ attributes alias:'_omp_get_initial_device_'::omp_get_initial_device
!dec$ attributes alias:'_omp_get_max_task_priorty_'::omp_get_max_task_priority
!dec$ attributes alias:'_omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'_omp_init_lock_with_hint_'::omp_init_lock_with_hint
!dec$ attributes alias:'_omp_destroy_lock_'::omp_destroy_lock
!dec$ attributes alias:'_omp_set_lock_'::omp_set_lock
!dec$ attributes alias:'_omp_unset_lock_'::omp_unset_lock
!dec$ attributes alias:'_omp_test_lock_'::omp_test_lock
!dec$ attributes alias:'_omp_init_nest_lock_'::omp_init_nest_lock
!dec$ attributes alias:'_omp_init_nest_lock_with_hint_'::omp_init_nest_lock_with_hint
!dec$ attributes alias:'_omp_destroy_nest_lock_'::omp_destroy_nest_lock
!dec$ attributes alias:'_omp_set_nest_lock_'::omp_set_nest_lock
!dec$ attributes alias:'_omp_unset_nest_lock_'::omp_unset_nest_lock
!dec$ attributes alias:'_omp_test_nest_lock_'::omp_test_nest_lock
!dec$ attributes alias:'_kmp_set_stacksize_'::kmp_set_stacksize
!dec$ attributes alias:'_kmp_set_stacksize_s_'::kmp_set_stacksize_s
!dec$ attributes alias:'_kmp_set_blocktime_'::kmp_set_blocktime
!dec$ attributes alias:'_kmp_set_library_serial_'::kmp_set_library_serial
!dec$ attributes alias:'_kmp_set_library_turnaround_'::kmp_set_library_turnaround
!dec$ attributes alias:'_kmp_set_library_throughput_'::kmp_set_library_throughput
!dec$ attributes alias:'_kmp_set_library_'::kmp_set_library
!dec$ attributes alias:'_kmp_get_stacksize_'::kmp_get_stacksize
!dec$ attributes alias:'_kmp_get_stacksize_s_'::kmp_get_stacksize_s
!dec$ attributes alias:'_kmp_get_blocktime_'::kmp_get_blocktime
!dec$ attributes alias:'_kmp_get_library_'::kmp_get_library
!dec$ attributes alias:'_kmp_set_affinity_'::kmp_set_affinity
!dec$ attributes alias:'_kmp_get_affinity_'::kmp_get_affinity
!dec$ attributes alias:'_kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
!dec$ attributes alias:'_kmp_create_affinity_mask_'::kmp_create_affinity_mask
!dec$ attributes alias:'_kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
!dec$ attributes alias:'_kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
!dec$ attributes alias:'_kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
!dec$ attributes alias:'_kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
!dec$ attributes alias:'_kmp_malloc_'::kmp_malloc
!dec$ attributes alias:'_kmp_aligned_malloc_'::kmp_aligned_malloc
!dec$ attributes alias:'_kmp_calloc_'::kmp_calloc
!dec$ attributes alias:'_kmp_realloc_'::kmp_realloc
!dec$ attributes alias:'_kmp_free_'::kmp_free
!dec$ attributes alias:'_kmp_set_warnings_on_'::kmp_set_warnings_on
!dec$ attributes alias:'_kmp_set_warnings_off_'::kmp_set_warnings_off
!dec$ attributes alias:'_kmp_get_cancellation_status_'::kmp_get_cancellation_status
!dec$ endif
end module omp_lib
-524
View File
@@ -1,524 +0,0 @@
! include/45/omp_lib.f90.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
module omp_lib_kinds
use, intrinsic :: iso_c_binding
integer, parameter :: omp_integer_kind = c_int
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = c_float
integer, parameter :: kmp_double_kind = c_double
integer, parameter :: omp_lock_kind = c_intptr_t
integer, parameter :: omp_nest_lock_kind = c_intptr_t
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: omp_proc_bind_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = c_intptr_t
integer, parameter :: kmp_size_t_kind = c_size_t
integer, parameter :: kmp_affinity_mask_kind = c_intptr_t
integer, parameter :: kmp_cancel_kind = omp_integer_kind
integer, parameter :: omp_lock_hint_kind = omp_integer_kind
end module omp_lib_kinds
module omp_lib
use omp_lib_kinds
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*) kmp_build_date
parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_parallel = 1
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_loop = 2
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_sections = 3
integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_taskgroup = 4
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_none = 0
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_uncontended = 1
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_contended = 2
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_nonspeculative = 4
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_speculative = 8
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_hle = 65536
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_rtm = 131072
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_adaptive = 262144
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(num_threads) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: num_threads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(dynamic_threads) bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind), value :: dynamic_threads
end subroutine omp_set_dynamic
subroutine omp_set_nested(nested) bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind), value :: nested
end subroutine omp_set_nested
function omp_get_num_threads() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
integer (kind=omp_integer_kind), value :: level
end function omp_get_ancestor_thread_num
function omp_get_team_size(level) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_team_size
integer (kind=omp_integer_kind), value :: level
end function omp_get_team_size
subroutine omp_set_schedule(kind, chunk_size) bind(c)
use omp_lib_kinds
integer (kind=omp_sched_kind), value :: kind
integer (kind=omp_integer_kind), value :: chunk_size
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, chunk_size) bind(c)
use omp_lib_kinds
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_get_schedule
function omp_get_proc_bind() bind(c)
use omp_lib_kinds
integer (kind=omp_proc_bind_kind) omp_get_proc_bind
end function omp_get_proc_bind
function omp_get_num_places() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_places
end function omp_get_num_places
function omp_get_place_num_procs(place_num) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: place_num
integer (kind=omp_integer_kind) omp_get_place_num_procs
end function omp_get_place_num_procs
subroutine omp_get_place_proc_ids(place_num, ids) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: place_num
integer (kind=omp_integer_kind) ids(*)
end subroutine omp_get_place_proc_ids
function omp_get_place_num() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_place_num
end function omp_get_place_num
function omp_get_partition_num_places() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_partition_num_places
end function omp_get_partition_num_places
subroutine omp_get_partition_place_nums(place_nums) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) place_nums(*)
end subroutine omp_get_partition_place_nums
function omp_get_wtime() bind(c)
use omp_lib_kinds
real (kind=kmp_double_kind) omp_get_wtime
end function omp_get_wtime
function omp_get_wtick() bind(c)
use omp_lib_kinds
real (kind=kmp_double_kind) omp_get_wtick
end function omp_get_wtick
function omp_get_default_device() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_default_device
end function omp_get_default_device
subroutine omp_set_default_device(device_num) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: device_num
end subroutine omp_set_default_device
function omp_get_num_devices() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_devices
end function omp_get_num_devices
function omp_get_num_teams() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_num_teams
end function omp_get_num_teams
function omp_get_team_num() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_team_num
end function omp_get_team_num
function omp_get_cancellation() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_cancellation
end function omp_get_cancellation
function omp_is_initial_device() bind(c)
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_is_initial_device
end function omp_is_initial_device
function omp_get_initial_device() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_initial_device
end function omp_get_initial_device
subroutine omp_init_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_init_lock
subroutine omp_destroy_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_destroy_lock
subroutine omp_set_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_set_lock
subroutine omp_unset_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
end subroutine omp_unset_lock
function omp_test_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_lock
!DIR$ ENDIF
use omp_lib_kinds
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) svar
end function omp_test_lock
subroutine omp_init_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_nest_lock
!DIR$ ENDIF
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) nvar
end function omp_test_nest_lock
function omp_get_max_task_priority() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_max_task_priority
end function omp_get_max_task_priority
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size) bind(c)
use omp_lib_kinds
integer (kind=kmp_size_t_kind), value :: size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial() bind(c)
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround() bind(c)
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput() bind(c)
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string) bind(c)
use, intrinsic :: iso_c_binding
character (kind=c_char) :: string(*)
end subroutine kmp_set_defaults
function kmp_get_stacksize() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s() bind(c)
use omp_lib_kinds
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
subroutine kmp_set_disp_num_buffers(num) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind), value :: num
end subroutine kmp_set_disp_num_buffers
function kmp_set_affinity(mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask) bind(c)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask) bind(c)
use omp_lib_kinds
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask) bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind), value :: size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind), value :: size
integer (kind=kmp_size_t_kind), value :: alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind), value :: nelem
integer (kind=kmp_size_t_kind), value :: elsize
end function kmp_calloc
function kmp_realloc(ptr, size) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind), value :: ptr
integer (kind=kmp_size_t_kind), value :: size
end function kmp_realloc
subroutine kmp_free(ptr) bind(c)
use omp_lib_kinds
integer (kind=kmp_pointer_kind), value :: ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on() bind(c)
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off() bind(c)
end subroutine kmp_set_warnings_off
function kmp_get_cancellation_status(cancelkind) bind(c)
use omp_lib_kinds
integer (kind=kmp_cancel_kind), value :: cancelkind
logical (kind=omp_logical_kind) kmp_get_cancellation_status
end function kmp_get_cancellation_status
subroutine omp_init_lock_with_hint(svar, hint) bind(c)
use omp_lib_kinds
integer (kind=omp_lock_kind) svar
integer (kind=omp_lock_hint_kind), value :: hint
end subroutine omp_init_lock_with_hint
subroutine omp_init_nest_lock_with_hint(nvar, hint) bind(c)
use omp_lib_kinds
integer (kind=omp_nest_lock_kind) nvar
integer (kind=omp_lock_hint_kind), value :: hint
end subroutine omp_init_nest_lock_with_hint
end interface
end module omp_lib
-645
View File
@@ -1,645 +0,0 @@
! include/45/omp_lib.h.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!//
!//===----------------------------------------------------------------------===//
!
!***
!*** Some of the directives for the following routine extend past column 72,
!*** so process this file in 132-column mode.
!***
!DIR$ fixedformlinesize:132
integer, parameter :: omp_integer_kind = 4
integer, parameter :: omp_logical_kind = 4
integer, parameter :: omp_real_kind = 4
integer, parameter :: omp_lock_kind = int_ptr_kind()
integer, parameter :: omp_nest_lock_kind = int_ptr_kind()
integer, parameter :: omp_sched_kind = omp_integer_kind
integer, parameter :: omp_proc_bind_kind = omp_integer_kind
integer, parameter :: kmp_pointer_kind = int_ptr_kind()
integer, parameter :: kmp_size_t_kind = int_ptr_kind()
integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
integer, parameter :: omp_lock_hint_kind = omp_integer_kind
integer (kind=omp_integer_kind), parameter :: openmp_version = @LIBOMP_OMP_YEAR_MONTH@
integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
character(*) kmp_build_date
parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
integer(kind=omp_sched_kind), parameter :: omp_sched_static = 1
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_none = 0
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_uncontended = 1
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_contended = 2
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_nonspeculative = 4
integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_speculative = 8
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_hle = 65536
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_rtm = 131072
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_adaptive = 262144
interface
! ***
! *** omp_* entry points
! ***
subroutine omp_set_num_threads(num_threads) bind(c)
import
integer (kind=omp_integer_kind), value :: num_threads
end subroutine omp_set_num_threads
subroutine omp_set_dynamic(dynamic_threads) bind(c)
import
logical (kind=omp_logical_kind), value :: dynamic_threads
end subroutine omp_set_dynamic
subroutine omp_set_nested(nested) bind(c)
import
logical (kind=omp_logical_kind), value :: nested
end subroutine omp_set_nested
function omp_get_num_threads() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_threads
end function omp_get_num_threads
function omp_get_max_threads() bind(c)
import
integer (kind=omp_integer_kind) omp_get_max_threads
end function omp_get_max_threads
function omp_get_thread_num() bind(c)
import
integer (kind=omp_integer_kind) omp_get_thread_num
end function omp_get_thread_num
function omp_get_num_procs() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_procs
end function omp_get_num_procs
function omp_in_parallel() bind(c)
import
logical (kind=omp_logical_kind) omp_in_parallel
end function omp_in_parallel
function omp_in_final() bind(c)
import
logical (kind=omp_logical_kind) omp_in_final
end function omp_in_final
function omp_get_dynamic() bind(c)
import
logical (kind=omp_logical_kind) omp_get_dynamic
end function omp_get_dynamic
function omp_get_nested() bind(c)
import
logical (kind=omp_logical_kind) omp_get_nested
end function omp_get_nested
function omp_get_thread_limit() bind(c)
import
integer (kind=omp_integer_kind) omp_get_thread_limit
end function omp_get_thread_limit
subroutine omp_set_max_active_levels(max_levels) bind(c)
import
integer (kind=omp_integer_kind), value :: max_levels
end subroutine omp_set_max_active_levels
function omp_get_max_active_levels() bind(c)
import
integer (kind=omp_integer_kind) omp_get_max_active_levels
end function omp_get_max_active_levels
function omp_get_level() bind(c)
import
integer (kind=omp_integer_kind) omp_get_level
end function omp_get_level
function omp_get_active_level() bind(c)
import
integer (kind=omp_integer_kind) omp_get_active_level
end function omp_get_active_level
function omp_get_ancestor_thread_num(level) bind(c)
import
integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
integer (kind=omp_integer_kind), value :: level
end function omp_get_ancestor_thread_num
function omp_get_team_size(level) bind(c)
import
integer (kind=omp_integer_kind) omp_get_team_size
integer (kind=omp_integer_kind), value :: level
end function omp_get_team_size
subroutine omp_set_schedule(kind, chunk_size) bind(c)
import
integer (kind=omp_sched_kind), value :: kind
integer (kind=omp_integer_kind), value :: chunk_size
end subroutine omp_set_schedule
subroutine omp_get_schedule(kind, chunk_size) bind(c)
import
integer (kind=omp_sched_kind) kind
integer (kind=omp_integer_kind) chunk_size
end subroutine omp_get_schedule
function omp_get_proc_bind() bind(c)
import
integer (kind=omp_proc_bind_kind) omp_get_proc_bind
end function omp_get_proc_bind
function omp_get_num_places() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_places
end function omp_get_num_places
function omp_get_place_num_procs(place_num) bind(c)
import
integer (kind=omp_integer_kind), value :: place_num
integer (kind=omp_integer_kind) omp_get_place_num_procs
end function omp_get_place_num_procs
subroutine omp_get_place_proc_ids(place_num, ids) bind(c)
import
integer (kind=omp_integer_kind), value :: place_num
integer (kind=omp_integer_kind) ids(*)
end subroutine omp_get_place_proc_ids
function omp_get_place_num() bind(c)
import
integer (kind=omp_integer_kind) omp_get_place_num
end function omp_get_place_num
function omp_get_partition_num_places() bind(c)
import
integer (kind=omp_integer_kind) omp_get_partition_num_places
end function omp_get_partition_num_places
subroutine omp_get_partition_place_nums(place_nums) bind(c)
import
integer (kind=omp_integer_kind) place_nums(*)
end subroutine omp_get_partition_place_nums
function omp_get_wtime() bind(c)
double precision omp_get_wtime
end function omp_get_wtime
function omp_get_wtick() bind(c)
double precision omp_get_wtick
end function omp_get_wtick
function omp_get_default_device() bind(c)
import
integer (kind=omp_integer_kind) omp_get_default_device
end function omp_get_default_device
subroutine omp_set_default_device(device_num) bind(c)
import
integer (kind=omp_integer_kind), value :: device_num
end subroutine omp_set_default_device
function omp_get_num_devices() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_devices
end function omp_get_num_devices
