2013-09-27 18:38:44 +08:00
|
|
|
/*
|
|
|
|
|
* kmp_ftn_os.h -- KPTS Fortran defines header file.
|
I apologise in advance for the size of this check-in. At Intel we do
understand that this is not friendly, and are working to change our
internal code-development to make it easier to make development
features available more frequently and in finer (more functional)
chunks. Unfortunately we haven't got that in place yet, and unpicking
this into multiple separate check-ins would be non-trivial, so please
bear with me on this one. We should be better in the future.
Apologies over, what do we have here?
GGC 4.9 compatibility
--------------------
* We have implemented the new entrypoints used by code compiled by GCC
4.9 to implement the same functionality in gcc 4.8. Therefore code
compiled with gcc 4.9 that used to work will continue to do so.
However, there are some other new entrypoints (associated with task
cancellation) which are not implemented. Therefore user code compiled
by gcc 4.9 that uses these new features will not link against the LLVM
runtime. (It remains unclear how to handle those entrypoints, since
the GCC interface has potentially unpleasant performance implications
for join barriers even when cancellation is not used)
--- new parallel entry points ---
new entry points that aren't OpenMP 4.0 related
These are implemented fully :-
GOMP_parallel_loop_dynamic()
GOMP_parallel_loop_guided()
GOMP_parallel_loop_runtime()
GOMP_parallel_loop_static()
GOMP_parallel_sections()
GOMP_parallel()
--- cancellation entry points ---
Currently, these only give a runtime error if OMP_CANCELLATION is true
because our plain barriers don't check for cancellation while waiting
GOMP_barrier_cancel()
GOMP_cancel()
GOMP_cancellation_point()
GOMP_loop_end_cancel()
GOMP_sections_end_cancel()
--- taskgroup entry points ---
These are implemented fully.
GOMP_taskgroup_start()
GOMP_taskgroup_end()
--- target entry points ---
These are empty (as they are in libgomp)
GOMP_target()
GOMP_target_data()
GOMP_target_end_data()
GOMP_target_update()
GOMP_teams()
Improvements in Barriers and Fork/Join
--------------------------------------
* Barrier and fork/join code is now in its own file (which makes it
easier to understand and modify).
* Wait/release code is now templated and in its own file; suspend/resume code is also templated
* There's a new, hierarchical, barrier, which exploits the
cache-hierarchy of the Intel(r) Xeon Phi(tm) coprocessor to improve
fork/join and barrier performance.
***BEWARE*** the new source files have *not* been added to the legacy
Cmake build system. If you want to use that fixes wil be required.
Statistics Collection Code
--------------------------
* New code has been added to collect application statistics (if this
is enabled at library compile time; by default it is not). The
statistics code itself is generally useful, the lightweight timing
code uses the X86 rdtsc instruction, so will require changes for other
architectures.
The intent of this code is not for users to tune their codes but
rather
1) For timing code-paths inside the runtime
2) For gathering general properties of OpenMP codes to focus attention
on which OpenMP features are most used.
Nested Hot Teams
----------------
* The runtime now maintains more state to reduce the overhead of
creating and destroying inner parallel teams. This improves the
performance of code that repeatedly uses nested parallelism with the
same resource allocation. Set the new KMP_HOT_TEAMS_MAX_LEVEL
envirable to a depth to enable this (and, of course, OMP_NESTED=true
to enable nested parallelism at all).
Improved Intel(r) VTune(Tm) Amplifier support
---------------------------------------------
* The runtime provides additional information to Vtune via the
itt_notify interface to allow it to display better OpenMP specific
analyses of load-imbalance.
Support for OpenMP Composite Statements
---------------------------------------
* Implement new entrypoints required by some of the OpenMP 4.1
composite statements.
Improved ifdefs
---------------
* More separation of concepts ("Does this platform do X?") from
platforms ("Are we compiling for platform Y?"), which should simplify
future porting.
ScaleMP* contribution
---------------------
Stack padding to improve the performance in their environment where
cross-node coherency is managed at the page level.
Redesign of wait and release code
---------------------------------
The code is simplified and performance improved.
Bug Fixes
---------
*Fixes for Windows multiple processor groups.
*Fix Fortran module build on Linux: offload attribute added.
