If OpenMP is initialized before fork()-ing occurs and affinity is set to
something like compact, then the master thread will be pinned to a single HW
thread/core after initialization. If the master (or any other thread) then
forks N processes, all N processes will then be pinned to that same single HW
thread/core. To reset the affinity for the new child process, the atfork
handler for the child process can call kmp_set_thread_affinity_mask_initial()
to reset its affinity to the initial affinity of the application before it
re-initializes libomp. The parent process will not be affected and still
keeps its affinity setting.
Differential Revision: https://reviews.llvm.org/D34118
llvm-svn: 305306
Fix static initializers to use the proper unlocked value for the poll
field of the tas and futex locks.
Patch by Terry Wilmarth
Differential Revision: https://reviews.llvm.org/D33794
llvm-svn: 304828
Some code was restructured to move it under KMP_DEBUG. The rest is
formatting changes to fix some things broken by clang-format
Patch by Terry Wilmarth
Differential Revision: https://reviews.llvm.org/D33744
llvm-svn: 304438
With these settings, the create_hwloc_map() method was being called causing an
assert(). After some consideration, it was determined that disabling affinity
explicitly should just disable hwloc as well. i.e., KMP_AFFINITY overrides
KMP_TOPOLOGY_METHOD. This lets the user know that the Hwloc mechanism is being
ignored when KMP_AFFINITY=disabled.
Differential Revision: https://reviews.llvm.org/D33208
llvm-svn: 304344
This change checks if the initial affinity mask is equal to exactly one
Windows processor group's affinity mask. If it is, then the code does not
respect the initial affinity mask and uses the entire machine instead.
The reasoning behind this is that, by default, Windows assigns exactly one
processor group as the initial affinity mask even when there are multiple
Windows processor groups available. User's typically want to use the whole
machine, so we ignore this special case and use the entire machine.
If the initial affinity mask is a proper subset of one group, or spans multiple
groups, then the initial affinity mask is respected since we can assume that the
operating system did not assign this initial affinity mask. This change only
affects machines with multiple processor groups
Differential Revision: https://reviews.llvm.org/D33210
llvm-svn: 304343
An assert() was being tripped when KMP_AFFINITY=respect + Multiple Processor
Groups. Let __kmp_affinity_create_proc_group_map() function be able to create
address2os object which contains a single group by deleting restriction that
process affinity mask must span multiple groups.
llvm-svn: 303101
This patch contains the clang-format and cleanup of the entire code base. Some
of clang-formats changes made the code look worse in places. A best effort was
made to resolve the bulk of these problems, but many remain. Most of the
problems were mangling line-breaks and tabbing of comments.
Patch by Terry Wilmarth
Differential Revision: https://reviews.llvm.org/D32659
llvm-svn: 302929
This patch chagnes the plugin interface so that:
1) future plugins can take advantage of systems with shared CPU/device storage
2) instead of using base addresses, target regions are launched by providing target addresseds and base offsets explicitly.
Differential revision: https://reviews.llvm.org/D33028
llvm-svn: 302663
Older Hwloc libraries (< 1.10.0) don't offer the HWLOC_OBJ_NUMANODE nor
HWLOC_OBJ_PACKAGE types. Instead they are named HWLOC_OBJ_NODE and
HWLOC_OBJ_SOCKET instead. This patch just defines the newer names based on
the older names when using an older Hwloc.
Differential Revision: https://reviews.llvm.org/D32496
llvm-svn: 301349
Without this fix cancellation status for parallel, sections and for persists
across construct boundaries.
Differential Revision: https://reviews.llvm.org/D31419
llvm-svn: 299434
This change slightly improves performance of KMP_YIELD_NOW() macro, by using
_rdtsc() intrinsic function if possible.
Patch by Hansang Bae
Differential Revision: https://reviews.llvm.org/D31008
llvm-svn: 298314
Affinity initialization code expects __kmp_affinity_type has the value
affinity_default by default, but the cleanup code does not properly set the
value back to affinity_default. This may introduce some issues when multiple
roots are trying to initialize/uninitialize the runtime successively.
Patch by Hansang Bae
Differential Revision: https://reviews.llvm.org/D31012
llvm-svn: 298313
This change fixes an assertion failure the in case KMP_AFFINITY is set with
'proclist' specified but without 'explicit'
e.g., KMP_AFFINITY=verbose,proclist=[0-31]
Patch by Olga Malysheva
Differential Revision: https://reviews.llvm.org/D30404
llvm-svn: 297480
Summary:
Bionic didn't get a GNU style strerror_r until Android M. Until then
we unconditionally exposed the POSIX one. Expand the check to account
for this.
Reviewers: pirama, AndreyChurbanov, jlpeyton
Reviewed By: jlpeyton
Subscribers: openmp-commits, srhines
Differential Revision: https://reviews.llvm.org/D30056
llvm-svn: 297235
Add build option LIBOMP_OMP_VERSION=50, 5.0 headers, and add the year/month
associated with OpenMP 5.0 in relevant source locations. Also, remove the
deprecated LIBOMP_OMP_VERSION=41 option.