function omp_get_num_teams() bind(c)
import
integer (kind=omp_integer_kind) omp_get_num_teams
end function omp_get_num_teams
function omp_get_team_num() bind(c)
import
integer (kind=omp_integer_kind) omp_get_team_num
end function omp_get_team_num
function omp_is_initial_device() bind(c)
import
logical (kind=omp_logical_kind) omp_is_initial_device
end function omp_is_initial_device
function omp_get_initial_device() bind(c)
import
integer (kind=omp_integer_kind) omp_get_initial_device
end function omp_get_initial_device
subroutine omp_init_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_init_lock
subroutine omp_destroy_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_destroy_lock
subroutine omp_set_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_set_lock
subroutine omp_unset_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_lock
!DIR$ ENDIF
import
integer (kind=omp_lock_kind) svar
end subroutine omp_unset_lock
function omp_test_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_lock
!DIR$ ENDIF
import
logical (kind=omp_logical_kind) omp_test_lock
integer (kind=omp_lock_kind) svar
end function omp_test_lock
subroutine omp_init_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_init_nest_lock
subroutine omp_destroy_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_destroy_nest_lock
subroutine omp_set_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_set_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_set_nest_lock
subroutine omp_unset_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_nest_lock_kind) nvar
end subroutine omp_unset_nest_lock
function omp_test_nest_lock(nvar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_test_nest_lock
!DIR$ ENDIF
import
integer (kind=omp_integer_kind) omp_test_nest_lock
integer (kind=omp_nest_lock_kind) nvar
end function omp_test_nest_lock
function omp_get_max_task_priority() bind(c)
import
integer (kind=omp_integer_kind) omp_get_max_task_priority
end function omp_get_max_task_priority
! ***
! *** kmp_* entry points
! ***
subroutine kmp_set_stacksize(size) bind(c)
import
integer (kind=omp_integer_kind), value :: size
end subroutine kmp_set_stacksize
subroutine kmp_set_stacksize_s(size) bind(c)
import
integer (kind=kmp_size_t_kind), value :: size
end subroutine kmp_set_stacksize_s
subroutine kmp_set_blocktime(msec) bind(c)
import
integer (kind=omp_integer_kind), value :: msec
end subroutine kmp_set_blocktime
subroutine kmp_set_library_serial() bind(c)
end subroutine kmp_set_library_serial
subroutine kmp_set_library_turnaround() bind(c)
end subroutine kmp_set_library_turnaround
subroutine kmp_set_library_throughput() bind(c)
end subroutine kmp_set_library_throughput
subroutine kmp_set_library(libnum) bind(c)
import
integer (kind=omp_integer_kind), value :: libnum
end subroutine kmp_set_library
subroutine kmp_set_defaults(string) bind(c)
character string(*)
end subroutine kmp_set_defaults
function kmp_get_stacksize() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_stacksize
end function kmp_get_stacksize
function kmp_get_stacksize_s() bind(c)
import
integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
end function kmp_get_stacksize_s
function kmp_get_blocktime() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_blocktime
end function kmp_get_blocktime
function kmp_get_library() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_library
end function kmp_get_library
subroutine kmp_set_disp_num_buffers(num) bind(c)
import
integer (kind=omp_integer_kind), value :: num
end subroutine kmp_set_disp_num_buffers
function kmp_set_affinity(mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_set_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity
function kmp_get_affinity(mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_get_affinity
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity
function kmp_get_affinity_max_proc() bind(c)
import
integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
end function kmp_get_affinity_max_proc
subroutine kmp_create_affinity_mask(mask) bind(c)
import
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_create_affinity_mask
subroutine kmp_destroy_affinity_mask(mask) bind(c)
import
integer (kind=kmp_affinity_mask_kind) mask
end subroutine kmp_destroy_affinity_mask
function kmp_set_affinity_mask_proc(proc, mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_set_affinity_mask_proc
function kmp_unset_affinity_mask_proc(proc, mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_unset_affinity_mask_proc
function kmp_get_affinity_mask_proc(proc, mask) bind(c)
import
integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
integer (kind=omp_integer_kind), value :: proc
integer (kind=kmp_affinity_mask_kind) mask
end function kmp_get_affinity_mask_proc
function kmp_malloc(size) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_malloc
integer (kind=kmp_size_t_kind), value :: size
end function kmp_malloc
function kmp_aligned_malloc(size, alignment) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_aligned_malloc
integer (kind=kmp_size_t_kind), value :: size
integer (kind=kmp_size_t_kind), value :: alignment
end function kmp_aligned_malloc
function kmp_calloc(nelem, elsize) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_calloc
integer (kind=kmp_size_t_kind), value :: nelem
integer (kind=kmp_size_t_kind), value :: elsize
end function kmp_calloc
function kmp_realloc(ptr, size) bind(c)
import
integer (kind=kmp_pointer_kind) kmp_realloc
integer (kind=kmp_pointer_kind), value :: ptr
integer (kind=kmp_size_t_kind), value :: size
end function kmp_realloc
subroutine kmp_free(ptr) bind(c)
import
integer (kind=kmp_pointer_kind), value :: ptr
end subroutine kmp_free
subroutine kmp_set_warnings_on() bind(c)
end subroutine kmp_set_warnings_on
subroutine kmp_set_warnings_off() bind(c)
end subroutine kmp_set_warnings_off
subroutine omp_init_lock_with_hint(svar, hint) bind(c)
import
integer (kind=omp_lock_kind) svar
integer (kind=omp_lock_hint_kind), value :: hint
end subroutine omp_init_lock_with_hint
subroutine omp_init_nest_lock_with_hint(nvar, hint) bind(c)
import
integer (kind=omp_nest_lock_kind) nvar
integer (kind=omp_lock_hint_kind), value :: hint
end subroutine omp_init_nest_lock_with_hint
end interface
!DIR$ IF DEFINED (__INTEL_OFFLOAD)
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_num_threads
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_dynamic
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_nested
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_threads
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_threads
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_thread_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_procs
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_in_parallel
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_in_final
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_dynamic
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_nested
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_thread_limit
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_max_active_levels
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_active_levels
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_level
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_active_level
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_ancestor_thread_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_team_size
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_schedule
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_schedule
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_proc_bind
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_wtime
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_wtick
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_default_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_default_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_is_initial_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_initial_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_devices
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_teams
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_team_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_destroy_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_unset_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_test_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_destroy_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_unset_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_test_nest_lock
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_task_priority
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_stacksize
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_stacksize_s
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_blocktime
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_serial
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_turnaround
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_throughput
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_defaults
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_stacksize
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_stacksize_s
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_blocktime
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_library
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_disp_num_buffers
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_affinity
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity_max_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_create_affinity_mask
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_destroy_affinity_mask
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_affinity_mask_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_unset_affinity_mask_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity_mask_proc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_malloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_aligned_malloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_calloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_realloc
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_free
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_warnings_on
!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_warnings_off
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_lock_with_hint
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_nest_lock_with_hint
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!$omp declare target(omp_set_num_threads )
!$omp declare target(omp_set_dynamic )
!$omp declare target(omp_set_nested )
!$omp declare target(omp_get_num_threads )
!$omp declare target(omp_get_max_threads )
!$omp declare target(omp_get_thread_num )
!$omp declare target(omp_get_num_procs )
!$omp declare target(omp_in_parallel )
!$omp declare target(omp_in_final )
!$omp declare target(omp_get_dynamic )
!$omp declare target(omp_get_nested )
!$omp declare target(omp_get_thread_limit )
!$omp declare target(omp_set_max_active_levels )
!$omp declare target(omp_get_max_active_levels )
!$omp declare target(omp_get_level )
!$omp declare target(omp_get_active_level )
!$omp declare target(omp_get_ancestor_thread_num )
!$omp declare target(omp_get_team_size )
!$omp declare target(omp_set_schedule )
!$omp declare target(omp_get_schedule )
!$omp declare target(omp_get_proc_bind )
!$omp declare target(omp_get_wtime )
!$omp declare target(omp_get_wtick )
!$omp declare target(omp_get_default_device )
!$omp declare target(omp_set_default_device )
!$omp declare target(omp_is_initial_device )
!$omp declare target(omp_get_initial_device )
!$omp declare target(omp_get_num_devices )
!$omp declare target(omp_get_num_teams )
!$omp declare target(omp_get_team_num )
!$omp declare target(omp_init_lock )
!$omp declare target(omp_destroy_lock )
!$omp declare target(omp_set_lock )
!$omp declare target(omp_unset_lock )
!$omp declare target(omp_test_lock )
!$omp declare target(omp_init_nest_lock )
!$omp declare target(omp_destroy_nest_lock )
!$omp declare target(omp_set_nest_lock )
!$omp declare target(omp_unset_nest_lock )
!$omp declare target(omp_test_nest_lock )
!$omp declare target(omp_get_max_task_priority )
!$omp declare target(kmp_set_stacksize )
!$omp declare target(kmp_set_stacksize_s )
!$omp declare target(kmp_set_blocktime )
!$omp declare target(kmp_set_library_serial )
!$omp declare target(kmp_set_library_turnaround )
!$omp declare target(kmp_set_library_throughput )
!$omp declare target(kmp_set_library )
!$omp declare target(kmp_set_defaults )
!$omp declare target(kmp_get_stacksize )
!$omp declare target(kmp_get_stacksize_s )
!$omp declare target(kmp_get_blocktime )
!$omp declare target(kmp_get_library )
!$omp declare target(kmp_set_disp_num_buffers )
!$omp declare target(kmp_set_affinity )
!$omp declare target(kmp_get_affinity )
!$omp declare target(kmp_get_affinity_max_proc )
!$omp declare target(kmp_create_affinity_mask )
!$omp declare target(kmp_destroy_affinity_mask )
!$omp declare target(kmp_set_affinity_mask_proc )
!$omp declare target(kmp_unset_affinity_mask_proc )
!$omp declare target(kmp_get_affinity_mask_proc )
!$omp declare target(kmp_malloc )
!$omp declare target(kmp_aligned_malloc )
!$omp declare target(kmp_calloc )
!$omp declare target(kmp_realloc )
!$omp declare target(kmp_free )
!$omp declare target(kmp_set_warnings_on )
!$omp declare target(kmp_set_warnings_off )
!$omp declare target(omp_init_lock_with_hint )
!$omp declare target(omp_init_nest_lock_with_hint )
!DIR$ ENDIF
!DIR$ ENDIF
@@ -1,13 +1,12 @@
/*
* include/50/omp-tools.h.var
* include/omp-tools.h.var
*/
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
@@ -372,7 +371,7 @@ typedef enum ompt_frame_flag_t {
ompt_frame_cfa = 0x10,
ompt_frame_framepointer = 0x20,
ompt_frame_stackaddress = 0x30
} ompt_frame_flag_t;
} ompt_frame_flag_t;
typedef enum ompt_state_t {
ompt_state_work_serial = 0x000,
@@ -721,14 +720,14 @@ typedef void (*ompt_callback_dispatch_t) (
ompt_data_t *parallel_data,
ompt_data_t *task_data,
ompt_dispatch_t kind,
ompt_data_t instance
ompt_data_t instance
);
typedef struct ompt_record_dispatch_t {
ompt_id_t parallel_id;
ompt_id_t task_id;
ompt_dispatch_t kind;
ompt_data_t instance;
ompt_data_t instance;
} ompt_record_dispatch_t;
typedef void (*ompt_callback_task_create_t) (
@@ -1,14 +1,13 @@
/*
* include/50/omp.h.var
* include/omp.h.var
*/
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
@@ -16,6 +15,9 @@
#ifndef __OMP_H
# define __OMP_H
# include <stdlib.h>
# include <stdint.h>
# define KMP_VERSION_MAJOR @LIBOMP_VERSION_MAJOR@
# define KMP_VERSION_MINOR @LIBOMP_VERSION_MINOR@
# define KMP_VERSION_BUILD @LIBOMP_VERSION_BUILD@
@@ -44,10 +46,11 @@
/* schedule kind constants */
typedef enum omp_sched_t {
omp_sched_static = 1,
omp_sched_dynamic = 2,
omp_sched_guided = 3,
omp_sched_auto = 4
omp_sched_static = 1,
omp_sched_dynamic = 2,
omp_sched_guided = 3,
omp_sched_auto = 4,
omp_sched_monotonic = 0x80000000
} omp_sched_t;
/* set API functions */
@@ -134,7 +137,6 @@
extern int __KAI_KMPC_CONVENTION omp_get_team_num (void);
extern int __KAI_KMPC_CONVENTION omp_get_cancellation (void);
# include <stdlib.h>
/* OpenMP 4.5 */
extern int __KAI_KMPC_CONVENTION omp_get_initial_device (void);
extern void* __KAI_KMPC_CONVENTION omp_target_alloc(size_t, int);
@@ -148,6 +150,7 @@
/* OpenMP 5.0 */
extern int __KAI_KMPC_CONVENTION omp_get_device_num (void);
typedef void * omp_depend_t;
/* kmp API functions */
extern int __KAI_KMPC_CONVENTION kmp_get_stacksize (void);
@@ -218,30 +221,113 @@
omp_control_tool_flush = 3,
omp_control_tool_end = 4
} omp_control_tool_t;
extern int __KAI_KMPC_CONVENTION omp_control_tool(int, int, void*);
/* OpenMP 5.0 Memory Management */
typedef void *omp_allocator_t;
extern __KMP_IMP const omp_allocator_t *OMP_NULL_ALLOCATOR;
extern __KMP_IMP const omp_allocator_t *omp_default_mem_alloc;
extern __KMP_IMP const omp_allocator_t *omp_large_cap_mem_alloc;
extern __KMP_IMP const omp_allocator_t *omp_const_mem_alloc;
extern __KMP_IMP const omp_allocator_t *omp_high_bw_mem_alloc;
extern __KMP_IMP const omp_allocator_t *omp_low_lat_mem_alloc;
extern __KMP_IMP const omp_allocator_t *omp_cgroup_mem_alloc;
extern __KMP_IMP const omp_allocator_t *omp_pteam_mem_alloc;
extern __KMP_IMP const omp_allocator_t *omp_thread_mem_alloc;
typedef uintptr_t omp_uintptr_t;
extern void __KAI_KMPC_CONVENTION omp_set_default_allocator(const omp_allocator_t *);
extern const omp_allocator_t * __KAI_KMPC_CONVENTION omp_get_default_allocator(void);
#ifdef __cplusplus
extern void *__KAI_KMPC_CONVENTION omp_alloc(size_t size, const omp_allocator_t *allocator = OMP_NULL_ALLOCATOR);
extern void __KAI_KMPC_CONVENTION omp_free(void * ptr, const omp_allocator_t *allocator = OMP_NULL_ALLOCATOR);
#else
extern void *__KAI_KMPC_CONVENTION omp_alloc(size_t size, const omp_allocator_t *allocator);
extern void __KAI_KMPC_CONVENTION omp_free(void *ptr, const omp_allocator_t *allocator);
#endif
typedef enum {
OMP_ATK_THREADMODEL = 1,
OMP_ATK_ALIGNMENT = 2,
OMP_ATK_ACCESS = 3,
OMP_ATK_POOL_SIZE = 4,
OMP_ATK_FALLBACK = 5,
OMP_ATK_FB_DATA = 6,
OMP_ATK_PINNED = 7,
OMP_ATK_PARTITION = 8
} omp_alloctrait_key_t;
typedef enum {
OMP_ATV_FALSE = 0,
OMP_ATV_TRUE = 1,
OMP_ATV_DEFAULT = 2,
OMP_ATV_CONTENDED = 3,
OMP_ATV_UNCONTENDED = 4,
OMP_ATV_SEQUENTIAL = 5,
OMP_ATV_PRIVATE = 6,
OMP_ATV_ALL = 7,
OMP_ATV_THREAD = 8,
OMP_ATV_PTEAM = 9,
OMP_ATV_CGROUP = 10,
OMP_ATV_DEFAULT_MEM_FB = 11,
OMP_ATV_NULL_FB = 12,
OMP_ATV_ABORT_FB = 13,
OMP_ATV_ALLOCATOR_FB = 14,
OMP_ATV_ENVIRONMENT = 15,
OMP_ATV_NEAREST = 16,
OMP_ATV_BLOCKED = 17,
OMP_ATV_INTERLEAVED = 18
} omp_alloctrait_value_t;
typedef struct {
omp_alloctrait_key_t key;
omp_uintptr_t value;
} omp_alloctrait_t;
# if defined(_WIN32)
// On Windows cl and icl do not support 64-bit enum, let's use integer then.
