summaryrefslogtreecommitdiffstats
path: root/openmp/runtime/src
Commit message (Collapse)AuthorAgeFilesLines
...
* Partial revert of [OMPT] Rename ompt_mutex_impl_t to kmp_mutex_implJoachim Protze2018-01-171-3/+3
| | | | | | The previous commit did not revert all replaced ompt_mutex_impl_unknown. llvm-svn: 322631
* [OMPT] Rename ompt_mutex_impl_t to kmp_mutex_implJoachim Protze2018-01-174-36/+36
| | | | | | | | | | The defintion is not part of the spec and thus should not have the prefix "ompt_" but rather a prefix that indicates that this is implementation specific. Differential Revision: https://reviews.llvm.org/D41166 llvm-svn: 322621
* [OMPT] Return appropiate values for ompt runtime entry points for non-OpenMP ↵Joachim Protze2018-01-172-8/+24
| | | | | | | | | | | threads When the current thread is not an (initialized) OpenMP thread, the runtime entry points return values that correspond to "not available" or similar Differential Revision: https://reviews.llvm.org/D41167 llvm-svn: 322620
* Fixed libomp static build broken by the commit rL322202.Andrey Churbanov2018-01-111-0/+2
| | | | | | | | Patch by simone <simone@cs.utah.edu>. Differential Revision: https://reviews.llvm.org/D41945 llvm-svn: 322282
* Force HWLOC topology method for NUMA-specific topologyJonathan Peyton2018-01-101-0/+9
| | | | | | | | | | | | If user requested affinity with granularity=tile we need to either use HWLOC or ignore the request. The change allows user to not specify KMP_TOPOLOGY_METHOD=hwloc and choose it automatically instead. Patch by Andrey Churbanov Differential Revision: https://reviews.llvm.org/D40905 llvm-svn: 322205
* Simplify __kmp_expand_threadsJonathan Peyton2018-01-101-37/+12
| | | | | | | | | | | | | | This change simplifies __kmp_expand_threads to take a single argument. Previously, it allowed two arguments and had logic to decide on different potential expansion sizes. However, no calls to __kmp_expand_threads in the runtime make use of this extra logic. Thus the extra argument and logic is removed here. Patch by Terry Wilmarth Differential Revision: https://reviews.llvm.org/D41836 llvm-svn: 322204
* Minor code cleanupJonathan Peyton2018-01-103-4/+13
| | | | | | | | Patch by Terry Wilmarth Differential Revision: https://reviews.llvm.org/D41831 llvm-svn: 322203
* Improve stability of the runtime in parent/child processesJonathan Peyton2018-01-106-4/+32
| | | | | | | | | | | | | | | This change improves stability of the runtime when the application forks child processes. Acquiring/releasing __kmp_initz_lock and __kmp_forkjoin_lock in the atfork handlers insures that the actual fork does not occur while those two locks are held, and __kmp_itt_reset() reverts the itt's global state to the initial state which also initializes the mutex stored in the global state. Some missing initialization code was also inserted in the child's atfork handler. Patch by Hansang Bae Differential Revision: https://reviews.llvm.org/D41462 llvm-svn: 322202
* [OMPT] Fix ompt_task_data handling in implicit barriersJoachim Protze2018-01-102-1/+2
| | | | | | | | Changes to task_data in barrier-begin were not visible at barrier-end Differential Revision: https://reviews.llvm.org/D41176 llvm-svn: 322178
* Fix type mismatch in omp_control_tool() implementation that makes it run ↵Paul Osmialowski2018-01-091-1/+1
| | | | | | | | incorrectly on 32-bit machines. Differential Revision: https://reviews.llvm.org/D41854 llvm-svn: 322068
* Correct types of pointers to doacross_num_doneJonas Hahnfeld2018-01-071-3/+3
| | | | | | | | | | This field is defined as kmp_int32, so we should use neither pointers to kmp_int64 nor 64 bit atomic instructions. (Found while testing on a Raspberry Pi, 32 bit ARM) Differential Revision: https://reviews.llvm.org/D41656 llvm-svn: 321964
* Fix some comments and formatting in kmp_dispatch.cppJonathan Peyton2018-01-041-8/+9
| | | | llvm-svn: 321831