Patch by Olga Malysheva
Differential Revision: https://reviews.llvm.org/D30450
llvm-svn: 297083
This adds AArch64 support to recently added part of the runtime responsible for offloading to target. This piece of code allows offloading-to-self on AArch64 machines.
Differential Revision: https://reviews.llvm.org/D30644
llvm-svn: 297070
This section of code (__kmp_test_then_* functions) is guarded by
(KMP_ARCH_X86 || KMP_ARCH_X86_64) so it does not make sense to have other
architecture guards inside this section. Non-x86 architectures always
use intrinsics (__sync_*)
llvm-svn: 296525
When using -rtlib=libgcc, the fallback implementation of __atomic_*
builtins is provided via libatomic (included in GCC). However, neither
GCC itself nor clang link libatomic implicitly, and it seems that GCC
upstream expects projects to link it explicitly as necessary.
Since compiler-rt provides __atomic_* builtins directly in the main
library, check if they are provided by the default libraries first.
If they are not, check if -latomic is available to provide them
and add explicit -latomic for tests in this case.
This fixes unresolved __atomic_load() references when running openmp
tests on i386 with libgcc backend.
Differential Revision: https://reviews.llvm.org/D30083
llvm-svn: 296183
Add counter to count number of static_steal for loops
Add counter for number of chunks executed per static_steal for loop
Add counter for number of chunks stolen per static_steal for loop
llvm-svn: 295461
Added test kmp_task_reduction_nest.cpp which has an example of
possible compiler codegen.
Differential Revision: https://reviews.llvm.org/D29600
llvm-svn: 295343
Fixed bug due to which a parent struct was deallocated when one of the struct's pointers was being unmapped.
Differential Revision: https://reviews.llvm.org/D29914
llvm-svn: 295231
This change allows the runtime to turn __kmp_yield() on/off repeatedly on Linux.
This feature was removed when disabling monitor thread, but there are
applications that perform better with this feature on.
Patch by Hansang Bae
Differential Revision: https://reviews.llvm.org/D29227
llvm-svn: 295203
Added new ThreadSanitizer annotations to remove false positives with OpenMP reduction.
Cleaned up Tsan annotations header file from unused annotations.
Patch by Simone Atzeni!
Differential Revision: https://reviews.llvm.org/D29202
llvm-svn: 295158
This change allows setting LIBOMPTARGET_LLVM_LIT_EXECUTABLE and
LIBOMPTARGET_FILECHECK_EXECUTABLE as full path. It also honors
OPENMP_LLVM_TOOLS_DIR which is meant as a common configuration
for both libomp and libomptarget.
Maybe this should be done in a common CMake module, but I'm no expert here.
Differential Revision: https://reviews.llvm.org/D29172
llvm-svn: 294284
This is the patch upstreaming the plugins part of libomptarget (CUDA, generic-elf-64).
Differential Revision: https://reviews.llvm.org/D14253
llvm-svn: 293724
glibc < 2.18 is C99 compliant and only provides the format macros in C++ if
__STDC_FORMAT_MACROS is defined. This change fixes the debug build for
GCC 4.8, GCC 6.2 and Clang 3.9.1 that were previously broken on my machine.
It shows no regression for libc++ >= 4.0.0 which has a fix since September:
http://lists.llvm.org/pipermail/cfe-commits/Week-of-Mon-20160926/171659.html
llvm-svn: 293468
Put the duplicated i_maxmin into traits_t by adding new members max_value and
min_value. Put ___kmp_size_type into traits_t by adding member type_size.
Differential Revision: https://reviews.llvm.org/D28847
llvm-svn: 293316
When the monitor thread is used, most threads in the team directly go to
sleep if the copy of bt_intervals/bt_set is not available in the cache,
and this happens at least once per thread in the wait function, making the
overall performance slightly better.
This change tries to mimic this behavior by using the bt_intervals cache,
which simply keeps the blocktime interval in terms of the platform-dependent
ticks or nanoseconds.
Patch by Hansang Bae
Differential Revision: https://reviews.llvm.org/D28906
llvm-svn: 293312
The lock tables were being reallocated if kmp_set_defaults() was called.
In the env_init code it says that the user should be able to switch between
different KMP_CONSISTENCY_CHECK values which is what this change enables.
llvm-svn: 292349
There is no corresponding free() for this expandable array. The logic is
added in __kmp_cleanup() next to the freeing of __kmp_nested_nth.
llvm-svn: 292348
Clang 4.0 trunk warns:
warning: logical not is only applied to the left hand side of this bitwise operator [-Wlogical-not-parentheses]
This points to a potential bug if the code really wants to check if the single
bit is not set: If for example (buf.edx >> 9) = 2 (has any bit set except the
least significant one), 'logical not' will return 0 which stays 0 after the
'bitwise and'.
To do this correctly we first need to evaluate the 'bitwise and'. In that case
it returns 2 & 1 = 0 which after the 'logical not' evaluates to 1.