typedef omp_uintptr_t omp_allocator_handle_t;
extern __KMP_IMP omp_allocator_handle_t const omp_null_allocator;
extern __KMP_IMP omp_allocator_handle_t const omp_default_mem_alloc;
extern __KMP_IMP omp_allocator_handle_t const omp_large_cap_mem_alloc;
extern __KMP_IMP omp_allocator_handle_t const omp_const_mem_alloc;
extern __KMP_IMP omp_allocator_handle_t const omp_high_bw_mem_alloc;
extern __KMP_IMP omp_allocator_handle_t const omp_low_lat_mem_alloc;
extern __KMP_IMP omp_allocator_handle_t const omp_cgroup_mem_alloc;
extern __KMP_IMP omp_allocator_handle_t const omp_pteam_mem_alloc;
extern __KMP_IMP omp_allocator_handle_t const omp_thread_mem_alloc;
typedef omp_uintptr_t omp_memspace_handle_t;
extern __KMP_IMP omp_memspace_handle_t const omp_default_mem_space;
extern __KMP_IMP omp_memspace_handle_t const omp_large_cap_mem_space;
extern __KMP_IMP omp_memspace_handle_t const omp_const_mem_space;
extern __KMP_IMP omp_memspace_handle_t const omp_high_bw_mem_space;
extern __KMP_IMP omp_memspace_handle_t const omp_low_lat_mem_space;
# else
# if __cplusplus >= 201103
typedef enum omp_allocator_handle_t : omp_uintptr_t
# else
typedef enum omp_allocator_handle_t
# endif
{
omp_null_allocator = 0,
omp_default_mem_alloc = 1,
omp_large_cap_mem_alloc = 2,
omp_const_mem_alloc = 3,
omp_high_bw_mem_alloc = 4,
omp_low_lat_mem_alloc = 5,
omp_cgroup_mem_alloc = 6,
omp_pteam_mem_alloc = 7,
omp_thread_mem_alloc = 8,
KMP_ALLOCATOR_MAX_HANDLE = UINTPTR_MAX
} omp_allocator_handle_t;
# if __cplusplus >= 201103
typedef enum omp_memspace_handle_t : omp_uintptr_t
# else
typedef enum omp_memspace_handle_t
# endif
{
omp_default_mem_space = 0,
omp_large_cap_mem_space = 1,
omp_const_mem_space = 2,
omp_high_bw_mem_space = 3,
omp_low_lat_mem_space = 4,
KMP_MEMSPACE_MAX_HANDLE = UINTPTR_MAX
} omp_memspace_handle_t;
# endif
extern omp_allocator_handle_t __KAI_KMPC_CONVENTION omp_init_allocator(omp_memspace_handle_t m,
int ntraits, omp_alloctrait_t traits[]);
extern void __KAI_KMPC_CONVENTION omp_destroy_allocator(omp_allocator_handle_t allocator);
extern void __KAI_KMPC_CONVENTION omp_set_default_allocator(omp_allocator_handle_t a);
extern omp_allocator_handle_t __KAI_KMPC_CONVENTION omp_get_default_allocator(void);
# ifdef __cplusplus
extern void *__KAI_KMPC_CONVENTION omp_alloc(size_t size, omp_allocator_handle_t a = omp_null_allocator);
extern void __KAI_KMPC_CONVENTION omp_free(void * ptr, omp_allocator_handle_t a = omp_null_allocator);
# else
extern void *__KAI_KMPC_CONVENTION omp_alloc(size_t size, omp_allocator_handle_t a);
extern void __KAI_KMPC_CONVENTION omp_free(void *ptr, omp_allocator_handle_t a);
# endif
/* OpenMP 5.0 Affinity Format */
extern void __KAI_KMPC_CONVENTION omp_set_affinity_format(char const *);
@@ -249,6 +335,26 @@
extern void __KAI_KMPC_CONVENTION omp_display_affinity(char const *);
extern size_t __KAI_KMPC_CONVENTION omp_capture_affinity(char *, size_t, char const *);
/* OpenMP 5.0 events */
# if defined(_WIN32)
// On Windows cl and icl do not support 64-bit enum, let's use integer then.
typedef omp_uintptr_t omp_event_handle_t;
# else
typedef enum omp_event_handle_t { KMP_EVENT_MAX_HANDLE = UINTPTR_MAX } omp_event_handle_t;
# endif
extern void __KAI_KMPC_CONVENTION omp_fulfill_event ( omp_event_handle_t event );
/* OpenMP 5.0 Pause Resources */
typedef enum omp_pause_resource_t {
omp_pause_resume = 0,
omp_pause_soft = 1,
omp_pause_hard = 2
} omp_pause_resource_t;
extern int __KAI_KMPC_CONVENTION omp_pause_resource(omp_pause_resource_t, int);
extern int __KAI_KMPC_CONVENTION omp_pause_resource_all(omp_pause_resource_t);
extern int __KAI_KMPC_CONVENTION omp_get_supported_active_levels(void);
# undef __KAI_KMPC_CONVENTION
# undef __KMP_IMP
@@ -1,12 +1,11 @@
! include/50/omp_lib.f.var
! include/omp_lib.f.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
!// See https://llvm.org/LICENSE.txt for license information.
!// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
!//
!//===----------------------------------------------------------------------===//
!
@@ -34,7 +33,19 @@
integer, parameter :: omp_lock_hint_kind = omp_integer_kind
integer, parameter :: omp_control_tool_kind = omp_integer_kind
integer, parameter :: omp_control_tool_result_kind = omp_integer_kind
integer, parameter :: omp_allocator_kind = int_ptr_kind()
integer, parameter :: omp_allocator_handle_kind = int_ptr_kind()
integer, parameter :: omp_memspace_handle_kind = int_ptr_kind()
integer, parameter :: omp_alloctrait_key_kind = omp_integer_kind
integer, parameter :: omp_alloctrait_val_kind = int_ptr_kind()
type omp_alloctrait
integer(kind=omp_alloctrait_key_kind) key
integer(kind=omp_alloctrait_val_kind) value
end type omp_alloctrait
integer, parameter :: omp_pause_resource_kind = omp_integer_kind
integer, parameter :: omp_depend_kind = int_ptr_kind()
integer, parameter :: omp_event_handle_kind = int_ptr_kind()
end module omp_lib_kinds
@@ -52,6 +63,7 @@
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer(kind=omp_sched_kind), parameter :: omp_sched_monotonic = Z'80000000'
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
@@ -73,15 +85,54 @@
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_rtm = 131072
integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_adaptive = 262144
integer (kind=omp_allocator_kind), parameter :: omp_null_allocator = 0
integer (kind=omp_allocator_kind), parameter :: omp_default_mem_alloc = 1
integer (kind=omp_allocator_kind), parameter :: omp_large_cap_mem_alloc = 2
integer (kind=omp_allocator_kind), parameter :: omp_const_mem_alloc = 3
integer (kind=omp_allocator_kind), parameter :: omp_high_bw_mem_alloc = 4
integer (kind=omp_allocator_kind), parameter :: omp_low_lat_mem_alloc = 5
integer (kind=omp_allocator_kind), parameter :: omp_cgroup_mem_alloc = 6
integer (kind=omp_allocator_kind), parameter :: omp_pteam_mem_alloc = 7
integer (kind=omp_allocator_kind), parameter :: omp_thread_mem_alloc = 8
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_threadmodel = 1
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_alignment = 2
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_access = 3
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_pool_size = 4
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_fallback = 5
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_fb_data = 6
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_pinned = 7
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_partition = 8
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_false = 0
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_true = 1
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_default = 2
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_contended = 3
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_uncontended = 4
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_sequential = 5
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_private = 6
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_all = 7
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_thread = 8
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_pteam = 9
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_cgroup = 10
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_default_mem_fb = 11
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_null_fb = 12
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_abort_fb = 13
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_allocator_fb = 14
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_environment = 15
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_nearest = 16
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_blocked = 17
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_interleaved = 18
integer (kind=omp_allocator_handle_kind), parameter :: omp_null_allocator = 0
integer (kind=omp_allocator_handle_kind), parameter :: omp_default_mem_alloc = 1
integer (kind=omp_allocator_handle_kind), parameter :: omp_large_cap_mem_alloc = 2
integer (kind=omp_allocator_handle_kind), parameter :: omp_const_mem_alloc = 3
integer (kind=omp_allocator_handle_kind), parameter :: omp_high_bw_mem_alloc = 4
integer (kind=omp_allocator_handle_kind), parameter :: omp_low_lat_mem_alloc = 5
integer (kind=omp_allocator_handle_kind), parameter :: omp_cgroup_mem_alloc = 6
integer (kind=omp_allocator_handle_kind), parameter :: omp_pteam_mem_alloc = 7
integer (kind=omp_allocator_handle_kind), parameter :: omp_thread_mem_alloc = 8
integer (kind=omp_memspace_handle_kind), parameter :: omp_default_mem_space = 0
integer (kind=omp_memspace_handle_kind), parameter :: omp_large_cap_mem_space = 1
integer (kind=omp_memspace_handle_kind), parameter :: omp_const_mem_space = 2
integer (kind=omp_memspace_handle_kind), parameter :: omp_high_bw_mem_space = 3
integer (kind=omp_memspace_handle_kind), parameter :: omp_low_lat_mem_space = 4
integer (kind=omp_pause_resource_kind), parameter :: omp_pause_resume = 0
integer (kind=omp_pause_resource_kind), parameter :: omp_pause_soft = 1
integer (kind=omp_pause_resource_kind), parameter :: omp_pause_hard = 2
interface
@@ -283,6 +334,29 @@
integer (kind=omp_integer_kind) omp_get_device_num
end function omp_get_device_num
function omp_pause_resource(kind, device_num)
use omp_lib_kinds
integer (kind=omp_pause_resource_kind) kind
integer (kind=omp_integer_kind) device_num
integer (kind=omp_integer_kind) omp_pause_resource
end function omp_pause_resource
function omp_pause_resource_all(kind)
use omp_lib_kinds
integer (kind=omp_pause_resource_kind) kind
integer (kind=omp_integer_kind) omp_pause_resource_all
end function omp_pause_resource_all
function omp_get_supported_active_levels()
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_supported_active_levels
end function omp_get_supported_active_levels
subroutine omp_fulfill_event(event)
use omp_lib_kinds
integer (kind=omp_event_handle_kind) event
end subroutine omp_fulfill_event
subroutine omp_init_lock(svar)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
@@ -370,14 +444,27 @@
integer (kind=omp_integer_kind) omp_get_max_task_priority
end function omp_get_max_task_priority
subroutine omp_set_default_allocator(svar)
function omp_init_allocator(memspace, ntraits, traits)
use omp_lib_kinds
integer (kind=omp_allocator_kind) svar
integer (omp_allocator_handle_kind) omp_init_allocator
integer (omp_memspace_handle_kind) :: memspace
integer (omp_integer_kind) :: ntraits
type(omp_alloctrait), intent(in) :: traits(*)
end function omp_init_allocator
subroutine omp_destroy_allocator(allocator) bind(c)
use omp_lib_kinds
integer (omp_allocator_handle_kind), value :: allocator
end subroutine omp_destroy_allocator
subroutine omp_set_default_allocator(allocator) bind(c)
use omp_lib_kinds
integer (omp_allocator_handle_kind) allocator
end subroutine omp_set_default_allocator
function omp_get_default_allocator()
function omp_get_default_allocator() bind(c)
use omp_lib_kinds
integer (kind=omp_allocator_kind) omp_get_default_allocator
integer(omp_allocator_handle_kind)omp_get_default_allocator
end function omp_get_default_allocator
subroutine omp_set_affinity_format(format)
@@ -621,6 +708,11 @@
!dec$ attributes alias:'OMP_GET_INITIAL_DEVICE' :: omp_get_initial_device