*Fix entry names for distribute-parallel-loop construct to be consistent with the compiler codegen.
*Fix an inconsistent error message for KMP_PLACE_THREADS environment variable.
llvm-svn: 219214
2014-10-08 00:25:50 +08:00
|
|
|
* $Revision: 43354 $
|
|
|
|
|
* $Date: 2014-07-22 17:15:02 -0500 (Tue, 22 Jul 2014) $
|
2013-09-27 18:38:44 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
//
|
|
|
|
|
// 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 KMP_FTN_OS_H
|
|
|
|
|
#define KMP_FTN_OS_H
|
|
|
|
|
|
|
|
|
|
// KMP_FNT_ENTRIES may be one of: KMP_FTN_PLAIN, KMP_FTN_UPPER, KMP_FTN_APPEND, KMP_FTN_UAPPEND.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* -------------------------- External definitions ------------------------ */
|
|
|
|
|
|
|
|
|
|
#if KMP_FTN_ENTRIES == KMP_FTN_PLAIN
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_STACKSIZE kmp_set_stacksize
|
|
|
|
|
#define FTN_SET_STACKSIZE_S kmp_set_stacksize_s
|
|
|
|
|
#define FTN_GET_STACKSIZE kmp_get_stacksize
|
|
|
|
|
#define FTN_GET_STACKSIZE_S kmp_get_stacksize_s
|
|
|
|
|
#define FTN_SET_BLOCKTIME kmp_set_blocktime
|
|
|
|
|
#define FTN_GET_BLOCKTIME kmp_get_blocktime
|
|
|
|
|
#define FTN_SET_LIBRARY_SERIAL kmp_set_library_serial
|
|
|
|
|
#define FTN_SET_LIBRARY_TURNAROUND kmp_set_library_turnaround
|
|
|
|
|
#define FTN_SET_LIBRARY_THROUGHPUT kmp_set_library_throughput
|
|
|
|
|
#define FTN_SET_LIBRARY kmp_set_library
|
|
|
|
|
#define FTN_GET_LIBRARY kmp_get_library
|
|
|
|
|
#define FTN_SET_DEFAULTS kmp_set_defaults
|
|
|
|
|
#define FTN_SET_AFFINITY kmp_set_affinity
|
|
|
|
|
#define FTN_GET_AFFINITY kmp_get_affinity
|
|
|
|
|
#define FTN_GET_AFFINITY_MAX_PROC kmp_get_affinity_max_proc
|
|
|
|
|
#define FTN_CREATE_AFFINITY_MASK kmp_create_affinity_mask
|
|
|
|
|
#define FTN_DESTROY_AFFINITY_MASK kmp_destroy_affinity_mask
|
|
|
|
|
#define FTN_SET_AFFINITY_MASK_PROC kmp_set_affinity_mask_proc
|
|
|
|
|
#define FTN_UNSET_AFFINITY_MASK_PROC kmp_unset_affinity_mask_proc
|
|
|
|
|
#define FTN_GET_AFFINITY_MASK_PROC kmp_get_affinity_mask_proc
|
|
|
|
|
|
|
|
|
|
#define FTN_MALLOC kmp_malloc
|
|
|
|
|
#define FTN_CALLOC kmp_calloc
|
|
|
|
|
#define FTN_REALLOC kmp_realloc
|
|
|
|
|
#define FTN_FREE kmp_free
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_NUM_KNOWN_THREADS kmp_get_num_known_threads
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_NUM_THREADS omp_set_num_threads
|
|
|
|
|
#define FTN_GET_NUM_THREADS omp_get_num_threads
|
|
|
|
|
#define FTN_GET_MAX_THREADS omp_get_max_threads
|
|
|
|
|
#define FTN_GET_THREAD_NUM omp_get_thread_num
|
|
|
|
|