Differential Revision: https://reviews.llvm.org/D28599
llvm-svn: 291764
Paul Osmialowski pointed out a double free bug in shutdown code. This patch
Moves the freeing of the implicit task to above the freeing of all fast memory
to prevent the double-free issue.
Differential Revision: https://reviews.llvm.org/D26860
llvm-svn: 287551
Have developer timers use partitioning scheme which also required that some
redundant developer timers be removed in favor of the already existing normal
timers. Move per thread stats initialization to just after global thread id
assignment which is as early as possible. Also put all global stats
initialization code in __kmp_stats_init() and all global stats destruction code
in __kmp_stats_fini().
Differential Revision: https://reviews.llvm.org/D26361
llvm-svn: 286892
This set of changes enables the affinity interface (Either the preexisting
native operating system or HWLOC) to be dynamically set at runtime
initialization. The point of this change is that we were seeing performance
degradations when using HWLOC. This allows the user to use the old affinity
mechanisms which on large machines (>64 cores) makes a large difference in
initialization time.
These changes mostly move affinity code under a small class hierarchy:
KMPAffinity
class Mask {}
KMPNativeAffinity : public KMPAffinity
class Mask : public KMPAffinity::Mask
KMPHwlocAffinity
class Mask : public KMPAffinity::Mask
Since all interface functions (for both affinity and the mask implementation)
are virtual, the implementation can be chosen at runtime initialization.
Differential Revision: https://reviews.llvm.org/D26356
llvm-svn: 286890
This patch allows ThreadSanitizer (Tsan) to verify OpenMP programs.
It means that no false positive will be reported by Tsan when
verifying an OpenMP programs.
This patch introduces annotations within the OpenMP runtime module to
provide information about thread synchronization to the Tsan runtime.
In order to enable the Tsan support when building the runtime, you must
enable the TSAN_SUPPORT option with the following environment variable:
-DLIBOMP_TSAN_SUPPORT=TRUE
The annotations will be enabled in the main shared library
(same mechanism of OMPT).
Patch by Simone Atzeni and Joachim Protze!
Differential Revision: https://reviews.llvm.org/D13072
llvm-svn: 286115
Check Task Scheduling Constraint (TSC) on stealing of untied task.
This is needed because the untied task can produce tied children
those can break TSC if untied is not a descendant of current task.
This can cause live lock on complex tyasking tests
(e.g. kastors/strassen-task-dep).
Differential Revision: https://reviews.llvm.org/D26182
llvm-svn: 285703
Summary:
If directives are used in a macro, clang complains with:
```
src/projects/openmp/runtime/src/kmp_runtime.c:7486:2: error: embedding a directive within macro arguments has undefined behavior [-Werror,-Wembedded-directive]
#if KMP_USE_MONITOR
```
This patch fixes two occurrences of the issue in `kmp_runtime.cpp`.
Reviewers: tlwilmar, jlpeyton, AndreyChurbanov, Hahnfeld
Subscribers: Hahnfeld, openmp-commits
Differential Revision: https://reviews.llvm.org/D25823
llvm-svn: 284728
Function strerror_r() has different signatures in different
implementations of libc: glibc's version returns a char*, while BSDs
and musl return a int. libomp unconditionally assumes glibc on Linux
and thus fails to compile against musl-libc. This patch addresses this
issue.
Differential Revision: https://reviews.llvm.org/D25071
llvm-svn: 284492
New mixed type atomic routines added for regular capture operations as well as
reverse update/capture operations. LHS - all integer and float types (no
complex so far), RHS - float16.
Patch by Olga Malysheva
Differential Revision: https://reviews.llvm.org/D25275
llvm-svn: 284489
This change removes/disables unnecessary code when monitor thread is not used.
Patch by Hansang Bae
Differential Revision: https://reviews.llvm.org/D25102
llvm-svn: 283577
Support finding lit as plain 'lit', which is the name used by setup.py
in LLVM's utils/lit.
Differential Revision: https://reviews.llvm.org/D25072
llvm-svn: 282876
Add check for "45" version to use "201511" string for OpenMP 4.5,
otherwise "200505" is used in Fortran module. Also, fix kmp_openmp_version
variable (used for the debugger, e.g.) and kmp_version_omp_api that is used
in KMP_VERSION=1 output.
Patch by Olga Malysheva
Differential Revision: https://reviews.llvm.org/D24761
llvm-svn: 282868
New routines should be used for atomics like "<int>OP=<float>" when <int> is
unsigned. Using functions __kmpc_atomic_fixed<bits>_<op>_fp) produces incorrect
results
Differential Revision: https://reviews.llvm.org/D24756
llvm-svn: 282509
This change set disables creation of the monitor thread by default. The global
counter maintained by the monitor thread was replaced by logic that uses system
time directly, and cyclic yielding on Linux target was also removed since there
was no clear benefit of using it. Turning on KMP_USE_MONITOR variable (=1)
enables creation of monitor thread again if it is really necessary for some
reasons.