!dec$ attributes alias:'OMP_GET_MAX_TASK_PRIORITY' :: omp_get_max_task_priority
!dec$ attributes alias:'OMP_GET_DEVICE_NUM' :: omp_get_device_num
!dec$ attributes alias:'OMP_PAUSE_RESOURCE' :: omp_pause_resource
!dec$ attributes alias:'OMP_PAUSE_RESOURCE_ALL' :: omp_pause_resource_all
!dec$ attributes alias:'OMP_GET_SUPPORTED_ACTIVE_LEVELS' :: omp_get_supported_active_levels
!dec$ attributes alias:'OMP_FULFILL_EVENT' :: omp_fulfill_event
!dec$ attributes alias:'OMP_CONTROL_TOOL' :: omp_control_tool
!dec$ attributes alias:'OMP_SET_AFFINITY_FORMAT' :: omp_set_affinity_format
!dec$ attributes alias:'OMP_GET_AFFINITY_FORMAT' :: omp_get_affinity_format
@@ -708,6 +800,11 @@
!dec$ attributes alias:'_OMP_GET_INITIAL_DEVICE' :: omp_get_initial_device
!dec$ attributes alias:'_OMP_GET_MAX_TASK_PRIORTY' :: omp_get_max_task_priority
!dec$ attributes alias:'_OMP_GET_DEVICE_NUM' :: omp_get_device_num
!dec$ attributes alias:'_OMP_PAUSE_RESOURCE' :: omp_pause_resource
!dec$ attributes alias:'_OMP_PAUSE_RESOURCE_ALL' :: omp_pause_resource_all
!dec$ attributes alias:'_OMP_GET_SUPPORTED_ACTIVE_LEVELS' :: omp_get_supported_active_levels
!dec$ attributes alias:'_OMP_FULFILL_EVENT' :: omp_fulfill_event
!dec$ attributes alias:'_OMP_CONTROL_TOOL' :: omp_control_tool
!dec$ attributes alias:'_OMP_SET_AFFINITY_FORMAT' :: omp_set_affinity_format
!dec$ attributes alias:'_OMP_GET_AFFINITY_FORMAT' :: omp_get_affinity_format
@@ -798,6 +895,11 @@
!dec$ attributes alias:'omp_get_initial_device_'::omp_get_initial_device
!dec$ attributes alias:'omp_get_max_task_priority_'::omp_get_max_task_priority
!dec$ attributes alias:'omp_get_device_num_'::omp_get_device_num
!dec$ attributes alias:'omp_pause_resource_' :: omp_pause_resource
!dec$ attributes alias:'omp_pause_resource_all_' :: omp_pause_resource_all
!dec$ attributes alias:'omp_get_supported_active_levels_' :: omp_get_supported_active_levels
!dec$ attributes alias:'omp_fulfill_event_' :: omp_fulfill_event
!dec$ attributes alias:'omp_set_affinity_format_' :: omp_set_affinity_format
!dec$ attributes alias:'omp_get_affinity_format_' :: omp_get_affinity_format
!dec$ attributes alias:'omp_display_affinity_' :: omp_display_affinity
@@ -887,6 +989,11 @@
!dec$ attributes alias:'_omp_get_initial_device_'::omp_get_initial_device
!dec$ attributes alias:'_omp_get_max_task_priorty_'::omp_get_max_task_priority
!dec$ attributes alias:'_omp_get_device_num_'::omp_get_device_num
!dec$ attributes alias:'_omp_pause_resource_' :: omp_pause_resource
!dec$ attributes alias:'_omp_pause_resource_all_' :: omp_pause_resource_all
!dec$ attributes alias:'_omp_get_supported_active_levels_' :: omp_get_supported_active_levels
!dec$ attributes alias:'_omp_fulfill_event_' :: omp_fulfill_event
!dec$ attributes alias:'_omp_init_lock_'::omp_init_lock
!dec$ attributes alias:'_omp_init_lock_with_hint_'::omp_init_lock_with_hint
!dec$ attributes alias:'_omp_destroy_lock_'::omp_destroy_lock
@@ -1,12 +1,11 @@
! include/50/omp_lib.f90.var
! include/omp_lib.f90.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
!// See https://llvm.org/LICENSE.txt for license information.
!// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
!//
!//===----------------------------------------------------------------------===//
!
@@ -31,7 +30,19 @@
integer, parameter :: omp_lock_hint_kind = omp_sync_hint_kind
integer, parameter :: omp_control_tool_kind = omp_integer_kind
integer, parameter :: omp_control_tool_result_kind = omp_integer_kind
integer, parameter :: omp_allocator_kind = c_intptr_t
integer, parameter :: omp_allocator_handle_kind = c_intptr_t
integer, parameter :: omp_memspace_handle_kind = c_intptr_t
integer, parameter :: omp_alloctrait_key_kind = omp_integer_kind
integer, parameter :: omp_alloctrait_val_kind = c_intptr_t
type omp_alloctrait
integer(kind=omp_alloctrait_key_kind) key
integer(kind=omp_alloctrait_val_kind) value
end type omp_alloctrait
integer, parameter :: omp_pause_resource_kind = omp_integer_kind
integer, parameter :: omp_depend_kind = c_intptr_t
integer, parameter :: omp_event_handle_kind = c_intptr_t
end module omp_lib_kinds
@@ -50,7 +61,7 @@
integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
integer(kind=omp_sched_kind), parameter :: omp_sched_guided = 3
integer(kind=omp_sched_kind), parameter :: omp_sched_auto = 4
integer(kind=omp_sched_kind), parameter :: omp_sched_monotonic = int(Z'80000000', kind=omp_sched_kind)
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
@@ -87,15 +98,54 @@
integer (kind=omp_control_tool_result_kind), parameter :: omp_control_tool_success = 0
integer (kind=omp_control_tool_result_kind), parameter :: omp_control_tool_ignored = 1
integer (kind=omp_allocator_kind), parameter :: omp_null_allocator = 0
integer (kind=omp_allocator_kind), parameter :: omp_default_mem_alloc = 1
integer (kind=omp_allocator_kind), parameter :: omp_large_cap_mem_alloc = 2
integer (kind=omp_allocator_kind), parameter :: omp_const_mem_alloc = 3
integer (kind=omp_allocator_kind), parameter :: omp_high_bw_mem_alloc = 4
integer (kind=omp_allocator_kind), parameter :: omp_low_lat_mem_alloc = 5
integer (kind=omp_allocator_kind), parameter :: omp_cgroup_mem_alloc = 6
integer (kind=omp_allocator_kind), parameter :: omp_pteam_mem_alloc = 7
integer (kind=omp_allocator_kind), parameter :: omp_thread_mem_alloc = 8
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_threadmodel = 1
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_alignment = 2
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_access = 3
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_pool_size = 4
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_fallback = 5
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_fb_data = 6
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_pinned = 7
integer (kind=omp_alloctrait_key_kind), parameter :: omp_atk_partition = 8
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_false = 0
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_true = 1
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_default = 2
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_contended = 3
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_uncontended = 4
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_sequential = 5
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_private = 6
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_all = 7
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_thread = 8
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_pteam = 9
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_cgroup = 10
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_default_mem_fb = 11
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_null_fb = 12
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_abort_fb = 13
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_allocator_fb = 14
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_environment = 15
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_nearest = 16
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_blocked = 17
integer (kind=omp_alloctrait_val_kind), parameter :: omp_atv_interleaved = 18
integer (kind=omp_allocator_handle_kind), parameter :: omp_null_allocator = 0
integer (kind=omp_allocator_handle_kind), parameter :: omp_default_mem_alloc = 1
integer (kind=omp_allocator_handle_kind), parameter :: omp_large_cap_mem_alloc = 2
integer (kind=omp_allocator_handle_kind), parameter :: omp_const_mem_alloc = 3
integer (kind=omp_allocator_handle_kind), parameter :: omp_high_bw_mem_alloc = 4
integer (kind=omp_allocator_handle_kind), parameter :: omp_low_lat_mem_alloc = 5
integer (kind=omp_allocator_handle_kind), parameter :: omp_cgroup_mem_alloc = 6
integer (kind=omp_allocator_handle_kind), parameter :: omp_pteam_mem_alloc = 7
integer (kind=omp_allocator_handle_kind), parameter :: omp_thread_mem_alloc = 8
integer (kind=omp_memspace_handle_kind), parameter :: omp_default_mem_space = 0
integer (kind=omp_memspace_handle_kind), parameter :: omp_large_cap_mem_space = 1
integer (kind=omp_memspace_handle_kind), parameter :: omp_const_mem_space = 2
integer (kind=omp_memspace_handle_kind), parameter :: omp_high_bw_mem_space = 3
integer (kind=omp_memspace_handle_kind), parameter :: omp_low_lat_mem_space = 4
integer (kind=omp_pause_resource_kind), parameter :: omp_pause_resume = 0
integer (kind=omp_pause_resource_kind), parameter :: omp_pause_soft = 1
integer (kind=omp_pause_resource_kind), parameter :: omp_pause_hard = 2
interface
@@ -299,6 +349,29 @@
integer (kind=omp_integer_kind) omp_get_device_num
end function omp_get_device_num
function omp_pause_resource(kind, device_num) bind(c)
use omp_lib_kinds
integer (kind=omp_pause_resource_kind), value :: kind
integer (kind=omp_integer_kind), value :: device_num
integer (kind=omp_integer_kind) omp_pause_resource
end function omp_pause_resource
function omp_pause_resource_all(kind) bind(c)
use omp_lib_kinds
integer (kind=omp_pause_resource_kind), value :: kind
integer (kind=omp_integer_kind) omp_pause_resource_all
end function omp_pause_resource_all
function omp_get_supported_active_levels() bind(c)
use omp_lib_kinds
integer (kind=omp_integer_kind) omp_get_supported_active_levels
end function omp_get_supported_active_levels
subroutine omp_fulfill_event(event) bind(c)
use omp_lib_kinds
integer (kind=omp_event_handle_kind), value :: event
end subroutine omp_fulfill_event
subroutine omp_init_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
@@ -386,14 +459,27 @@
integer (kind=omp_integer_kind) omp_get_max_task_priority
end function omp_get_max_task_priority
subroutine omp_set_default_allocator(svar) bind(c)
function omp_init_allocator(memspace, ntraits, traits)
use omp_lib_kinds
integer (kind=omp_allocator_kind), value :: svar
integer (kind=omp_allocator_handle_kind) omp_init_allocator
integer (kind=omp_memspace_handle_kind) :: memspace
integer (kind=omp_integer_kind) :: ntraits
type(omp_alloctrait), intent(in) :: traits(*)
end function omp_init_allocator
subroutine omp_destroy_allocator(allocator) bind(c)
use omp_lib_kinds
integer (kind=omp_allocator_handle_kind), value :: allocator
end subroutine omp_destroy_allocator
subroutine omp_set_default_allocator(allocator) bind(c)
use omp_lib_kinds
integer (kind=omp_allocator_handle_kind), value :: allocator
end subroutine omp_set_default_allocator
function omp_get_default_allocator() bind(c)
use omp_lib_kinds
integer (kind=omp_allocator_kind) omp_get_default_allocator
integer (kind=omp_allocator_handle_kind) omp_get_default_allocator
end function omp_get_default_allocator
subroutine omp_set_affinity_format(format)
@@ -1,12 +1,11 @@
! include/50/omp_lib.h.var
! include/omp_lib.h.var
!
!//===----------------------------------------------------------------------===//
!//
!// The LLVM Compiler Infrastructure
!//
!// This file is dual licensed under the MIT and the University of Illinois Open
!// Source Licenses. See LICENSE.txt for details.
!// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
!// See https://llvm.org/LICENSE.txt for license information.
!// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
!//
!//===----------------------------------------------------------------------===//
!