* Fix trademarks found by scannerJonathan Peyton2018-01-046-28/+28
| | | | llvm-svn: 321827
* [OMPT] Set and reset frame address when creating a task with dependencesJoachim Protze2017-12-241-6/+17
| | | | | | | | | As for normal task creation, the task frame addresses need to be stored for the encountering task. Differential Revision: https://reviews.llvm.org/D41165 llvm-svn: 321421
* Remove unused positional argument for printfJoachim Protze2017-12-222-2/+4
| | | | | | | | | | | | | | | | | The format string for hints only prints the second argument (string) and drops the first argument (hint id). Depending on how you read the POSIX text for printf, this could be valid. But for practical reason, i.e., unpacking the va_list passed to printf based on the formating information, it makes sense to fix the implementation and not pass the id for hint. Failing testcases were: misc_bugs/teams-reduction.c ompt/parallel/not_enough_threads.c Differential Revision: https://reviews.llvm.org/D41504 llvm-svn: 321361
* [OMPT] Add missing ompt_get_num_procs functionJoachim Protze2017-12-212-0/+13
| | | | | | | | | | | | | This function is defined in OpenMP-TR6 section 4.1.5.1.6 The functions was not implemented yet. Since ompt-functions can only be called after the runtime was initialized and has loaded a tool, it can assume the runtime to be initialized. In contrast to omp_get_num_procs which needs to check whether the runtime is initialized. Differential Revision: https://reviews.llvm.org/D40949 llvm-svn: 321269
* [OMPT] Fix return address handling in a few GOMP interface methodsJoachim Protze2017-12-211-4/+10
| | | | | | | | | | | This revision fixes failing testcases with parallel for loops and the gomp interface. The return address needs to be stored at entry to runtime. The storage is cleared on usage, so we need to update the storage before calling again internal functions, that will trigger event callbacks. Differential Revision: https://reviews.llvm.org/D41181 llvm-svn: 321265
* [OMPT] Handle null pointer in set_callback to improve performanceJoachim Protze2017-12-211-2/+5
| | | | | | | | | | | | | We use the bitmap ompt_enabled thoughout the runtime, to avoid loading the vector of callback functions when testing if specific code should be executed. Before invoking an event callback function, the pointer is tested for NULL. This revision resets the corresponding bit in ompt_enabled to 0 if NULL is passed in set_callback. Differential Revision: https://reviews.llvm.org/D41171 llvm-svn: 321264
* [AArch64] fix an issue with older /proc/cpuinfo layoutPaul Osmialowski2017-12-131-0/+8
| | | | | | | | | | There are two /proc/cpuinfo layots in use for AArch64: old and new. The old one has all 'processor : n' lines in one section, hence checking for duplications does not make sense. Differential Revision: https://reviews.llvm.org/D41000 llvm-svn: 320593
* Use hyperbarrier by default on all architecturesJonas Hahnfeld2017-12-081-15/+6
| | | | | | | | | | | | | | | | | | All architectures except x86_64 used the linear barrier implementation by default which doesn't give good performance for a larger number of threads. Improvements for PARALLEL overhead (EPCC) with this patch on a Power8 system (2 sockets x 10 cores x 8 threads, OMP_PLACES=cores) 20 threads: 4.55us -> 3.49us 40 threads: 8.84us -> 4.06us 80 threads: 19.18us -> 4.74us 160 threads: 54.22us -> 6.73us Differential Revision: https://reviews.llvm.org/D40358 llvm-svn: 320152
* Fix thread affinity on non-x86 LinuxJonas Hahnfeld2017-12-082-5/+2
| | | | | | | | | | | | | | | | | To make thread affinity work according to the OpenMP spec, the runtime needs information about the hardware topology. On Linux the default way is to parse /proc/cpuinfo which contains this information for x86 machines but (at least) not for AArch64 and Power architectures. Fortunately, there is a different code path which is able to get that data from sysfs. The needed patch has landed in 2006 for Linux 2.6.16 which is safe to assume nowadays (even RHEL 5 had a kernel version derived from 2.6.18, and we are now at RHEL 7!). Differential Revision: https://reviews.llvm.org/D40357 llvm-svn: 320151