Differential Revision: https://reviews.llvm.org/D24739
llvm-svn: 282507
Fix lit search to correctly respect LIBOMP_LLVM_LIT_EXECUTABLE as full
program path.
The variable passed to find_program() is created by CMake as a cache
variable, and therefore can be directly overriden by the user. Since
this was the design of LIBOMP_LLVM_LIT_EXECUTABLE (as can be deduced
from the error messages) and there is no other use of LIT_EXECUTABLE,
remove the redundant variable and pass LIBOMP_LLVM_LIT_EXECUTABLE
directly to find_program().
Furthermore, the previous code did not work since the HINTS argument
specifies more search directories rather than expected full path.
Quoting the CMake documentation:
> 3. Search the paths specified by the HINTS option. These should be
> paths computed by system introspection, such as a hint provided by
> the location of another item already found. Hard-coded guesses should
> be specified with the PATHS option.
Differential Revision: https://reviews.llvm.org/D24710
llvm-svn: 281887
Introduce a new LIBOMP_INSTALL_VARIABLES cache variable that can be used
to disable creating libgomp and libiomp5 aliases on 'make install'.
Those aliases are undesired e.g. on Gentoo systems where libomp is used
purely by clang.
Differential Revision: https://reviews.llvm.org/D24563
llvm-svn: 281512
Previous differencials D23305-D23310 changed task frame information management only for the kmp interface, but not for the whole gomp interface. This broke some testcases when building with gcc.
This patch fixes the broken task frame information for the gomp interface.
Patch by Joachim Protze!
Differential Revision: https://reviews.llvm.org/D24502
llvm-svn: 281468
In case, the current team is a serialized team (lwt), the frame information should be written to this data structure.
Before, nested serialized teams would overwrite the same task information.
Patch by Joachim Protze!
Differential Revision: https://reviews.llvm.org/D23310
llvm-svn: 281467
The comment already states, that this function should work similarly as __ompt_get_taskinfo.
The function only looked for lwt entries of the current team, but not when unrolling the parents. This fix aligns the implementation to __ompt_get_taskinfo.
The new test case creates a single theaded team (->lwt) and then a nested active team.
Before the innermost print_id(1) would deliver a different team then the outer print_id(0).
Patch by Joachim Protze!
Differential Revision: https://reviews.llvm.org/D23309
llvm-svn: 281466
The exit address is set when execution of a task is started and should be reset as soon as the execution is finished.
Especially for the asm implementation of __kmp_invoke_microtask, resetting in this call would be painfull, so reset just after the invokation.
The testcase shows the effect of this patch:
Before, the implicit barriers at the end of an implicit task would see an exit address for the implicit task.
This barrier is a task scheduling point. Thus, any explicit task scheduled there would see an exit, but no reenter address for the implicit task.
Patch by Joachim Protze!
Differential Revision: https://reviews.llvm.org/D23307
llvm-svn: 281465
The latest OMPT spec changed the semantic of a tasks reenter frame to be the application frame, that will be entered, when the runtime frame drops.
Before it was the last frame in the runtime. This doesn't work for some gcc execution pathes or even clang generated code for :
Since there is no runtime frame between the executed task and the encountering task.
The test case compares exit and reenter addresses against addresses captured in application code
Patch by Joachim Protze!
Differential Revision: https://reviews.llvm.org/D23305
llvm-svn: 281464
OMPT tests can check for right frame information of tasks:
* parent_task_frame was directly printed as a pointer, but actually points to a struct ompt_frame {void*, void*}
* NULL is printed in the beginning of execution and loaded to FileChecker variable [[NULL]]
* implicit tasks now also print their frame information
* macro to print frame address from application
* print task info for barrier begin
Patch by Joachim Protze!
Differential Revision: https://reviews.llvm.org/D23304
llvm-svn: 281463
Rather than checking KMP_CPU_SETSIZE, which doesn't exist when using Hwloc, we
use the get_max_proc() function which can vary based on the operating system.
For example on Windows with multiple processor groups, it might be the case that
the highest bit possible in the bitmask is not equal to the number of hardware
threads on the machine but something higher than that.
Differential Revision: https://reviews.llvm.org/D24206
llvm-svn: 281245
There is a bug in CMakeLists which causes powerpc64le systems to be recognized as big-endian. This patch fixes the issue.
Differential Revision: https://reviews.llvm.org/D23626
llvm-svn: 281068
Implementation of missing OpenMP 4.0 API functions omp_get_default_device and omp_set_default_device.
Also, added support for the environment variable OMP_DEFAULT_DEVICE.
Differential Revision: https://reviews.llvm.org/D23587
llvm-svn: 281065
When affinity isn't supported, __kmp_affinity_compact doesn't exist. The
problem is that in kmp_affinity.h there is a function which uses it without the
proper KMP_AFFINITY_SUPPORTED guard around it. The compiler was smart enough to
ignore it and the function __kmp_affinity_cmp_Address_child_num which relies on
it, but I think it is cleaner to have it under the proper guard. Since the
function is only used in the kmp_affinity.cpp file and there aren't any plans to
have it elsewhere. I have moved it there.
llvm-svn: 280542
the __kmp_affinity_determine_capable() functions are highly operating system
specific. This change has the functions use the type they expect explicitly.
llvm-svn: 280538
In case atomic reduction method is not available (the compiler can't generate
it) the assertion failure occurred if KMP_FORCE_REDUCTION=atomic was specified.