#define FTN_GET_NUM_PROCS omp_get_num_procs
|
|
|
|
|
#define FTN_SET_DYNAMIC omp_set_dynamic
|
|
|
|
|
#define FTN_GET_DYNAMIC omp_get_dynamic
|
|
|
|
|
#define FTN_SET_NESTED omp_set_nested
|
|
|
|
|
#define FTN_GET_NESTED omp_get_nested
|
|
|
|
|
#define FTN_IN_PARALLEL omp_in_parallel
|
|
|
|
|
#define FTN_GET_THREAD_LIMIT omp_get_thread_limit
|
|
|
|
|
#define FTN_SET_SCHEDULE omp_set_schedule
|
|
|
|
|
#define FTN_GET_SCHEDULE omp_get_schedule
|
|
|
|
|
#define FTN_SET_MAX_ACTIVE_LEVELS omp_set_max_active_levels
|
|
|
|
|
#define FTN_GET_MAX_ACTIVE_LEVELS omp_get_max_active_levels
|
|
|
|
|
#define FTN_GET_ACTIVE_LEVEL omp_get_active_level
|
|
|
|
|
#define FTN_GET_LEVEL omp_get_level
|
|
|
|
|
#define FTN_GET_ANCESTOR_THREAD_NUM omp_get_ancestor_thread_num
|
|
|
|
|
#define FTN_GET_TEAM_SIZE omp_get_team_size
|
|
|
|
|
#define FTN_IN_FINAL omp_in_final
|
|
|
|
|
// #define FTN_SET_PROC_BIND omp_set_proc_bind
|
|
|
|
|
#define FTN_GET_PROC_BIND omp_get_proc_bind
|
|
|
|
|
// #define FTN_CURR_PROC_BIND omp_curr_proc_bind
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_NUM_TEAMS omp_get_num_teams
|
|
|
|
|
#define FTN_GET_TEAM_NUM omp_get_team_num
|
|
|
|
|
#endif
|
|
|
|
|
#define FTN_INIT_LOCK omp_init_lock
|
|
|
|
|
#define FTN_DESTROY_LOCK omp_destroy_lock
|
|
|
|
|
#define FTN_SET_LOCK omp_set_lock
|
|
|
|
|
#define FTN_UNSET_LOCK omp_unset_lock
|
|
|
|
|
#define FTN_TEST_LOCK omp_test_lock
|
|
|
|
|
#define FTN_INIT_NEST_LOCK omp_init_nest_lock
|
|
|
|
|
#define FTN_DESTROY_NEST_LOCK omp_destroy_nest_lock
|
|
|
|
|
#define FTN_SET_NEST_LOCK omp_set_nest_lock
|
|
|
|
|
#define FTN_UNSET_NEST_LOCK omp_unset_nest_lock
|
|
|
|
|
#define FTN_TEST_NEST_LOCK omp_test_nest_lock
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_WARNINGS_ON kmp_set_warnings_on
|
|
|
|
|
#define FTN_SET_WARNINGS_OFF kmp_set_warnings_off
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_WTIME omp_get_wtime
|
|
|
|
|
#define FTN_GET_WTICK omp_get_wtick
|
|
|
|
|
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#if KMP_MIC || KMP_OS_DARWIN
|
|
|
|
|
#define FTN_GET_DEFAULT_DEVICE omp_get_default_device
|
|
|
|
|
#define FTN_SET_DEFAULT_DEVICE omp_set_default_device
|
|
|
|
|
#define FTN_GET_NUM_DEVICES omp_get_num_devices
|
|
|
|
|
#endif
|
|
|
|
|
#endif
|
|
|
|
|
|
2013-12-24 01:28:57 +08:00
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_CANCELLATION omp_get_cancellation
|
|
|
|
|
#define FTN_GET_CANCELLATION_STATUS kmp_get_cancellation_status
|
|
|
|
|
#endif
|
|
|
|
|
|
2013-09-27 18:38:44 +08:00
|
|
|
#endif /* KMP_FTN_PLAIN */
|
|
|
|
|
|
|
|
|
|