* Add missing memory barrier for queuing locksJonas Hahnfeld2017-12-081-0/+1
| | | | | | | | | | Otherwise I see hangs in the omp_single_copyprivate test when compiling in release mode. With the debug assertions, I get a failure `head > 0 && tail > 0`. Differential Revision: https://reviews.llvm.org/D40722 llvm-svn: 320150
* [OpenMP] Add entry for Intel Compiler 18Jonathan Peyton2017-12-061-0/+2
| | | | | | | | Patch by Simon Convent Differential Revision: https://reviews.llvm.org/D40386 llvm-svn: 319961
* Eliminate double printing of verbose affinity settingsJonathan Peyton2017-12-061-1/+3
| | | | | | | | | Redundant extra verbose output of binding to full mask in case affinity=balanced or OMP_PLACES=<any> or OMP_PROC_BIND=<any> Differential Revision: https://reviews.llvm.org/D40624 llvm-svn: 319960
* Trivial enum fixJonathan Peyton2017-12-061-4/+4
| | | | | | | | | | | | This change is a trivial fix for enums that removes specification of "last" or "upper" values, or other boundary values. This simplifies the code in places, and results in never needing to update the "upper" values again. Patch by Terry Wilmarth Differential Revision: https://reviews.llvm.org/D40804 llvm-svn: 319957
* Fix PR30890: Reduction across teams hangsJonas Hahnfeld2017-12-051-23/+70
| | | | | | | | | | __kmpc_reduce_nowait() correctly swapped the teams for reductions in a teams construct. Apply the same logic to __kmpc_reduce() and __kmpc_reduce_end(). Differential Revision: https://reviews.llvm.org/D40753 llvm-svn: 319788
* Extension of HWLOC topology discovery with NUMA nodes and tilesAndrey Churbanov2017-11-305-179/+385
| | | | | | | | Patch by Olga Malysheva Differential Revision: https://reviews.llvm.org/D40309 llvm-svn: 319422
* Make kmp_r_sched_t into a unionJonathan Peyton2017-11-292-30/+24
| | | | | | | | | | | This change makes kmp_r_sched_t type into a union for simpler comparisons and assignments Patch by Terry Wilmarth Differential Revision: https://reviews.llvm.org/D40374 llvm-svn: 319379
* Fix aligned memory allocation in the stub libraryJonathan Peyton2017-11-291-9/+34
| | | | | | | | | | | | | | kmp_aligned_malloc() always returned NULL on Windows (stub library only) that may cause Fortran application crash. With this change all memory allocation functions were fixed to use aligned{m,re,rec}alloc() to allocate/reallocate memory. To deallocate that memory _aligned_free() is used in kmp_free(). Patch by Olga Malysheva Differential Revision: https://reviews.llvm.org/D40296 llvm-svn: 319375
* Warning is emitted when tiles are requested but cannot be usedJonathan Peyton2017-11-292-1/+15
| | | | | | | | | | | | | | Added two warnings: 1) Before building the topology map check if tiles are requested but the topo method is not hwloc; 2) After building the topology map check if tiles are requested but not detected by the library. Patch by Olga Malysheva Differential Revision: https://reviews.llvm.org/D40340 llvm-svn: 319374
* Fix types of Fortran array elementsJonathan Peyton2017-11-296-12/+12
| | | | | | | | | | | | Fortran array elements made default integer in OMP_GET_PLACE_PROC_IDS and OMP_GET_PARTITION_PLACE_NUMS subroutines, otherwise call to them produces incorrect result. Patch by Olga Malysheva Differential Revision: https://reviews.llvm.org/D40356 llvm-svn: 319372
* [CMake] Refactor common settings and flagsJonas Hahnfeld2017-11-291-5/+5
| | | | | | | | | | | | These are needed by both libraries, so we can do that in a common namespace and unify configuration parameters. Also make sure that the user isn't requesting libomptarget if the library cannot be built on the system. Issue an error in that case. Differential Revision: https://reviews.llvm.org/D40081 llvm-svn: 319342