@@ -39,8 +38,20 @@
parameter(omp_control_tool_kind=omp_integer_kind)
integer omp_control_tool_result_kind
parameter(omp_control_tool_result_kind=omp_integer_kind)
integer omp_allocator_kind
parameter(omp_allocator_kind=int_ptr_kind())
integer omp_allocator_handle_kind
parameter(omp_allocator_handle_kind=int_ptr_kind())
integer omp_memspace_handle_kind
parameter(omp_memspace_handle_kind=int_ptr_kind())
integer omp_alloctrait_key_kind
parameter(omp_alloctrait_key_kind=omp_integer_kind)
integer omp_alloctrait_val_kind
parameter(omp_alloctrait_val_kind=int_ptr_kind())
integer omp_pause_resource_kind
parameter(omp_pause_resource_kind=omp_integer_kind)
integer omp_depend_kind
parameter(omp_depend_kind=int_ptr_kind())
integer omp_event_handle_kind
parameter(omp_event_handle_kind=int_ptr_kind())
integer(kind=omp_integer_kind)openmp_version
parameter(openmp_version=@LIBOMP_OMP_YEAR_MONTH@)
@@ -61,6 +72,8 @@
parameter(omp_sched_guided=3)
integer(kind=omp_sched_kind)omp_sched_auto
parameter(omp_sched_auto=4)
integer(kind=omp_sched_kind)omp_sched_monotonic
parameter(omp_sched_monotonic=Z'80000000')
integer(kind=omp_proc_bind_kind)omp_proc_bind_false
parameter(omp_proc_bind_false=0)
@@ -118,25 +131,106 @@
integer(omp_control_tool_result_kind)omp_control_tool_ignored
parameter(omp_control_tool_ignored=1)
integer(kind=omp_allocator_kind)omp_null_allocator
integer(kind=omp_alloctrait_key_kind)omp_atk_threadmodel
parameter(omp_atk_threadmodel=1)
integer(kind=omp_alloctrait_key_kind)omp_atk_alignment
parameter(omp_atk_alignment=2)
integer(kind=omp_alloctrait_key_kind)omp_atk_access
parameter(omp_atk_access=3)
integer(kind=omp_alloctrait_key_kind)omp_atk_pool_size
parameter(omp_atk_pool_size=4)
integer(kind=omp_alloctrait_key_kind)omp_atk_fallback
parameter(omp_atk_fallback=5)
integer(kind=omp_alloctrait_key_kind)omp_atk_fb_data
parameter(omp_atk_fb_data=6)
integer(kind=omp_alloctrait_key_kind)omp_atk_pinned
parameter(omp_atk_pinned=7)
integer(kind=omp_alloctrait_key_kind)omp_atk_partition
parameter(omp_atk_partition=8)
! Reserved for future use
integer(kind=omp_alloctrait_val_kind)omp_atv_false
parameter(omp_atv_false=0)
! Reserved for future use
integer(kind=omp_alloctrait_val_kind)omp_atv_true
parameter(omp_atv_true=1)
integer(kind=omp_alloctrait_val_kind)omp_atv_default
parameter(omp_atv_default=2)
integer(kind=omp_alloctrait_val_kind)omp_atv_contended
parameter(omp_atv_contended=3)
integer(kind=omp_alloctrait_val_kind)omp_atv_uncontended
parameter(omp_atv_uncontended=4)
integer(kind=omp_alloctrait_val_kind)omp_atv_sequential
parameter(omp_atv_sequential=5)
integer(kind=omp_alloctrait_val_kind)omp_atv_private
parameter(omp_atv_private=6)
integer(kind=omp_alloctrait_val_kind)omp_atv_all
parameter(omp_atv_all=7)
integer(kind=omp_alloctrait_val_kind)omp_atv_thread
parameter(omp_atv_thread=8)
integer(kind=omp_alloctrait_val_kind)omp_atv_pteam
parameter(omp_atv_pteam=9)
integer(kind=omp_alloctrait_val_kind)omp_atv_cgroup
parameter(omp_atv_cgroup=10)
integer(kind=omp_alloctrait_val_kind)omp_atv_default_mem_fb
parameter(omp_atv_default_mem_fb=11)
integer(kind=omp_alloctrait_val_kind)omp_atv_null_fb
parameter(omp_atv_null_fb=12)
integer(kind=omp_alloctrait_val_kind)omp_atv_abort_fb
parameter(omp_atv_abort_fb=13)
integer(kind=omp_alloctrait_val_kind)omp_atv_allocator_fb
parameter(omp_atv_allocator_fb=14)
integer(kind=omp_alloctrait_val_kind)omp_atv_environment
parameter(omp_atv_environment=15)
integer(kind=omp_alloctrait_val_kind)omp_atv_nearest
parameter(omp_atv_nearest=16)
integer(kind=omp_alloctrait_val_kind)omp_atv_blocked
parameter(omp_atv_blocked=17)
integer(kind=omp_alloctrait_val_kind)omp_atv_interleaved
parameter(omp_atv_interleaved=18)
type omp_alloctrait
integer (kind=omp_alloctrait_key_kind) key
integer (kind=omp_alloctrait_val_kind) value
end type omp_alloctrait
integer(kind=omp_allocator_handle_kind)omp_null_allocator
parameter(omp_null_allocator=0)
integer(kind=omp_allocator_kind)omp_default_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_default_mem_alloc
parameter(omp_default_mem_alloc=1)
integer(kind=omp_allocator_kind)omp_large_cap_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_large_cap_mem_alloc
parameter(omp_large_cap_mem_alloc=2)
integer(kind=omp_allocator_kind)omp_const_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_const_mem_alloc
parameter(omp_const_mem_alloc=3)
integer(kind=omp_allocator_kind)omp_high_bw_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_high_bw_mem_alloc
parameter(omp_high_bw_mem_alloc=4)
integer(kind=omp_allocator_kind)omp_low_lat_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_low_lat_mem_alloc
parameter(omp_low_lat_mem_alloc=5)
integer(kind=omp_allocator_kind)omp_cgroup_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_cgroup_mem_alloc
parameter(omp_cgroup_mem_alloc=6)
integer(kind=omp_allocator_kind)omp_pteam_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_pteam_mem_alloc
parameter(omp_pteam_mem_alloc=7)
integer(kind=omp_allocator_kind)omp_thread_mem_alloc
integer(kind=omp_allocator_handle_kind)omp_thread_mem_alloc
parameter(omp_thread_mem_alloc=8)
integer(kind=omp_memspace_handle_kind)omp_default_mem_space
parameter(omp_default_mem_space=0)
integer(kind=omp_memspace_handle_kind)omp_large_cap_mem_space
parameter(omp_large_cap_mem_space=1)
integer(kind=omp_memspace_handle_kind)omp_const_mem_space
parameter(omp_const_mem_space=2)
integer(kind=omp_memspace_handle_kind)omp_high_bw_mem_space
parameter(omp_high_bw_mem_space=3)
integer(kind=omp_memspace_handle_kind)omp_low_lat_mem_space
parameter(omp_low_lat_mem_space=4)
integer(kind=omp_pause_resource_kind)omp_pause_resume
parameter(omp_pause_resume=0)
integer(kind=omp_pause_resource_kind)omp_pause_soft
parameter(omp_pause_soft=1)
integer(kind=omp_pause_resource_kind)omp_pause_hard
parameter(omp_pause_hard=2)
interface
! ***
@@ -332,6 +426,29 @@
integer (kind=omp_integer_kind) omp_get_device_num
end function omp_get_device_num
function omp_pause_resource(kind, device_num) bind(c)
import
integer (kind=omp_pause_resource_kind), value :: kind
integer (kind=omp_integer_kind), value :: device_num
integer (kind=omp_integer_kind) omp_pause_resource
end function omp_pause_resource
function omp_pause_resource_all(kind) bind(c)
import
integer (kind=omp_pause_resource_kind), value :: kind
integer (kind=omp_integer_kind) omp_pause_resource_all
end function omp_pause_resource_all
function omp_get_supported_active_levels() bind(c)
import
integer (kind=omp_integer_kind) omp_get_supported_active_levels
end function omp_get_supported_active_levels
subroutine omp_fulfill_event(event) bind(c)
import
integer (kind=omp_event_handle_kind), value :: event
end subroutine omp_fulfill_event
subroutine omp_init_lock(svar) bind(c)
!DIR$ IF(__INTEL_COMPILER.GE.1400)
!DIR$ attributes known_intrinsic :: omp_init_lock
@@ -419,14 +536,27 @@
integer (kind=omp_integer_kind) omp_get_max_task_priority
end function omp_get_max_task_priority
subroutine omp_set_default_allocator(svar) bind(c)
function omp_init_allocator(memspace, ntraits, traits)
import
integer (kind=omp_allocator_kind), value :: svar
integer (omp_allocator_handle_kind) omp_init_allocator
integer (omp_memspace_handle_kind) :: memspace
integer (omp_integer_kind) :: ntraits
type(omp_alloctrait), intent(in) :: traits(*)
end function omp_init_allocator
subroutine omp_destroy_allocator(allocator) bind(c)
import
integer (omp_allocator_handle_kind), value :: allocator
end subroutine omp_destroy_allocator
subroutine omp_set_default_allocator(allocator) bind(c)
import
integer (omp_allocator_handle_kind), value :: allocator
end subroutine omp_set_default_allocator
function omp_get_default_allocator() bind(c)
import
integer (kind=omp_allocator_kind) omp_get_default_allocator
integer (omp_allocator_handle_kind) omp_get_default_allocator
end function omp_get_default_allocator
subroutine omp_set_affinity_format(format)
@@ -652,6 +782,10 @@
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_initial_device
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_devices
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_device_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_pause_resource
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_pause_resource_all
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_supported_active_levels
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_fulfill_event
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_teams
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_team_num
!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_lock
@@ -731,6 +865,10 @@
!$omp declare target(omp_get_initial_device )
!$omp declare target(omp_get_num_devices )
!$omp declare target(omp_get_device_num )
!$omp declare target(omp_pause_resource )
!$omp declare target(omp_pause_resource_all )
!$omp declare target(omp_get_supported_active_levels )
!$omp declare target(omp_fulfill_event)
!$omp declare target(omp_get_num_teams )
!$omp declare target(omp_get_team_num )
!$omp declare target(omp_init_lock )
+374 -471
View File
File diff suppressed because it is too large Load Diff
+20 -57
View File
@@ -4,10 +4,9 @@
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
@@ -458,7 +457,8 @@ static int __kmp_hwloc_get_nobjs_under_obj(hwloc_obj_t obj,
}
static int __kmp_hwloc_count_children_by_depth(hwloc_topology_t t,
hwloc_obj_t o, unsigned depth,
hwloc_obj_t o,
kmp_hwloc_depth_t depth,
hwloc_obj_t *f) {
if (o->depth == depth) {
if (*f == NULL)
@@ -531,7 +531,7 @@ static int __kmp_hwloc_process_obj_core_pu(AddrUnsPair *addrPair,
static int __kmp_hwloc_check_numa() {
hwloc_topology_t &tp = __kmp_hwloc_topology;
hwloc_obj_t hT, hC, hL, hN, hS; // hwloc objects (pointers to)
int depth;
int depth, l2cache_depth, package_depth;
// Get some PU
hT = hwloc_get_obj_by_type(tp, HWLOC_OBJ_PU, 0);
@@ -545,12 +545,14 @@ static int __kmp_hwloc_check_numa() {
if (hN != NULL && hN->depth > hS->depth) {
__kmp_numa_detected = TRUE; // socket includes node(s)
if (__kmp_affinity_gran == affinity_gran_node) {
__kmp_affinity_gran == affinity_gran_numa;
__kmp_affinity_gran = affinity_gran_numa;
}
}
package_depth = hwloc_get_type_depth(tp, HWLOC_OBJ_PACKAGE);
l2cache_depth = hwloc_get_cache_type_depth(tp, 2, HWLOC_OBJ_CACHE_UNIFIED);
// check tile, get object by depth because of multiple caches possible
depth = hwloc_get_cache_type_depth(tp, 2, HWLOC_OBJ_CACHE_UNIFIED);
depth = (l2cache_depth < package_depth) ? package_depth : l2cache_depth;
hL = hwloc_get_ancestor_obj_by_depth(tp, depth, hT);
hC = NULL; // not used, but reset it here just in case
if (hL != NULL &&
@@ -3017,8 +3019,6 @@ static void __kmp_affinity_process_proclist(kmp_affin_mask_t **out_masks,
KMP_CPU_FREE(sumMask);
}
#if OMP_40_ENABLED
/*-----------------------------------------------------------------------------
Re-parse the OMP_PLACES proc id list, forming the newMasks for the different
places. Again, Here is the grammar:
@@ -3039,7 +3039,6 @@ signed := num
signed := + signed
signed := - signed
-----------------------------------------------------------------------------*/
static void __kmp_process_subplace_list(const char **scan,
kmp_affin_mask_t *osId2Mask,
int maxOsId, kmp_affin_mask_t *tempMask,
@@ -3358,8 +3357,6 @@ void __kmp_affinity_process_placelist(kmp_affin_mask_t **out_masks,
KMP_CPU_INTERNAL_FREE_ARRAY(newMasks, numNewMasks);
}
#endif /* OMP_40_ENABLED */
#undef ADD_MASK
#undef ADD_MASK_OSID
@@ -4484,21 +4481,15 @@ static void __kmp_aux_affinity_initialize(void) {
case affinity_explicit:
KMP_DEBUG_ASSERT(__kmp_affinity_proclist != NULL);
#if OMP_40_ENABLED
if (__kmp_nested_proc_bind.bind_types[0] == proc_bind_intel)
#endif
{
if (__kmp_nested_proc_bind.bind_types[0] == proc_bind_intel) {
__kmp_affinity_process_proclist(
&__kmp_affinity_masks, &__kmp_affinity_num_masks,
__kmp_affinity_proclist, osId2Mask, maxIndex);
}
#if OMP_40_ENABLED
else {
} else {
__kmp_affinity_process_placelist(
&__kmp_affinity_masks, &__kmp_affinity_num_masks,
__kmp_affinity_proclist, osId2Mask, maxIndex);
}
#endif
if (__kmp_affinity_num_masks == 0) {
if (__kmp_affinity_verbose ||
(__kmp_affinity_warnings && (__kmp_affinity_type != affinity_none))) {
@@ -4614,13 +4605,11 @@ static void __kmp_aux_affinity_initialize(void) {
__kmp_affinity_num_masks = numUnique;
}
#if OMP_40_ENABLED
if ((__kmp_nested_proc_bind.bind_types[0] != proc_bind_intel) &&
(__kmp_affinity_num_places > 0) &&
((unsigned)__kmp_affinity_num_places < __kmp_affinity_num_masks)) {
__kmp_affinity_num_masks = __kmp_affinity_num_places;
}
#endif
KMP_CPU_ALLOC_ARRAY(__kmp_affinity_masks, __kmp_affinity_num_masks);
@@ -4690,9 +4679,7 @@ void __kmp_affinity_uninitialize(void) {
}
__kmp_affinity_num_masks = 0;
__kmp_affinity_type = affinity_default;
#if OMP_40_ENABLED
__kmp_affinity_num_places = 0;
#endif
if (__kmp_affinity_proclist != NULL) {
__kmp_free(__kmp_affinity_proclist);
__kmp_affinity_proclist = NULL;
@@ -4733,10 +4720,7 @@ void __kmp_affinity_set_init_mask(int gtid, int isa_root) {
kmp_affin_mask_t *mask;
int i;
#if OMP_40_ENABLED
if (KMP_AFFINITY_NON_PROC_BIND)
#endif
{
if (KMP_AFFINITY_NON_PROC_BIND) {
if ((__kmp_affinity_type == affinity_none) ||
(__kmp_affinity_type == affinity_balanced)) {
#if KMP_GROUP_AFFINITY
@@ -4752,9 +4736,7 @@ void __kmp_affinity_set_init_mask(int gtid, int isa_root) {
i = (gtid + __kmp_affinity_offset) % __kmp_affinity_num_masks;
mask = KMP_CPU_INDEX(__kmp_affinity_masks, i);
}
}
#if OMP_40_ENABLED
else {
} else {
if ((!isa_root) ||
(__kmp_nested_proc_bind.bind_types[0] == proc_bind_false)) {
#if KMP_GROUP_AFFINITY
@@ -4773,9 +4755,7 @@ void __kmp_affinity_set_init_mask(int gtid, int isa_root) {
mask = KMP_CPU_INDEX(__kmp_affinity_masks, i);
}
}
#endif
#if OMP_40_ENABLED
th->th.th_current_place = i;
if (isa_root) {
th->th.th_new_place = i;
@@ -4795,17 +4775,6 @@ void __kmp_affinity_set_init_mask(int gtid, int isa_root) {
KA_TRACE(100, ("__kmp_affinity_set_init_mask: binding T#%d to place %d\n",
gtid, i));
}
#else
if (i == -1) {
KA_TRACE(
100,
("__kmp_affinity_set_init_mask: binding T#%d to __kmp_affin_fullMask\n",
gtid));
} else {
KA_TRACE(100, ("__kmp_affinity_set_init_mask: binding T#%d to mask %d\n",
gtid, i));
}
#endif /* OMP_40_ENABLED */
KMP_CPU_COPY(th->th.th_affin_mask, mask);
@@ -4831,8 +4800,6 @@ void __kmp_affinity_set_init_mask(int gtid, int isa_root) {
__kmp_set_system_affinity(th->th.th_affin_mask, TRUE);
}
#if OMP_40_ENABLED
void __kmp_affinity_set_place(int gtid) {
if (!KMP_AFFINITY_CAPABLE()) {
return;
@@ -4873,8 +4840,6 @@ void __kmp_affinity_set_place(int gtid) {
__kmp_set_system_affinity(th->th.th_affin_mask, TRUE);
}
#endif /* OMP_40_ENABLED */
int __kmp_aux_set_affinity(void **mask) {
int gtid;
kmp_info_t *th;
@@ -4885,7 +4850,7 @@ int __kmp_aux_set_affinity(void **mask) {
}
gtid = __kmp_entry_gtid();
KA_TRACE(1000, ; {
KA_TRACE(1000, (""); {
char buf[KMP_AFFIN_MASK_PRINT_LEN];
__kmp_affinity_print_mask(buf, KMP_AFFIN_MASK_PRINT_LEN,
(kmp_affin_mask_t *)(*mask));
@@ -4929,7 +4894,6 @@ int __kmp_aux_set_affinity(void **mask) {
KMP_CPU_COPY(th->th.th_affin_mask, (kmp_affin_mask_t *)(*mask));
}
#if OMP_40_ENABLED
th->th.th_current_place = KMP_PLACE_UNDEFINED;
th->th.th_new_place = KMP_PLACE_UNDEFINED;
th->th.th_first_place = 0;
@@ -4937,7 +4901,6 @@ int __kmp_aux_set_affinity(void **mask) {
// Turn off 4.0 affinity for the current tread at this parallel level.