/* ------------------------------------------------------------------------ */
|
|
|
|
|
|
|
|
|
|
#if KMP_FTN_ENTRIES == KMP_FTN_APPEND
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_STACKSIZE kmp_set_stacksize_
|
|
|
|
|
#define FTN_SET_STACKSIZE_S kmp_set_stacksize_s_
|
|
|
|
|
#define FTN_GET_STACKSIZE kmp_get_stacksize_
|
|
|
|
|
#define FTN_GET_STACKSIZE_S kmp_get_stacksize_s_
|
|
|
|
|
#define FTN_SET_BLOCKTIME kmp_set_blocktime_
|
|
|
|
|
#define FTN_GET_BLOCKTIME kmp_get_blocktime_
|
|
|
|
|
#define FTN_SET_LIBRARY_SERIAL kmp_set_library_serial_
|
|
|
|
|
#define FTN_SET_LIBRARY_TURNAROUND kmp_set_library_turnaround_
|
|
|
|
|
#define FTN_SET_LIBRARY_THROUGHPUT kmp_set_library_throughput_
|
|
|
|
|
#define FTN_SET_LIBRARY kmp_set_library_
|
|
|
|
|
#define FTN_GET_LIBRARY kmp_get_library_
|
|
|
|
|
#define FTN_SET_DEFAULTS kmp_set_defaults_
|
|
|
|
|
#define FTN_SET_AFFINITY kmp_set_affinity_
|
|
|
|
|
#define FTN_GET_AFFINITY kmp_get_affinity_
|
|
|
|
|
#define FTN_GET_AFFINITY_MAX_PROC kmp_get_affinity_max_proc_
|
|
|
|
|
#define FTN_CREATE_AFFINITY_MASK kmp_create_affinity_mask_
|
|
|
|
|
#define FTN_DESTROY_AFFINITY_MASK kmp_destroy_affinity_mask_
|
|
|
|
|
#define FTN_SET_AFFINITY_MASK_PROC kmp_set_affinity_mask_proc_
|
|
|
|
|
#define FTN_UNSET_AFFINITY_MASK_PROC kmp_unset_affinity_mask_proc_
|
|
|
|
|
#define FTN_GET_AFFINITY_MASK_PROC kmp_get_affinity_mask_proc_
|
|
|
|
|
|
|
|
|
|
#define FTN_MALLOC kmp_malloc_
|
|
|
|
|
#define FTN_CALLOC kmp_calloc_
|
|
|
|
|
#define FTN_REALLOC kmp_realloc_
|
|
|
|
|
#define FTN_FREE kmp_free_
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_NUM_KNOWN_THREADS kmp_get_num_known_threads_
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_NUM_THREADS omp_set_num_threads_
|
|
|
|
|
#define FTN_GET_NUM_THREADS omp_get_num_threads_
|
|
|
|
|
#define FTN_GET_MAX_THREADS omp_get_max_threads_
|
|
|
|
|
#define FTN_GET_THREAD_NUM omp_get_thread_num_
|
|
|
|
|
#define FTN_GET_NUM_PROCS omp_get_num_procs_
|
|
|
|
|
#define FTN_SET_DYNAMIC omp_set_dynamic_
|
|
|
|
|
#define FTN_GET_DYNAMIC omp_get_dynamic_
|
|
|
|
|
#define FTN_SET_NESTED omp_set_nested_
|
|
|
|
|
#define FTN_GET_NESTED omp_get_nested_
|
|
|
|
|
#define FTN_IN_PARALLEL omp_in_parallel_
|
|
|
|
|
#define FTN_GET_THREAD_LIMIT omp_get_thread_limit_
|
|
|
|
|
#define FTN_SET_SCHEDULE omp_set_schedule_
|
|
|
|
|
#define FTN_GET_SCHEDULE omp_get_schedule_
|
|
|
|
|
#define FTN_SET_MAX_ACTIVE_LEVELS omp_set_max_active_levels_
|
|
|
|
|
#define FTN_GET_MAX_ACTIVE_LEVELS omp_get_max_active_levels_
|
|
|
|
|
#define FTN_GET_ACTIVE_LEVEL omp_get_active_level_