This change replaces the assertion with a warning and sets the reduction method
to the default one - 'critical'.
Patch by Olga Malysheva
Differential Revision: https://reviews.llvm.org/D23990
llvm-svn: 280519
Summary:
On FreeBSD, linking the misc_bugs/omp_foreign_thread_team_reuse.c test
case fails with:
/usr/local/bin/ld: /tmp/omp_foreign_thread_team_reuse-c5e71b.o: undefined reference to symbol 'pthread_create@@FBSD_1.0'
This is because the program is linked without `-lpthread`. Since the
%libomp-compile-and-run macro does not allow that option to be added to
the compile command line, split it up and add the required `-lpthread`
between %libomp-compile and %libomp-run.
Reviewers: jlpeyton, hfinkel, Hahnfeld
Subscribers: Hahnfeld, emaste, openmp-commits
Differential Revision: https://reviews.llvm.org/D23084
llvm-svn: 278036
Consider the following code:
int dep;
#pragma omp target nowait depend(out: dep)
{
sleep(1);
}
#pragma omp task depend(in: dep)
{
printf("Task with dependency\n");
}
printf("Doing some work...\n");
In its current state the runtime will block on the second task and not
continue execution.
Differential Revision: https://reviews.llvm.org/D23116
llvm-svn: 277992
Consider the following code which may be executed by a serial team:
int dep;
#pragma omp target nowait depend(out: dep)
{
sleep(1);
}
#pragma omp task depend(in: dep)
{
#pragma omp target nowait
{
sleep(1);
}
}
Here the explicit task may not be freed until the nested proxy task has
finished. The current code hasn't considered this and called __kmp_free_task
anyway which triggered an assert because of remaining incomplete children:
KMP_DEBUG_ASSERT( TCR_4(taskdata->td_incomplete_child_tasks) == 0 );
Differential Revision: https://reviews.llvm.org/D23115
llvm-svn: 277991
node->dn.task is only filled after the dependencies are already processed.
This currently leads to unhelpful output from KA_TRACE or even a crash
if one enables KMP_SUPPORT_GRAPH_OUTPUT.
llvm-svn: 277717
Summary:
Android does not have pthread_cancel. Disable KMP_CANCEL_THREADS if
__ANDROID__ is defined.
Subscribers: tberghammer, srhines, openmp-commits, danalbert
Differential Revision: https://reviews.llvm.org/D23029
llvm-svn: 277618
This patch enables balanced affinity on machines that do not have
hardware threads and have cores clustered into packages. In facts,
balacing algorithm could be generalized for any arrangement with
at least two levels of hierarchy (depth > 1).
Differential Revision: https://reviews.llvm.org/D22365
llvm-svn: 277212
Summary:
When compiling the runtime library with clang we get warnings like:
```
error: passing an object that undergoes default argument promotion to 'va_start' has undefined behavior [-Werror,-Wvarargs]
va_start( args, id );
^
note: parameter of type 'kmp_i18n_id_t' (aka 'kmp_i18n_id') is declared here
kmp_i18n_id_t id,
```
My understanding is that the va_start macro only gets the promoted type so it won't know what was the exact type of the argument, which can potentially not work for some targets given that the implementation of the the calling convention could not be done properly.
This patch fixes that by using a built-in type in the function signature.
Reviewers: tlwilmar, jlpeyton, AndreyChurbanov
Subscribers: arpith-jacob, carlo.bertolli, caomhin, openmp-commits
Differential Revision: https://reviews.llvm.org/D22427
llvm-svn: 276428
When linking with libhwloc, the ORDERED EPCC test slows down on big
machines (> 48 cores). Performance analysis showed that a cache thrash
was occurring and this padding helps alleviate the problem.
Also, inside the main spin-wait loop in kmp_wait_release.h, we can eliminate
the references to the global shared variables by instead creating a local
variable, oversubscribed and instead checking that.
Differential Revision: http://reviews.llvm.org/D22093
llvm-svn: 274894
These tests are now modeled after the sections nowait test where threads wait
to be released in the first construct (either for or single) and the last thread
skips the last for/single construct and releases those threads. If the test
fails, then it hangs because an unnecessary barrier is executed in between the
constructs.
llvm-svn: 274641
If update_master_only is set the place list is not completely traversed
and therefore this assertion failed. Make it only trigger if
update_master_only is false.
(was introduced by D20539)
Differential Revision: http://reviews.llvm.org/D21925
llvm-svn: 274482
This change fixes an error in comparing the existing schedule on the team to
the new schedule, in the chunk field. Also added additional checks and used
KMP_CHECK_UPDATE where appropriate.
Patch by Terry Wilmarth.