th->th.th_current_task->td_icvs.proc_bind = proc_bind_false;
#endif
return retval;
}
@@ -4955,7 +4918,7 @@ int __kmp_aux_get_affinity(void **mask) {
th = __kmp_threads[gtid];
KMP_DEBUG_ASSERT(th->th.th_affin_mask != NULL);
KA_TRACE(1000, ; {
KA_TRACE(1000, (""); {
char buf[KMP_AFFIN_MASK_PRINT_LEN];
__kmp_affinity_print_mask(buf, KMP_AFFIN_MASK_PRINT_LEN,
th->th.th_affin_mask);
@@ -4972,7 +4935,7 @@ int __kmp_aux_get_affinity(void **mask) {
#if !KMP_OS_WINDOWS
retval = __kmp_get_system_affinity((kmp_affin_mask_t *)(*mask), FALSE);
KA_TRACE(1000, ; {
KA_TRACE(1000, (""); {
char buf[KMP_AFFIN_MASK_PRINT_LEN];
__kmp_affinity_print_mask(buf, KMP_AFFIN_MASK_PRINT_LEN,
(kmp_affin_mask_t *)(*mask));
@@ -5006,7 +4969,7 @@ int __kmp_aux_set_affinity_mask_proc(int proc, void **mask) {
return -1;
}
KA_TRACE(1000, ; {
KA_TRACE(1000, (""); {
int gtid = __kmp_entry_gtid();
char buf[KMP_AFFIN_MASK_PRINT_LEN];
__kmp_affinity_print_mask(buf, KMP_AFFIN_MASK_PRINT_LEN,
@@ -5038,7 +5001,7 @@ int __kmp_aux_unset_affinity_mask_proc(int proc, void **mask) {
return -1;
}
KA_TRACE(1000, ; {
KA_TRACE(1000, (""); {
int gtid = __kmp_entry_gtid();
char buf[KMP_AFFIN_MASK_PRINT_LEN];
__kmp_affinity_print_mask(buf, KMP_AFFIN_MASK_PRINT_LEN,
@@ -5070,7 +5033,7 @@ int __kmp_aux_get_affinity_mask_proc(int proc, void **mask) {
return -1;
}
KA_TRACE(1000, ; {
KA_TRACE(1000, (""); {
int gtid = __kmp_entry_gtid();
char buf[KMP_AFFIN_MASK_PRINT_LEN];
__kmp_affinity_print_mask(buf, KMP_AFFIN_MASK_PRINT_LEN,
+3 -4
View File
@@ -4,10 +4,9 @@
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
+325 -70
View File
@@ -4,10 +4,9 @@
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
@@ -34,7 +33,7 @@ typedef kmp_int64 bufsize;
#endif
#else
typedef ssize_t bufsize;
#endif
#endif // KMP_OS_WINDOWS
/* The three modes of operation are, fifo search, lifo search, and best-fit */
@@ -1221,74 +1220,216 @@ void ___kmp_thread_free(kmp_info_t *th, void *ptr KMP_SRC_LOC_DECL) {
KE_TRACE(30, ("<- __kmp_thread_free()\n"));
}
#if OMP_50_ENABLED
/* OMP 5.0 Memory Management support */
static int (*p_hbw_check)(void);
static void *(*p_hbw_malloc)(size_t);
static void (*p_hbw_free)(void *);
static int (*p_hbw_set_policy)(int);
static const char *kmp_mk_lib_name;
static void *h_memkind;
/* memkind experimental API: */
// memkind_alloc
static void *(*kmp_mk_alloc)(void *k, size_t sz);
// memkind_free
static void (*kmp_mk_free)(void *kind, void *ptr);
// memkind_check_available
static int (*kmp_mk_check)(void *kind);
// kinds we are going to use
static void **mk_default;
static void **mk_interleave;
static void **mk_hbw;
static void **mk_hbw_interleave;
static void **mk_hbw_preferred;
static void **mk_hugetlb;
static void **mk_hbw_hugetlb;
static void **mk_hbw_preferred_hugetlb;
#if KMP_OS_UNIX && KMP_DYNAMIC_LIB
static inline void chk_kind(void ***pkind) {
KMP_DEBUG_ASSERT(pkind);
if (*pkind) // symbol found
if (kmp_mk_check(**pkind)) // kind not available or error
*pkind = NULL;
}
#endif
void __kmp_init_memkind() {
// as of 2018-07-31 memkind does not support Windows*, exclude it for now
#if KMP_OS_UNIX && KMP_DYNAMIC_LIB
// use of statically linked memkind is problematic, as it depends on libnuma
kmp_mk_lib_name = "libmemkind.so";
h_memkind = dlopen(kmp_mk_lib_name, RTLD_LAZY);
if (h_memkind) {
p_hbw_check = (int (*)())dlsym(h_memkind, "hbw_check_available");
p_hbw_malloc = (void *(*)(size_t))dlsym(h_memkind, "hbw_malloc");
p_hbw_free = (void (*)(void *))dlsym(h_memkind, "hbw_free");
p_hbw_set_policy = (int (*)(int))dlsym(h_memkind, "hbw_set_policy");
if (p_hbw_check && p_hbw_malloc && p_hbw_free && p_hbw_set_policy) {
kmp_mk_check = (int (*)(void *))dlsym(h_memkind, "memkind_check_available");
kmp_mk_alloc =
(void *(*)(void *, size_t))dlsym(h_memkind, "memkind_malloc");
kmp_mk_free = (void (*)(void *, void *))dlsym(h_memkind, "memkind_free");
mk_default = (void **)dlsym(h_memkind, "MEMKIND_DEFAULT");
if (kmp_mk_check && kmp_mk_alloc && kmp_mk_free && mk_default &&
!kmp_mk_check(*mk_default)) {
__kmp_memkind_available = 1;
if (p_hbw_check() == 0) {
p_hbw_set_policy(1); // return NULL is not enough memory
__kmp_hbw_mem_available = 1; // found HBW memory available
}
return; // success - all symbols resolved
mk_interleave = (void **)dlsym(h_memkind, "MEMKIND_INTERLEAVE");
chk_kind(&mk_interleave);
mk_hbw = (void **)dlsym(h_memkind, "MEMKIND_HBW");
chk_kind(&mk_hbw);
mk_hbw_interleave = (void **)dlsym(h_memkind, "MEMKIND_HBW_INTERLEAVE");
chk_kind(&mk_hbw_interleave);
mk_hbw_preferred = (void **)dlsym(h_memkind, "MEMKIND_HBW_PREFERRED");
chk_kind(&mk_hbw_preferred);
mk_hugetlb = (void **)dlsym(h_memkind, "MEMKIND_HUGETLB");
chk_kind(&mk_hugetlb);
mk_hbw_hugetlb = (void **)dlsym(h_memkind, "MEMKIND_HBW_HUGETLB");
chk_kind(&mk_hbw_hugetlb);
mk_hbw_preferred_hugetlb =
(void **)dlsym(h_memkind, "MEMKIND_HBW_PREFERRED_HUGETLB");
chk_kind(&mk_hbw_preferred_hugetlb);
KE_TRACE(25, ("__kmp_init_memkind: memkind library initialized\n"));
return; // success
}
dlclose(h_memkind); // failure
h_memkind = NULL;
}
p_hbw_check = NULL;
p_hbw_malloc = NULL;
p_hbw_free = NULL;
p_hbw_set_policy = NULL;
kmp_mk_check = NULL;
kmp_mk_alloc = NULL;
kmp_mk_free = NULL;
mk_default = NULL;
mk_interleave = NULL;
mk_hbw = NULL;
mk_hbw_interleave = NULL;
mk_hbw_preferred = NULL;
mk_hugetlb = NULL;
mk_hbw_hugetlb = NULL;
mk_hbw_preferred_hugetlb = NULL;
#else
kmp_mk_lib_name = "";
h_memkind = NULL;
p_hbw_check = NULL;
p_hbw_malloc = NULL;
p_hbw_free = NULL;
p_hbw_set_policy = NULL;
kmp_mk_check = NULL;
kmp_mk_alloc = NULL;
kmp_mk_free = NULL;
mk_default = NULL;
mk_interleave = NULL;
mk_hbw = NULL;
mk_hbw_interleave = NULL;
mk_hbw_preferred = NULL;
mk_hugetlb = NULL;
mk_hbw_hugetlb = NULL;
mk_hbw_preferred_hugetlb = NULL;
#endif
}
void __kmp_fini_memkind() {
#if KMP_OS_UNIX && KMP_DYNAMIC_LIB
if (__kmp_memkind_available)
KE_TRACE(25, ("__kmp_fini_memkind: finalize memkind library\n"));
if (h_memkind) {
dlclose(h_memkind);
h_memkind = NULL;
}
p_hbw_check = NULL;
p_hbw_malloc = NULL;
p_hbw_free = NULL;
p_hbw_set_policy = NULL;
kmp_mk_check = NULL;
kmp_mk_alloc = NULL;
kmp_mk_free = NULL;
mk_default = NULL;
mk_interleave = NULL;
mk_hbw = NULL;
mk_hbw_interleave = NULL;
mk_hbw_preferred = NULL;
mk_hugetlb = NULL;
mk_hbw_hugetlb = NULL;
mk_hbw_preferred_hugetlb = NULL;
#endif
}
void __kmpc_set_default_allocator(int gtid, const omp_allocator_t *allocator) {
if (allocator == OMP_NULL_ALLOCATOR)
omp_allocator_handle_t __kmpc_init_allocator(int gtid, omp_memspace_handle_t ms,
int ntraits,
omp_alloctrait_t traits[]) {
// OpenMP 5.0 only allows predefined memspaces
KMP_DEBUG_ASSERT(ms == omp_default_mem_space || ms == omp_low_lat_mem_space ||
ms == omp_large_cap_mem_space || ms == omp_const_mem_space ||
ms == omp_high_bw_mem_space);
kmp_allocator_t *al;
int i;
al = (kmp_allocator_t *)__kmp_allocate(sizeof(kmp_allocator_t)); // zeroed
al->memspace = ms; // not used currently
for (i = 0; i < ntraits; ++i) {
switch (traits[i].key) {
case OMP_ATK_THREADMODEL:
case OMP_ATK_ACCESS:
case OMP_ATK_PINNED:
break;
case OMP_ATK_ALIGNMENT:
al->alignment = traits[i].value;
KMP_ASSERT(IS_POWER_OF_TWO(al->alignment));
break;
case OMP_ATK_POOL_SIZE:
al->pool_size = traits[i].value;
break;
case OMP_ATK_FALLBACK:
al->fb = (omp_alloctrait_value_t)traits[i].value;
KMP_DEBUG_ASSERT(
al->fb == OMP_ATV_DEFAULT_MEM_FB || al->fb == OMP_ATV_NULL_FB ||
al->fb == OMP_ATV_ABORT_FB || al->fb == OMP_ATV_ALLOCATOR_FB);
break;
case OMP_ATK_FB_DATA:
al->fb_data = RCAST(kmp_allocator_t *, traits[i].value);
break;
case OMP_ATK_PARTITION:
al->memkind = RCAST(void **, traits[i].value);
break;
default:
KMP_ASSERT2(0, "Unexpected allocator trait");
}
}
if (al->fb == 0) {
// set default allocator
al->fb = OMP_ATV_DEFAULT_MEM_FB;
al->fb_data = (kmp_allocator_t *)omp_default_mem_alloc;
} else if (al->fb == OMP_ATV_ALLOCATOR_FB) {
KMP_ASSERT(al->fb_data != NULL);
} else if (al->fb == OMP_ATV_DEFAULT_MEM_FB) {
al->fb_data = (kmp_allocator_t *)omp_default_mem_alloc;
}
if (__kmp_memkind_available) {
// Let's use memkind library if available
if (ms == omp_high_bw_mem_space) {
if (al->memkind == (void *)OMP_ATV_INTERLEAVED && mk_hbw_interleave) {
al->memkind = mk_hbw_interleave;
} else if (mk_hbw_preferred) {
// AC: do not try to use MEMKIND_HBW for now, because memkind library
// cannot reliably detect exhaustion of HBW memory.