|
|
|
|
|
#define FTN_GET_LEVEL omp_get_level_
|
|
|
|
|
#define FTN_GET_ANCESTOR_THREAD_NUM omp_get_ancestor_thread_num_
|
|
|
|
|
#define FTN_GET_TEAM_SIZE omp_get_team_size_
|
|
|
|
|
#define FTN_IN_FINAL omp_in_final_
|
|
|
|
|
// #define FTN_SET_PROC_BIND omp_set_proc_bind_
|
|
|
|
|
#define FTN_GET_PROC_BIND omp_get_proc_bind_
|
|
|
|
|
// #define FTN_CURR_PROC_BIND omp_curr_proc_bind_
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_NUM_TEAMS omp_get_num_teams_
|
|
|
|
|
#define FTN_GET_TEAM_NUM omp_get_team_num_
|
|
|
|
|
#endif
|
|
|
|
|
#define FTN_INIT_LOCK omp_init_lock_
|
|
|
|
|
#define FTN_DESTROY_LOCK omp_destroy_lock_
|
|
|
|
|
#define FTN_SET_LOCK omp_set_lock_
|
|
|
|
|
#define FTN_UNSET_LOCK omp_unset_lock_
|
|
|
|
|
#define FTN_TEST_LOCK omp_test_lock_
|
|
|
|
|
#define FTN_INIT_NEST_LOCK omp_init_nest_lock_
|
|
|
|
|
#define FTN_DESTROY_NEST_LOCK omp_destroy_nest_lock_
|
|
|
|
|
#define FTN_SET_NEST_LOCK omp_set_nest_lock_
|
|
|
|
|
#define FTN_UNSET_NEST_LOCK omp_unset_nest_lock_
|
|
|
|
|
#define FTN_TEST_NEST_LOCK omp_test_nest_lock_
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_WARNINGS_ON kmp_set_warnings_on_
|
|
|
|
|
#define FTN_SET_WARNINGS_OFF kmp_set_warnings_off_
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_WTIME omp_get_wtime_
|
|
|
|
|
#define FTN_GET_WTICK omp_get_wtick_
|
|
|
|
|
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#if KMP_MIC || KMP_OS_DARWIN
|
|
|
|
|
#define FTN_GET_DEFAULT_DEVICE omp_get_default_device_
|
|
|
|
|
#define FTN_SET_DEFAULT_DEVICE omp_set_default_device_
|
|
|
|
|
#define FTN_GET_NUM_DEVICES omp_get_num_devices_
|
|
|
|
|
#endif
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
|
2013-12-24 01:28:57 +08:00
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_CANCELLATION omp_get_cancellation_
|
|
|
|
|
#define FTN_GET_CANCELLATION_STATUS kmp_get_cancellation_status_
|
|
|
|
|
#endif
|
|
|
|
|
|
2013-09-27 18:38:44 +08:00
|
|
|
#endif /* KMP_FTN_APPEND */
|
|
|
|
|
|
|
|
|
|
/* ------------------------------------------------------------------------ */
|
|
|
|
|
|
|
|
|
|
#if KMP_FTN_ENTRIES == KMP_FTN_UPPER
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_STACKSIZE KMP_SET_STACKSIZE
|
|
|
|
|
#define FTN_SET_STACKSIZE_S KMP_SET_STACKSIZE_S
|
|
|
|
|
#define FTN_GET_STACKSIZE KMP_GET_STACKSIZE
|
|
|
|
|
#define FTN_GET_STACKSIZE_S KMP_GET_STACKSIZE_S
|
|
|
|
|
#define FTN_SET_BLOCKTIME KMP_SET_BLOCKTIME
|
|
|
|
|
#define FTN_GET_BLOCKTIME KMP_GET_BLOCKTIME
|
|
|
|
|
#define FTN_SET_LIBRARY_SERIAL KMP_SET_LIBRARY_SERIAL
|
|
|
|
|