* [CMake] Disallow direct configurationJonas Hahnfeld2017-11-291-1/+1
| | | | | | | | | | As a first step, this allows us to generalize the detection of standalone builds and make it fully compatible when building in llvm/runtimes/ which automatically sets OPENMP_STANDLONE_BUILD. Differential Revision: https://reviews.llvm.org/D40080 llvm-svn: 319341
* Fix for OMP doacross implementation on PowerJonas Hahnfeld2017-11-221-1/+8
| | | | | | | | | | Power has a weak consistency model so we need memory barriers to make writes (both from runtime and from user code) available for all threads. Differential Revision: https://reviews.llvm.org/D40175 llvm-svn: 318848
* Fixed OMP doacross implementation on 32-bit platforms.Andrey Churbanov2017-11-201-8/+15
| | | | | | Differential Revision: https://reviews.llvm.org/D40171 llvm-svn: 318658
* Exclude untied tasks from checking of task scheduling constraint (TSC).Andrey Churbanov2017-11-163-101/+164
| | | | | | | | This can improve performance of tests with untied tasks. Differential Revision: https://reviews.llvm.org/D39613 llvm-svn: 318388
* [OMPT] Provide initialization for Mac OS XJonas Hahnfeld2017-11-111-33/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Traditionally, the library had a weak symbol for ompt_start_tool() that served as fallback and disabled OMPT if called. Tools could provide their own version and replace the default implementation to register callbacks and lookup functions. This mechanism has worked reasonably well on Linux systems where this interface was initially developed. On Darwin / Mac OS X the situation is a bit more complicated and the weak symbol doesn't work out-of-the-box. In my tests, the library with the tool needed to link against the OpenMP runtime to make the process work. This would effectively mean that a tool needed to choose a runtime library whereas one design goal of the interface was to allow tools that are agnostic of the runtime. The solution is to use dlsym() with the argument RTLD_DEFAULT so that static implementations of ompt_start_tool() are found in the main executable. This works because the linker on Mac OS X includes all symbols of an executable in the global symbol table by default. To use the same code path on Linux, the application would need to be built with -Wl,--export-dynamic. To avoid this restriction, we continue to use weak symbols on Linux systems as before. Finally this patch extends the existing test to cover all possible ways of initializing the tool as described by the standard. It also fixes ompt_finalize() to not call omp_get_thread_num() when the library is shut down which resulted in hangs on Darwin. The changes have been tested on Linux to make sure that it passes the current tests as well as the newly extended one. Differential Revision: https://reviews.llvm.org/D39801 llvm-svn: 317980
* [OMPT] Fix assertion for OpenMP code generated with outdated compilersJoachim Protze2017-11-103-7/+13
| | | | | | | | | | | | For up-to-date compilers, this assertion is reasonable, but it breaks compatibility with the typical compiler installed on most systems. This patch changes the default value to what we had when there was no compiler support. A warning about the outdated compiler is printed during runtime, when this point is reached. Differential Revision: https://reviews.llvm.org/D39890 llvm-svn: 317928
* Add const to some variables to avoid const_castsJonas Hahnfeld2017-11-092-7/+6
| | | | | | | | | In these places the const attribute seems correct and doesn't need any other change, so let's do it. Differential Revision: https://reviews.llvm.org/D39756 llvm-svn: 317798
* Remove const from variables with dynamic memoryJonas Hahnfeld2017-11-0913-83/+70