// It could be possible using hbw_verify_memory_region() but memkind
// manual says: "Using this function in production code may result in
// serious performance penalty".
al->memkind = mk_hbw_preferred;
} else {
// HBW is requested but not available --> return NULL allocator
__kmp_free(al);
return omp_null_allocator;
}
} else {
if (al->memkind == (void *)OMP_ATV_INTERLEAVED && mk_interleave) {
al->memkind = mk_interleave;
} else {
al->memkind = mk_default;
}
}
} else {
if (ms == omp_high_bw_mem_space) {
// cannot detect HBW memory presence without memkind library
__kmp_free(al);
return omp_null_allocator;
}
}
return (omp_allocator_handle_t)al;
}
void __kmpc_destroy_allocator(int gtid, omp_allocator_handle_t allocator) {
if (allocator > kmp_max_mem_alloc)
__kmp_free(allocator);
}
void __kmpc_set_default_allocator(int gtid, omp_allocator_handle_t allocator) {
if (allocator == omp_null_allocator)
allocator = omp_default_mem_alloc;
KMP_DEBUG_ASSERT(
allocator == omp_default_mem_alloc ||
allocator == omp_large_cap_mem_alloc ||
allocator == omp_const_mem_alloc || allocator == omp_high_bw_mem_alloc ||
allocator == omp_low_lat_mem_alloc || allocator == omp_cgroup_mem_alloc ||
allocator == omp_pteam_mem_alloc || allocator == omp_thread_mem_alloc);
__kmp_threads[gtid]->th.th_def_allocator = allocator;
}
const omp_allocator_t *__kmpc_get_default_allocator(int gtid) {
omp_allocator_handle_t __kmpc_get_default_allocator(int gtid) {
return __kmp_threads[gtid]->th.th_def_allocator;
}
@@ -1296,44 +1437,137 @@ typedef struct kmp_mem_desc { // Memory block descriptor
void *ptr_alloc; // Pointer returned by allocator
size_t size_a; // Size of allocated memory block (initial+descriptor+align)
void *ptr_align; // Pointer to aligned memory, returned
const omp_allocator_t *allocator; // allocator
kmp_allocator_t *allocator; // allocator
} kmp_mem_desc_t;
static int alignment = sizeof(void *); // let's align to pointer size
void *__kmpc_alloc(int gtid, size_t size, const omp_allocator_t *allocator) {
void *__kmpc_alloc(int gtid, size_t size, omp_allocator_handle_t allocator) {
void *ptr = NULL;
kmp_allocator_t *al;
KMP_DEBUG_ASSERT(__kmp_init_serial);
if (allocator == OMP_NULL_ALLOCATOR)
if (allocator == omp_null_allocator)
allocator = __kmp_threads[gtid]->th.th_def_allocator;
KE_TRACE(25, ("__kmpc_alloc: T#%d (%d, %p)\n", gtid, (int)size, allocator));
al = RCAST(kmp_allocator_t *, CCAST(omp_allocator_handle_t, allocator));
int sz_desc = sizeof(kmp_mem_desc_t);
void *ptr = NULL;
kmp_mem_desc_t desc;
kmp_uintptr_t addr; // address returned by allocator
kmp_uintptr_t addr_align; // address to return to caller
kmp_uintptr_t addr_descr; // address of memory block descriptor
KE_TRACE(25, ("__kmpc_alloc: T#%d (%d, %p)\n", gtid, (int)size, allocator));
desc.size_a = size + sz_desc + alignment;
if (allocator == omp_default_mem_alloc)
ptr = __kmp_allocate(desc.size_a);
if (allocator == omp_high_bw_mem_alloc && __kmp_hbw_mem_available) {
KMP_DEBUG_ASSERT(p_hbw_malloc != NULL);
ptr = p_hbw_malloc(desc.size_a);
int align = alignment; // default alignment
if (allocator > kmp_max_mem_alloc && al->alignment > 0) {
align = al->alignment; // alignment requested by user
}
desc.size_a = size + sz_desc + align;
KE_TRACE(10, ("__kmpc_alloc: T#%d %p=alloc(%d) hbw %d\n", gtid, ptr,
desc.size_a, __kmp_hbw_mem_available));
if (__kmp_memkind_available) {
if (allocator < kmp_max_mem_alloc) {
// pre-defined allocator
if (allocator == omp_high_bw_mem_alloc && mk_hbw_preferred) {
ptr = kmp_mk_alloc(*mk_hbw_preferred, desc.size_a);
} else {
ptr = kmp_mk_alloc(*mk_default, desc.size_a);
}
} else if (al->pool_size > 0) {
// custom allocator with pool size requested
kmp_uint64 used =
KMP_TEST_THEN_ADD64((kmp_int64 *)&al->pool_used, desc.size_a);
if (used + desc.size_a > al->pool_size) {
// not enough space, need to go fallback path
KMP_TEST_THEN_ADD64((kmp_int64 *)&al->pool_used, -desc.size_a);
if (al->fb == OMP_ATV_DEFAULT_MEM_FB) {
al = (kmp_allocator_t *)omp_default_mem_alloc;
ptr = kmp_mk_alloc(*mk_default, desc.size_a);
} else if (al->fb == OMP_ATV_ABORT_FB) {
KMP_ASSERT(0); // abort fallback requested
} else if (al->fb == OMP_ATV_ALLOCATOR_FB) {
KMP_ASSERT(al != al->fb_data);
al = al->fb_data;
return __kmpc_alloc(gtid, size, (omp_allocator_handle_t)al);
} // else ptr == NULL;
} else {
// pool has enough space
ptr = kmp_mk_alloc(*al->memkind, desc.size_a);
if (ptr == NULL) {
if (al->fb == OMP_ATV_DEFAULT_MEM_FB) {
al = (kmp_allocator_t *)omp_default_mem_alloc;
ptr = kmp_mk_alloc(*mk_default, desc.size_a);
} else if (al->fb == OMP_ATV_ABORT_FB) {
KMP_ASSERT(0); // abort fallback requested
} else if (al->fb == OMP_ATV_ALLOCATOR_FB) {
KMP_ASSERT(al != al->fb_data);
al = al->fb_data;
return __kmpc_alloc(gtid, size, (omp_allocator_handle_t)al);
}
}
}
} else {
// custom allocator, pool size not requested
ptr = kmp_mk_alloc(*al->memkind, desc.size_a);
if (ptr == NULL) {
if (al->fb == OMP_ATV_DEFAULT_MEM_FB) {
al = (kmp_allocator_t *)omp_default_mem_alloc;
ptr = kmp_mk_alloc(*mk_default, desc.size_a);
} else if (al->fb == OMP_ATV_ABORT_FB) {
KMP_ASSERT(0); // abort fallback requested
} else if (al->fb == OMP_ATV_ALLOCATOR_FB) {
KMP_ASSERT(al != al->fb_data);
al = al->fb_data;
return __kmpc_alloc(gtid, size, (omp_allocator_handle_t)al);
}
}
}
} else if (allocator < kmp_max_mem_alloc) {
// pre-defined allocator
if (allocator == omp_high_bw_mem_alloc) {
// ptr = NULL;
} else {
ptr = __kmp_thread_malloc(__kmp_thread_from_gtid(gtid), desc.size_a);
}
} else if (al->pool_size > 0) {
// custom allocator with pool size requested
kmp_uint64 used =
KMP_TEST_THEN_ADD64((kmp_int64 *)&al->pool_used, desc.size_a);
if (used + desc.size_a > al->pool_size) {
// not enough space, need to go fallback path
KMP_TEST_THEN_ADD64((kmp_int64 *)&al->pool_used, -desc.size_a);
if (al->fb == OMP_ATV_DEFAULT_MEM_FB) {
al = (kmp_allocator_t *)omp_default_mem_alloc;
ptr = __kmp_thread_malloc(__kmp_thread_from_gtid(gtid), desc.size_a);
} else if (al->fb == OMP_ATV_ABORT_FB) {
KMP_ASSERT(0); // abort fallback requested
} else if (al->fb == OMP_ATV_ALLOCATOR_FB) {
KMP_ASSERT(al != al->fb_data);
al = al->fb_data;
return __kmpc_alloc(gtid, size, (omp_allocator_handle_t)al);
} // else ptr == NULL;
} else {
// pool has enough space
ptr = __kmp_thread_malloc(__kmp_thread_from_gtid(gtid), desc.size_a);
if (ptr == NULL && al->fb == OMP_ATV_ABORT_FB) {
KMP_ASSERT(0); // abort fallback requested
} // no sense to look for another fallback because of same internal alloc
}
} else {
// custom allocator, pool size not requested
ptr = __kmp_thread_malloc(__kmp_thread_from_gtid(gtid), desc.size_a);
if (ptr == NULL && al->fb == OMP_ATV_ABORT_FB) {
KMP_ASSERT(0); // abort fallback requested
} // no sense to look for another fallback because of same internal alloc
}
KE_TRACE(10, ("__kmpc_alloc: T#%d %p=alloc(%d)\n", gtid, ptr, desc.size_a));
if (ptr == NULL)
return NULL;
addr = (kmp_uintptr_t)ptr;
addr_align = (addr + sz_desc + alignment - 1) & ~(alignment - 1);
addr_align = (addr + sz_desc + align - 1) & ~(align - 1);
addr_descr = addr_align - sz_desc;
desc.ptr_alloc = ptr;
desc.ptr_align = (void *)addr_align;
desc.allocator = allocator;
desc.allocator = al;
*((kmp_mem_desc_t *)addr_descr) = desc; // save descriptor contents
KMP_MB();
@@ -1341,11 +1575,14 @@ void *__kmpc_alloc(int gtid, size_t size, const omp_allocator_t *allocator) {
return desc.ptr_align;
}
void __kmpc_free(int gtid, void *ptr, const omp_allocator_t *allocator) {
void __kmpc_free(int gtid, void *ptr, const omp_allocator_handle_t allocator) {
KE_TRACE(25, ("__kmpc_free: T#%d free(%p,%p)\n", gtid, ptr, allocator));
if (ptr == NULL)
return;
kmp_allocator_t *al;
omp_allocator_handle_t oal;
al = RCAST(kmp_allocator_t *, CCAST(omp_allocator_handle_t, allocator));
kmp_mem_desc_t desc;
kmp_uintptr_t addr_align; // address to return to caller
kmp_uintptr_t addr_descr; // address of memory block descriptor
@@ -1356,24 +1593,42 @@ void __kmpc_free(int gtid, void *ptr, const omp_allocator_t *allocator) {
KMP_DEBUG_ASSERT(desc.ptr_align == ptr);
if (allocator) {
KMP_DEBUG_ASSERT(desc.allocator == allocator);
} else {
allocator = desc.allocator;
KMP_DEBUG_ASSERT(desc.allocator == al || desc.allocator == al->fb_data);
}
KMP_DEBUG_ASSERT(allocator);
al = desc.allocator;
oal = (omp_allocator_handle_t)al; // cast to void* for comparisons
KMP_DEBUG_ASSERT(al);
if (allocator == omp_default_mem_alloc)
__kmp_free(desc.ptr_alloc);
if (allocator == omp_high_bw_mem_alloc && __kmp_hbw_mem_available) {
KMP_DEBUG_ASSERT(p_hbw_free != NULL);
p_hbw_free(desc.ptr_alloc);
if (__kmp_memkind_available) {
if (oal < kmp_max_mem_alloc) {
// pre-defined allocator
if (oal == omp_high_bw_mem_alloc && mk_hbw_preferred) {
kmp_mk_free(*mk_hbw_preferred, desc.ptr_alloc);
} else {
kmp_mk_free(*mk_default, desc.ptr_alloc);
}
} else {
if (al->pool_size > 0) { // custom allocator with pool size requested
kmp_uint64 used =
KMP_TEST_THEN_ADD64((kmp_int64 *)&al->pool_used, -desc.size_a);
(void)used; // to suppress compiler warning
KMP_DEBUG_ASSERT(used >= desc.size_a);
}
kmp_mk_free(*al->memkind, desc.ptr_alloc);
}
} else {
if (oal > kmp_max_mem_alloc && al->pool_size > 0) {
kmp_uint64 used =
KMP_TEST_THEN_ADD64((kmp_int64 *)&al->pool_used, -desc.size_a);
(void)used; // to suppress compiler warning
KMP_DEBUG_ASSERT(used >= desc.size_a);
}
__kmp_thread_free(__kmp_thread_from_gtid(gtid), desc.ptr_alloc);
}
KE_TRACE(10, ("__kmpc_free: T#%d freed %p (%p)\n", gtid, desc.ptr_alloc,
allocator));
}
#endif
/* If LEAK_MEMORY is defined, __kmp_free() will *not* free memory. It causes
memory leaks, but it may be useful for debugging memory corruptions, used
freed pointers, etc. */
+44 -51
View File
@@ -4,10 +4,9 @@
//===----------------------------------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is dual licensed under the MIT and the University of Illinois Open
// Source Licenses. See LICENSE.txt for details.