#define FTN_SET_LIBRARY_TURNAROUND KMP_SET_LIBRARY_TURNAROUND
|
|
|
|
|
#define FTN_SET_LIBRARY_THROUGHPUT KMP_SET_LIBRARY_THROUGHPUT
|
|
|
|
|
#define FTN_SET_LIBRARY KMP_SET_LIBRARY
|
|
|
|
|
#define FTN_GET_LIBRARY KMP_GET_LIBRARY
|
|
|
|
|
#define FTN_SET_DEFAULTS KMP_SET_DEFAULTS
|
|
|
|
|
#define FTN_SET_AFFINITY KMP_SET_AFFINITY
|
|
|
|
|
#define FTN_GET_AFFINITY KMP_GET_AFFINITY
|
|
|
|
|
#define FTN_GET_AFFINITY_MAX_PROC KMP_GET_AFFINITY_MAX_PROC
|
|
|
|
|
#define FTN_CREATE_AFFINITY_MASK KMP_CREATE_AFFINITY_MASK
|
|
|
|
|
#define FTN_DESTROY_AFFINITY_MASK KMP_DESTROY_AFFINITY_MASK
|
|
|
|
|
#define FTN_SET_AFFINITY_MASK_PROC KMP_SET_AFFINITY_MASK_PROC
|
|
|
|
|
#define FTN_UNSET_AFFINITY_MASK_PROC KMP_UNSET_AFFINITY_MASK_PROC
|
|
|
|
|
#define FTN_GET_AFFINITY_MASK_PROC KMP_GET_AFFINITY_MASK_PROC
|
|
|
|
|
|
|
|
|
|
#define FTN_MALLOC KMP_MALLOC
|
|
|
|
|
#define FTN_CALLOC KMP_CALLOC
|
|
|
|
|
#define FTN_REALLOC KMP_REALLOC
|
|
|
|
|
#define FTN_FREE KMP_FREE
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_NUM_KNOWN_THREADS KMP_GET_NUM_KNOWN_THREADS
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_NUM_THREADS OMP_SET_NUM_THREADS
|
|
|
|
|
#define FTN_GET_NUM_THREADS OMP_GET_NUM_THREADS
|
|
|
|
|
#define FTN_GET_MAX_THREADS OMP_GET_MAX_THREADS
|
|
|
|
|
#define FTN_GET_THREAD_NUM OMP_GET_THREAD_NUM
|
|
|
|
|
#define FTN_GET_NUM_PROCS OMP_GET_NUM_PROCS
|
|
|
|
|
#define FTN_SET_DYNAMIC OMP_SET_DYNAMIC
|
|
|
|
|
#define FTN_GET_DYNAMIC OMP_GET_DYNAMIC
|
|
|
|
|
#define FTN_SET_NESTED OMP_SET_NESTED
|
|
|
|
|
#define FTN_GET_NESTED OMP_GET_NESTED
|
|
|
|
|
#define FTN_IN_PARALLEL OMP_IN_PARALLEL
|
|
|
|
|
#define FTN_GET_THREAD_LIMIT OMP_GET_THREAD_LIMIT
|
|
|
|
|
#define FTN_SET_SCHEDULE OMP_SET_SCHEDULE
|
|
|
|
|
#define FTN_GET_SCHEDULE OMP_GET_SCHEDULE
|
|
|
|
|
#define FTN_SET_MAX_ACTIVE_LEVELS OMP_SET_MAX_ACTIVE_LEVELS
|
|
|
|
|
#define FTN_GET_MAX_ACTIVE_LEVELS OMP_GET_MAX_ACTIVE_LEVELS
|
|
|
|
|
#define FTN_GET_ACTIVE_LEVEL OMP_GET_ACTIVE_LEVEL
|
|
|
|
|
#define FTN_GET_LEVEL OMP_GET_LEVEL
|
|
|
|
|
#define FTN_GET_ANCESTOR_THREAD_NUM OMP_GET_ANCESTOR_THREAD_NUM
|
|
|
|
|
#define FTN_GET_TEAM_SIZE OMP_GET_TEAM_SIZE
|
|
|
|
|
#define FTN_IN_FINAL OMP_IN_FINAL
|
|
|
|
|
// #define FTN_SET_PROC_BIND OMP_SET_PROC_BIND
|
|
|
|
|
#define FTN_GET_PROC_BIND OMP_GET_PROC_BIND
|
|
|
|
|
// #define FTN_CURR_PROC_BIND OMP_CURR_PROC_BIND
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_NUM_TEAMS OMP_GET_NUM_TEAMS
|
|
|
|
|
#define FTN_GET_TEAM_NUM OMP_GET_TEAM_NUM
|
|
|
|
|
#endif
|
|
|
|
|
#define FTN_INIT_LOCK OMP_INIT_LOCK
|
|
|
|
|
#define FTN_DESTROY_LOCK OMP_DESTROY_LOCK