Differential Revision: http://reviews.llvm.org/D21897
llvm-svn: 274371
EPCC Performance of single is considerably worse than plain barrier.
Adding a read-only check to the code before the atomic compare-and-store
helps considerably.
Patch by Terry Wilmarth.
Differential Revision: http://reviews.llvm.org/D21893
llvm-svn: 274369
This rewrite of the omp_sections_nowait.c test file causes it to hang if the
nowait is not respected. If the nowait isn't respected, the lone thread which
can escape the first sections construct will just sleep at a barrier which
shouldn't exist. All reliance on timers is taken out. For good measure, the test
makes sure that all eight sections are executed as well. The test should take no
longer than a few seconds on any modern machine.
Differential Revision: http://reviews.llvm.org/D21842
llvm-svn: 274151
* Incorrect lock value written in __kmp_test_futex_lock
* Incorrect lock value check in tas/futex lock with USE_LOCK_PROFILE on
Patch by Hansang Bae
llvm-svn: 274053
UNICODE and _UNICODE defintions were added in the LLVM CMake build system.
While on Unices, the UNICODE/_UNICODE macros don't cause problems, on Windows
only ittnotify_static.c should be compiled using -DUNICODE. We are still
looking at a proper fix, but this change sets the build back to exactly what it
was doing before. Also, a comment and TODO were added in the src/CMakeLists.txt
file to help explain.
llvm-svn: 274052
That patch made all LLVM projects build with -DUNICODE. However, this doesn't
work for the OpenMP runtime.
But just overriding the flag with -UUNICODE breaks compiling ittnotify_static.c,
which for some reason needs to be compiled with -DUNICIODE. Note that compiling
ittnotify.h with -DUNICODE does not work though.
This seems like a mess. This commit fixes it for now, but it would be great
if someone who works on the OpenMP runtime could fix it properly.
llvm-svn: 273898
Bug fix for hang when omp task and nested parallelism used together.
Still some problem remains with task state saving/restoring, but
user's case works fine now. All tasking unit tests passed as well.
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21558
llvm-svn: 273297
Replaced readings of nproc from team structure with ones from
thread structure to improve performance.
Patch by Andrey Churbanov.
Differential Revision: http://reviews.llvm.org/D21559
llvm-svn: 273293
The removal of legacy code to support long-deprecated debugger support library
resulted in some whitespace changes. Comments from that legacy code were made
public as they may be useful for other debuggers.
Patch by Olga Malysheva.
Differential Revision: http://reviews.llvm.org/D21391
llvm-svn: 273282
A couple improvements:
1) Add ability to limit fullMask size when KMP_HW_SUBSET limits resources.
2) Make KMP_HW_SUBSET work for affinity_none, and only limit fullMask in this case.
Patch by Andrey Churbanov.
Differential Revision: http://reviews.llvm.org/D21528
llvm-svn: 273278
There was a segfault in the stubs library in posix_memalign because
of a bad parameter. The fix is to send address of the pointer as a
parameter. Also added check of result of posix_memalign.
Patch by Andrey Churbanov.
Differential Revision: http://reviews.llvm.org/D21529
llvm-svn: 273276
This change appends the process id to the KMP_STATS_FILE (if specified) which
enables MPI processes to output their stats to separate files.
Differential Revision: http://reviews.llvm.org/D21386
llvm-svn: 273273
Change hwloc discovery algorithm to print topology for only accessible
resources, and report uniformity correspondingly, similar to what other topology
discovery algorithms do. Fixes minor inconsistency in total topology reported
and resources used for threads binding in case hwloc used.
Patch by Andrey Churbanov.
Differential Revision: http://reviews.llvm.org/D21389
llvm-svn: 272952
This patch allows a user to enable Hwloc on windows. There are three main
changes in here:
1.kmp.h - Move definitions/declarations out of KMP_OS_WINDOWS guard (our windows
implementation of affinity) because they need to be defined when
KMP_USE_HWLOC is on as well.
2.teach __kmp_set_system_affinity, __kmp_get_system_affinity,
__kmp_get_proc_group, and __kmp_affinity_bind_thread how to use hwloc.
3.teach CMake how to include hwloc when building Windows
Another minor change in here is to make sure that anything under KMP_USE_HWLOC
is also guarded by KMP_AFFINITY_SUPPORTED as well. This is to prevent Mac
builds from requiring anything from Hwloc.
Differential Revision: http://reviews.llvm.org/D21441
llvm-svn: 272951
With single thread using __kmpc_omp_wait_deps segfaults in OpenMP runtime.
Offloading with depend also encounters this problem when we generate
kmpc_omp_wait_deps instead of kmpc_omp_task_with_deps.
Patch by Alex Duran
Differential Revision: http://reviews.llvm.org/D21384
llvm-svn: 272949
Cleanup: fixed missing memory cleanup in couple of corner cases. Fixes possible
memory leak in some corner cases
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21355
llvm-svn: 272946
Improved performance of ittnotify calls by request from ittnotify
owner: calls to __itt_string_handle_create made unique (it was
called multiple times).