| | | | | | | | | | | | | | | | | | | Allocated memory is typically not 'const' if it needs to be freed. This patch removes around 50 wrong const attributes, modifies the corresponding functions and finally gets rid of some const_casts. These have especially been strange for __kmp_str_fname_free() that added a 'const' to call __kmp_str_free() which removed it again. Two minor cleanups that I performed in this process: * __kmp_tool_libraries now lives in kmp_settings.cpp as it is used nowhere else. * __kmp_msg_empty was removed as it was never used and Clang now complained that it was assigned a string literal that is 'const char *'. Differential Revision: https://reviews.llvm.org/D39755 llvm-svn: 317797
* Cleanup version symbol macros and attributes/declspecsJonathan Peyton2017-11-0710-523/+371
| | | | | | | | | | | | 1) Get rid of xaliasify, xexpand and xversionify for KMP_EXPAND_NAME and KMP_VERSION_SYMBOL. KMP_VERSION_SYMBOL is a combination of xaliasify and xversionify. 2) Put all attribute and __declspec definitions in kmp_os.h Differential Revision: https://reviews.llvm.org/D39516 llvm-svn: 317636
* [OMPT] Improve cast that was lost on commit, NFC.Jonas Hahnfeld2017-11-061-2/+2
| | | | llvm-svn: 317480
* Updating implementation of OMPT as specified in OpenMP 5.0 Preview 2 (TR6)Joachim Protze2017-11-055-259/+167
| | | | | | | | | | | The TR6 document is expected to be publically released around November 15. This patch does not implement OMPT for libomptarget. Patch by Simon Convent and Joachim Protze Differential Revision: https://reviews.llvm.org/D39182 llvm-svn: 317436
* Rename fields of ompt_frame_tJoachim Protze2017-11-058-102/+94
| | | | | | | | | | This is part of the renaming of data types from OpenMP TR4 to TR6 Patch by Simon Convent Differential Revision: https://reviews.llvm.org/D39326 llvm-svn: 317435
* Revert "Rename fields of ompt_frame_t"Jonas Hahnfeld2017-11-038-94/+102
| | | | | | This reverts commit r317338 which discarded some recent commits. llvm-svn: 317347
* Revert "Updating implementation of OMPT as specified in OpenMP 5.0 Preview 2 ↵Jonas Hahnfeld2017-11-0315-218/+314
| | | | | | | | (TR6)" This reverts commit r317339 which discarded some recent commits. llvm-svn: 317346
* Updating implementation of OMPT as specified in OpenMP 5.0 Preview 2 (TR6)Joachim Protze2017-11-0315-314/+218
| | | | | | | | | | | The TR6 document is expected to be publically released around November 15. This patch does not implement OMPT for libomptarget. Patch by Simon Convent and Joachim Protze Differential Revision: https://reviews.llvm.org/D39182 llvm-svn: 317339
* Rename fields of ompt_frame_tJoachim Protze2017-11-038-102/+94
| | | | | | | | | | This is part of the renaming of data types from OpenMP TR4 to TR6 Patch by Simon Convent Differential Revision: https://reviews.llvm.org/D39326 llvm-svn: 317338
* [OpenMP] Fix race condition in omp_init_lockJonathan Peyton2017-11-011-3/+4
| | | | | | | | | | | | | | | | | | | | | This is a partial fix for bug 34050. This prevents callers of omp_set_lock (which does not hold __kmp_global_lock) from ever seeing an uninitialized version of __kmp_i_lock_table.table. It does not solve a use-after-free race condition if omp_set_lock obtains a pointer to __kmp_i_lock_table.table before it is updated and then attempts to dereference afterwards. That race is far less likely and can be handled in a separate patch. The unit test usually segfaults on the current trunk revision. It passes with the patch. Patch by Adam Azarchs Differential Revision: https://reviews.llvm.org/D39439 llvm-svn: 317115
* Update implementation of OMPT to the specification OpenMP 5.0 Preview 1 (TR4).Joachim Protze2017-11-0131-1420/+3619
| | | | | | | | | | | | | | The code is tested to work with latest clang, GNU and Intel compiler. The implementation is optimized for low overhead when no tool is attached shifting the cost to execution with tool attached. This patch does not implement OMPT for libomptarget. Patch by Simon Convent and Joachim Protze Differential Revision: https://reviews.llvm.org/D38185 llvm-svn: 317085
OpenPOWER on IntegriCloud