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
@@ -675,7 +674,7 @@ static inline void operator/=(kmp_cmplx128_a16_t &lhs,
lhs.q /= rhs.q;
}
#endif
#endif // (KMP_ARCH_X86) && KMP_HAVE_QUAD
// ATOMIC implementation routines -----------------------------------------
// One routine for each operation and operand type.
@@ -844,7 +843,7 @@ static inline void operator/=(kmp_cmplx128_a16_t &lhs,
OP_CMPXCHG_WORKAROUND(TYPE, BITS, OP) \
}
// end of the second part of the workaround for C78287
#endif
#endif // USE_CMPXCHG_FIX
#else
// -------------------------------------------------------------------------
@@ -1194,8 +1193,8 @@ MIN_MAX_CRITICAL(float16, max_a16, Quad_a16_t, <, 16r,
1) // __kmpc_atomic_float16_max_a16
MIN_MAX_CRITICAL(float16, min_a16, Quad_a16_t, >, 16r,
1) // __kmpc_atomic_float16_min_a16
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// ------------------------------------------------------------------------
// Need separate macros for .EQV. because of the need of complement (~)
// OP ignored for critical sections, ^=~ used instead
@@ -1290,8 +1289,8 @@ ATOMIC_CRITICAL(float16, mul_a16, Quad_a16_t, *, 16r,
1) // __kmpc_atomic_float16_mul_a16
ATOMIC_CRITICAL(float16, div_a16, Quad_a16_t, /, 16r,
1) // __kmpc_atomic_float16_div_a16
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// routines for complex types
#if USE_CMPXCHG_FIX
@@ -1342,10 +1341,8 @@ ATOMIC_CRITICAL(cmplx16, mul_a16, kmp_cmplx128_a16_t, *, 32c,
1) // __kmpc_atomic_cmplx16_mul_a16
ATOMIC_CRITICAL(cmplx16, div_a16, kmp_cmplx128_a16_t, /, 32c,
1) // __kmpc_atomic_cmplx16_div_a16
#endif
#endif
#if OMP_40_ENABLED
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// OpenMP 4.0: x = expr binop x for non-commutative operations.
// Supported only on IA-32 architecture and Intel(R) 64
@@ -1524,8 +1521,8 @@ ATOMIC_CRITICAL_REV(float16, sub_a16, Quad_a16_t, -, 16r,
1) // __kmpc_atomic_float16_sub_a16_rev
ATOMIC_CRITICAL_REV(float16, div_a16, Quad_a16_t, /, 16r,
1) // __kmpc_atomic_float16_div_a16_rev
#endif
#endif
#endif // KMP_ARCH_X86
#endif // KMP_HAVE_QUAD
// routines for complex types
ATOMIC_CRITICAL_REV(cmplx4, sub, kmp_cmplx32, -, 8c,
@@ -1550,14 +1547,12 @@ ATOMIC_CRITICAL_REV(cmplx16, sub_a16, kmp_cmplx128_a16_t, -, 32c,
1) // __kmpc_atomic_cmplx16_sub_a16_rev
ATOMIC_CRITICAL_REV(cmplx16, div_a16, kmp_cmplx128_a16_t, /, 32c,
1) // __kmpc_atomic_cmplx16_div_a16_rev
#endif
#endif
#endif // KMP_ARCH_X86
#endif // KMP_HAVE_QUAD
#endif // KMP_ARCH_X86 || KMP_ARCH_X86_64
// End of OpenMP 4.0: x = expr binop x for non-commutative operations.
#endif // OMP_40_ENABLED
/* ------------------------------------------------------------------------ */
/* Routines for mixed types of LHS and RHS, when RHS is "larger" */
/* Note: in order to reduce the total number of types combinations */
@@ -1807,7 +1802,7 @@ ATOMIC_CRITICAL_REV_FP(float10, long double, div_rev, /, fp, _Quad, 10r,
1) // __kmpc_atomic_float10_div_rev_fp
#endif /* KMP_ARCH_X86 || KMP_ARCH_X86_64 */
#endif
#endif // KMP_HAVE_QUAD
#if KMP_ARCH_X86 || KMP_ARCH_X86_64
// ------------------------------------------------------------------------
@@ -2021,7 +2016,7 @@ ATOMIC_CRITICAL_READ_WRK(cmplx4, rd, kmp_cmplx32, +, 8c,
#else
ATOMIC_CRITICAL_READ(cmplx4, rd, kmp_cmplx32, +, 8c,
1) // __kmpc_atomic_cmplx4_rd
#endif
#endif // (KMP_OS_WINDOWS)
ATOMIC_CRITICAL_READ(cmplx8, rd, kmp_cmplx64, +, 16c,
1) // __kmpc_atomic_cmplx8_rd
ATOMIC_CRITICAL_READ(cmplx10, rd, kmp_cmplx80, +, 20c,
@@ -2034,8 +2029,8 @@ ATOMIC_CRITICAL_READ(float16, a16_rd, Quad_a16_t, +, 16r,
1) // __kmpc_atomic_float16_a16_rd
ATOMIC_CRITICAL_READ(cmplx16, a16_rd, kmp_cmplx128_a16_t, +, 32c,
1) // __kmpc_atomic_cmplx16_a16_rd
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// ------------------------------------------------------------------------
// Atomic WRITE routines
@@ -2109,7 +2104,7 @@ ATOMIC_CMPXCHG_WR(fixed8, wr, kmp_int64, 64, =,
#else
ATOMIC_XCHG_WR(fixed8, wr, kmp_int64, 64, =,
KMP_ARCH_X86) // __kmpc_atomic_fixed8_wr
#endif
#endif // (KMP_ARCH_X86)
ATOMIC_XCHG_FLOAT_WR(float4, wr, kmp_real32, 32, =,
KMP_ARCH_X86) // __kmpc_atomic_float4_wr
@@ -2119,14 +2114,14 @@ ATOMIC_CMPXCHG_WR(float8, wr, kmp_real64, 64, =,
#else
ATOMIC_XCHG_FLOAT_WR(float8, wr, kmp_real64, 64, =,
KMP_ARCH_X86) // __kmpc_atomic_float8_wr
#endif
#endif // (KMP_ARCH_X86)
ATOMIC_CRITICAL_WR(float10, wr, long double, =, 10r,
1) // __kmpc_atomic_float10_wr
#if KMP_HAVE_QUAD
ATOMIC_CRITICAL_WR(float16, wr, QUAD_LEGACY, =, 16r,
1) // __kmpc_atomic_float16_wr
#endif
#endif // KMP_HAVE_QUAD
ATOMIC_CRITICAL_WR(cmplx4, wr, kmp_cmplx32, =, 8c, 1) // __kmpc_atomic_cmplx4_wr
ATOMIC_CRITICAL_WR(cmplx8, wr, kmp_cmplx64, =, 16c,
1) // __kmpc_atomic_cmplx8_wr
@@ -2140,8 +2135,8 @@ ATOMIC_CRITICAL_WR(float16, a16_wr, Quad_a16_t, =, 16r,
1) // __kmpc_atomic_float16_a16_wr
ATOMIC_CRITICAL_WR(cmplx16, a16_wr, kmp_cmplx128_a16_t, =, 32c,
1) // __kmpc_atomic_cmplx16_a16_wr
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// ------------------------------------------------------------------------
// Atomic CAPTURE routines
@@ -2566,6 +2561,8 @@ ATOMIC_CMPX_L_CPT(fixed8, orl_cpt, kmp_int64, 64, ||,
new_value = rhs; \
else \
new_value = old_value; \
} else { \
new_value = *lhs; \
} \
__kmp_release_atomic_lock(&ATOMIC_LOCK##LCK_ID, gtid); \
return new_value;
@@ -2659,8 +2656,8 @@ MIN_MAX_CRITICAL_CPT(float16, max_a16_cpt, Quad_a16_t, <, 16r,
1) // __kmpc_atomic_float16_max_a16_cpt
MIN_MAX_CRITICAL_CPT(float16, min_a16_cpt, Quad_a16_t, >, 16r,
1) // __kmpc_atomic_float16_mix_a16_cpt
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// ------------------------------------------------------------------------
#ifdef KMP_GOMP_COMPAT
@@ -2784,8 +2781,8 @@ ATOMIC_CRITICAL_CPT(float16, mul_a16_cpt, Quad_a16_t, *, 16r,
1) // __kmpc_atomic_float16_mul_a16_cpt
ATOMIC_CRITICAL_CPT(float16, div_a16_cpt, Quad_a16_t, /, 16r,
1) // __kmpc_atomic_float16_div_a16_cpt
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// routines for complex types
@@ -2833,10 +2830,8 @@ ATOMIC_CRITICAL_CPT(cmplx16, mul_a16_cpt, kmp_cmplx128_a16_t, *, 32c,
1) // __kmpc_atomic_cmplx16_mul_a16_cpt
ATOMIC_CRITICAL_CPT(cmplx16, div_a16_cpt, kmp_cmplx128_a16_t, /, 32c,
1) // __kmpc_atomic_cmplx16_div_a16_cpt
#endif
#endif
#if OMP_40_ENABLED
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// OpenMP 4.0: v = x = expr binop x; { v = x; x = expr binop x; } { x = expr
// binop x; v = x; } for non-commutative operations.
@@ -2999,8 +2994,8 @@ ATOMIC_CRITICAL_CPT_REV(float16, sub_a16_cpt_rev, Quad_a16_t, -, 16r,
1) // __kmpc_atomic_float16_sub_a16_cpt_rev
ATOMIC_CRITICAL_CPT_REV(float16, div_a16_cpt_rev, Quad_a16_t, /, 16r,
1) // __kmpc_atomic_float16_div_a16_cpt_rev
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// routines for complex types
@@ -3066,8 +3061,8 @@ ATOMIC_CRITICAL_CPT_REV(cmplx16, sub_a16_cpt_rev, kmp_cmplx128_a16_t, -, 32c,
1) // __kmpc_atomic_cmplx16_sub_a16_cpt_rev
ATOMIC_CRITICAL_CPT_REV(cmplx16, div_a16_cpt_rev, kmp_cmplx128_a16_t, /, 32c,
1) // __kmpc_atomic_cmplx16_div_a16_cpt_rev
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// Capture reverse for mixed type: RHS=float16
#if KMP_HAVE_QUAD
@@ -3246,7 +3241,7 @@ ATOMIC_CMPXCHG_SWP(float8, kmp_real64, 64,
ATOMIC_XCHG_SWP(fixed8, kmp_int64, 64, KMP_ARCH_X86) // __kmpc_atomic_fixed8_swp
ATOMIC_XCHG_FLOAT_SWP(float8, kmp_real64, 64,
KMP_ARCH_X86) // __kmpc_atomic_float8_swp
#endif
#endif // (KMP_ARCH_X86)
// ------------------------------------------------------------------------
// Routines for Extended types: long double, _Quad, complex flavours (use
@@ -3301,7 +3296,7 @@ ATOMIC_XCHG_FLOAT_SWP(float8, kmp_real64, 64,
ATOMIC_CRITICAL_SWP(float10, long double, 10r, 1) // __kmpc_atomic_float10_swp
#if KMP_HAVE_QUAD
ATOMIC_CRITICAL_SWP(float16, QUAD_LEGACY, 16r, 1) // __kmpc_atomic_float16_swp
#endif
#endif // KMP_HAVE_QUAD
// cmplx4 routine to return void
ATOMIC_CRITICAL_SWP_WRK(cmplx4, kmp_cmplx32, 8c, 1) // __kmpc_atomic_cmplx4_swp
@@ -3317,13 +3312,11 @@ ATOMIC_CRITICAL_SWP(float16_a16, Quad_a16_t, 16r,
1) // __kmpc_atomic_float16_a16_swp
ATOMIC_CRITICAL_SWP(cmplx16_a16, kmp_cmplx128_a16_t, 32c,
1) // __kmpc_atomic_cmplx16_a16_swp
#endif
#endif
#endif // (KMP_ARCH_X86)
#endif // KMP_HAVE_QUAD
// End of OpenMP 4.0 Capture
#endif // OMP_40_ENABLED
#endif // KMP_ARCH_X86 || KMP_ARCH_X86_64
#undef OP_CRITICAL
@@ -3340,7 +3333,7 @@ void __kmpc_atomic_1(ident_t *id_ref, int gtid, void *lhs, void *rhs,
FALSE /* must use lock */
#else
TRUE
#endif
#endif // KMP_ARCH_X86 && defined(KMP_GOMP_COMPAT)
) {
kmp_int8 old_value, new_value;
@@ -3387,7 +3380,7 @@ void __kmpc_atomic_2(ident_t *id_ref, int gtid, void *lhs, void *rhs,
TRUE /* no alignment problems */
#else
!((kmp_uintptr_t)lhs & 0x1) /* make sure address is 2-byte aligned */
#endif
#endif // KMP_ARCH_X86 && defined(KMP_GOMP_COMPAT)
) {
kmp_int16 old_value, new_value;
@@ -3436,7 +3429,7 @@ void __kmpc_atomic_4(ident_t *id_ref, int gtid, void *lhs, void *rhs,
TRUE /* no alignment problems */
#else
!((kmp_uintptr_t)lhs & 0x3) /* make sure address is 4-byte aligned */
#endif
#endif // KMP_ARCH_X86 || KMP_ARCH_X86_64
) {
kmp_int32 old_value, new_value;
@@ -3486,7 +3479,7 @@ void __kmpc_atomic_8(ident_t *id_ref, int gtid, void *lhs, void *rhs,
TRUE /* no alignment problems */
#else
!((kmp_uintptr_t)lhs & 0x7) /* make sure address is 8-byte aligned */
#endif
#endif // KMP_ARCH_X86 && defined(KMP_GOMP_COMPAT)
) {
kmp_int64 old_value, new_value;

Some files were not shown because too many files have changed in this diff Show More