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21353
llvm-svn: 272945
Deprecate KMP_PLACE_THREADS and rename it to KMP_HW_SUBSET due to confusion
about its purpose and function among users. KMP_HW_SUBSET is an environment
variable which allows users to easily pick a subset of the hardware topology to
use. e.g., KMP_HW_SUBSET=30c,2t means use 30 cores, 2 threads per core.
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21340
llvm-svn: 272937
Added argv array check/allocation for parallel directly nested inside the teams
construct, as new coming Fortran codegen passes parameters directly into
kmpc_fork_call missing same parameters in kmpc_fork_teams (earlier codegen
passed to parallel the subset of parameter passed to teams, and thus
no check/allocation needed).
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21336
llvm-svn: 272935
Currently, there is a big overhead in reporting of loop metadata through
ittnotify. The pair of functions: __kmp_str_loc_init/__kmp_str_loc_free are
replaced with strchr/atoi calls. Thus, a lot of time consuming actions are
skipped - many memory allocations/deallocations, heavy string duplication, etc.
The loop metadata only needs line and column info from the source string, so no
allocations and string splitting actually needed.
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21309
llvm-svn: 272698
Cleanup - unused code removal.
TODO: consider to remove (replace with flag class methods)
also kmp_wait_64 and kmp_release_64 routines.
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21332
llvm-svn: 272697
OpenMP 4.1 is now OpenMP 4.5. Any mention of 41 or 4.1 is replaced with
45 or 4.5. Also, if the CMake option LIBOMP_OMP_VERSION is 41, CMake warns that
41 is deprecated and to use 45 instead.
llvm-svn: 272687
Fix for bugzilla https://llvm.org/bugs/show_bug.cgi?id=26602. Removed functions
body consisted of the only KMP_ASSERT(0) statement. Thus possible runtime crash
converted to compile-time error, which looks preferable (faster possible error
detection).
TODO: consider C++11 static assert as an alternative, that could
make the diagnostics better.
Patch by Andrey Churbanov
Differential Revision: http://reviews.llvm.org/D21304
llvm-svn: 272590
Remove static specifier from var fullMask and remove kmp_get_fullMask() routine.
When iterating through procs in a mask, always check if proc is in fullMask
(this check was missing in a few places).
Patch by Brian Bliss.
Differential Revision: http://reviews.llvm.org/D21300
llvm-svn: 272589
If either current_task or new_task is untied then skip task scheduling
constraint checks, because untied tasks are not affected by the task
scheduling constraints.
Differential Revision: http://reviews.llvm.org/D21196
llvm-svn: 272570
The problem scenario is the following:
A dynamic library, libfoo.so, depends on libomp.so (it creates parallel region
and calls some omp functions). An application has a loop where it dynamically
loads libfoo.so, calls the function from it, unloads libfoo.so. After several
loop iterations application crashes with the message about lack of resources
OMP: Error #34: System unable to allocate necessary resources for OMP thread:
The problem is that pthread_kill() was not followed by pthread_join() in case
of terminated thread. This patch fixes this problem for both worker and monitor
threads.
Differential Revision: http://reviews.llvm.org/D21200
llvm-svn: 272567
These changes remove the hwloc_topology_ignore_type function which doesn't exist
in the hwloc 2.0 API. In the existing code, the topology extracted from hwloc
has the cache levels stripped out and then assumes the final stripped topology
follows the typical three-level topology: packages -> cores -> HW threads.
But the code is doing unclean manipulations to determine at what level those
resources are located and also assumes too much about what hwloc is detecting
(there could be intermediate levels in between socket and core for instance).
This new way of extracting the topology doesn't strip out any hardware objects
that hwloc detects. It does not assume the three level topology, and instead
searches for the relevant three levels within the topology for each bit of
information using hwloc interface functions. i.e., the three level topology
subset that our affinity code is interested in is extracted from the hwloc
topology tree directly.
For example, the new __kmp_hwloc_get_nobjs_under_obj function gives the user the
number of cores under a socket reliably without worrying if there are unexpected
objects between the socket object and core object in the hwloc topology
structure. Also, now that all topology information is kept, there are also
possibilities of using the caches/numa nodes to determine more sophisticated
affinity settings in the future.
There is also some cleanup code added for the destruction of the
__kmp_hwloc_topology object.
Differential Revision: http://reviews.llvm.org/D21195
llvm-svn: 272565
The bitmask complement operation doesn't consider the max proc id which means
something like !{0} will be translated to {1,2,3,4,...,600,601,...,1023} on a
Linux system even though there aren't 600 processors on said system. This
change has the complement bitmask and-ed with the fullmask so that it will only
contain valid processors.
Differential Revision: http://reviews.llvm.org/D21245
llvm-svn: 272561
Refactored __kmp_execute_tasks_template to shorten and remove code redundancy.
The original code for __kmp_execute_tasks_template was very redundant with
large sections of repeated code that needed to be kept consistent, and goto
statements that made the control flow difficult to discern. This refactoring
removes all gotos and redundancy.
Patch by Terry Wilmarth
Differential Revision: http://reviews.llvm.org/D20879
llvm-svn: 272286
MSVC doesn't allow std::atomic<>s in a union since they don't have trivial
copy constructor. Replacing them with e.g. std::atomic_int works, but that
breaks the GCC build on Linux, because then calls to e.g. std::atomic_load_explicit
fail, as they expect a real std::atomic<> pointer.
Fixing this with an #ifdef to unbreak the build for now.
llvm-svn: 272271
As I replaced no-op TCR_4 with actual code, compiler complained while building debug build.
This patch moves 'cast to int' to the correct place.
Extension to Differential Revision: http://reviews.llvm.org/D19880
llvm-svn: 271377
This patch replaces use of compiler builtin atomics with
C++11 atomics for ticket locks implementation. Ticket locks
are used in critical places of the runtime, e.g. in the tasking
mechanism.
The main reason this change was introduced is the problem
with work stealing function on ARM architecture which suffered
from nasty race condition. It turned out that the root cause of
the problem lies in the way ticket locks are implemented. Changing
compiler builtins into C++11 atomics solves the problem.
Two assertions were added into kmp_tasking.c which are useful
for detecting early symptoms of something wrong going on with
work stealing, which were among the possible outcomes of the
race condition.
Differential Revision: http://reviews.llvm.org/D19878
llvm-svn: 271324
This patch implements the new kmp_sch_static_balanced_chunked schedule kind that
the compiler will generate when it encounters schedule(simd: static). It just
adds the new constant and the new switch case __kmp_for_static_init.
Patch by Alex Duran.
Differential Revision: http://reviews.llvm.org/D20699
llvm-svn: 271320
When an asynchronous offload task is completed, COI calls the runtime to queue
a "destructor task". When the task deques are full, a dead-lock situation
arises where the OpenMP threads are inside but cannot progress because the COI
thread is stuck inside the runtime trying to find a slot in a deque.
This patch implements the solution where the task deques doubled in size when
a task is being queued from a COI thread.
Differential Revision: http://reviews.llvm.org/D20733
llvm-svn: 271319
The problem is the lack of dispatch buffers when thousands of loops with nowait,
about 10 iterations each, are executed by hundreds of threads. We only have
built-in 7 dispatch buffers, but there is a need in dozens or hundreds of
buffers.
The problem can be fixed by setting KMP_MAX_DISP_BUF to bigger value. In order
to give users same possibility I changed build-time control into run-time one,
adding API just in case.
This change adds an environment variable KMP_DISP_NUM_BUFFERS and a new API
function kmp_set_disp_num_buffers(int num_buffers).
The KMP_DISP_NUM_BUFFERS envirable works only before serial initialization,
because during the serial initialization we already allocate buffers for the hot
team, so it is too late to change the number of buffers later (or we need to
reallocate buffers for all teams which sounds too complicated). The
kmp_set_defaults() routine does not work for this envirable, because it calls
serial initialization before reading the parameter string. So a new routine,
kmp_set_disp_num_buffers(), is created so that it can set our internal global
variable before the library initialization. If both the envirable and API used
the envirable wins.
Differential Revision: http://reviews.llvm.org/D20697
llvm-svn: 271318
The OMP_PROC_BIND=spread strategy fails to assign the master thread the
correct place partition after the first parallel region. Other threads in the
hot team will remember their place_partition, but the master's place partition
is restored to what it was before entering the parallel region. So when the hot
team is used for subsequent parallel regions, the master has lost this info.
This fix calls __kmp_partition_places to update only the master thread's place
partition in the spread case when there are no other changes to the hot team.
Patch by Terry Wilmarth
Differential Revision: http://reviews.llvm.org/D20539
llvm-svn: 270890
On Blue Gene/Q, having LIBOMP_USE_ITT_NOTIFY support compiled into a
statically-linked binary causes a failure at runtime because dlopen fails.
This patch changes LIBOMP_USE_ITT_NOTIFY to a cacheable configuration setting
that can be disabled.
Patch by John Mellor-Crummey
Differential Revision: http://reviews.llvm.org/D20517
llvm-svn: 270884
Clang no longer restricts itself to generating microtasks with a small number
of arguments, and so an assembly implementation is required to prevent hitting
the parameter limit present in the C implementation. This adds an
implementation for ppc64[le].
llvm-svn: 270821
Most of this is modifications to check for differences before updating data
fields in team struct. There is also some rearrangement of the team struct.
Patch by Diego Caballero
Differential Revision: http://reviews.llvm.org/D20487
llvm-svn: 270468
These changes allow testing on Windows using clang.exe.
There are two main changes:
1. Only link to -lm when it actually exists on the system
2. Create basic versions of pthread_create() and pthread_join() for windows.
They are not POSIX compliant by any stretch but will allow any existing
and future tests to use pthread_create() and pthread_join() for testing
interactions of libomp with os threads.
Differential Revision: http://reviews.llvm.org/D20391
llvm-svn: 270464
Jonathan Peyton