|
|
|
|
|
#define FTN_SET_LOCK OMP_SET_LOCK
|
|
|
|
|
#define FTN_UNSET_LOCK OMP_UNSET_LOCK
|
|
|
|
|
#define FTN_TEST_LOCK OMP_TEST_LOCK
|
|
|
|
|
#define FTN_INIT_NEST_LOCK OMP_INIT_NEST_LOCK
|
|
|
|
|
#define FTN_DESTROY_NEST_LOCK OMP_DESTROY_NEST_LOCK
|
|
|
|
|
#define FTN_SET_NEST_LOCK OMP_SET_NEST_LOCK
|
|
|
|
|
#define FTN_UNSET_NEST_LOCK OMP_UNSET_NEST_LOCK
|
|
|
|
|
#define FTN_TEST_NEST_LOCK OMP_TEST_NEST_LOCK
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_WARNINGS_ON KMP_SET_WARNINGS_ON
|
|
|
|
|
#define FTN_SET_WARNINGS_OFF KMP_SET_WARNINGS_OFF
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_WTIME OMP_GET_WTIME
|
|
|
|
|
#define FTN_GET_WTICK OMP_GET_WTICK
|
|
|
|
|
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#if KMP_MIC || KMP_OS_DARWIN
|
|
|
|
|
#define FTN_GET_DEFAULT_DEVICE OMP_GET_DEFAULT_DEVICE
|
|
|
|
|
#define FTN_SET_DEFAULT_DEVICE OMP_SET_DEFAULT_DEVICE
|
|
|
|
|
#define FTN_GET_NUM_DEVICES OMP_GET_NUM_DEVICES
|
|
|
|
|
#endif
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
|
2013-12-24 01:28:57 +08:00
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_CANCELLATION OMP_GET_CANCELLATION
|
|
|
|
|
#define FTN_GET_CANCELLATION_STATUS KMP_GET_CANCELLATION_STATUS
|
|
|
|
|
#endif
|
|
|
|
|
|
2013-09-27 18:38:44 +08:00
|
|
|
#endif /* KMP_FTN_UPPER */
|
|
|
|
|
|
|
|
|
|
/* ------------------------------------------------------------------------ */
|
|
|
|
|
|
|
|
|
|
#if KMP_FTN_ENTRIES == KMP_FTN_UAPPEND
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_STACKSIZE KMP_SET_STACKSIZE_
|
|
|
|
|
#define FTN_SET_STACKSIZE_S KMP_SET_STACKSIZE_S_
|
|
|
|
|
#define FTN_GET_STACKSIZE KMP_GET_STACKSIZE_
|
|
|
|
|
#define FTN_GET_STACKSIZE_S KMP_GET_STACKSIZE_S_
|
|
|
|
|
#define FTN_SET_BLOCKTIME KMP_SET_BLOCKTIME_
|
|
|
|
|
#define FTN_GET_BLOCKTIME KMP_GET_BLOCKTIME_
|
|
|
|
|
#define FTN_SET_LIBRARY_SERIAL KMP_SET_LIBRARY_SERIAL_
|
|
|
|
|
#define FTN_SET_LIBRARY_TURNAROUND KMP_SET_LIBRARY_TURNAROUND_
|
|
|
|
|
#define FTN_SET_LIBRARY_THROUGHPUT KMP_SET_LIBRARY_THROUGHPUT_
|
|
|
|
|
#define FTN_SET_LIBRARY KMP_SET_LIBRARY_
|
|
|
|
|
#define FTN_GET_LIBRARY KMP_GET_LIBRARY_
|
|
|
|
|
#define FTN_SET_DEFAULTS KMP_SET_DEFAULTS_
|
|
|
|
|
#define FTN_SET_AFFINITY KMP_SET_AFFINITY_
|
|
|
|
|
#define FTN_GET_AFFINITY KMP_GET_AFFINITY_
|
|
|
|
|
#define FTN_GET_AFFINITY_MAX_PROC KMP_GET_AFFINITY_MAX_PROC_
|
|
|
|
|
#define FTN_CREATE_AFFINITY_MASK KMP_CREATE_AFFINITY_MASK_
|
|
|
|
|
#define FTN_DESTROY_AFFINITY_MASK KMP_DESTROY_AFFINITY_MASK_
|
|
|
|
|
#define FTN_SET_AFFINITY_MASK_PROC KMP_SET_AFFINITY_MASK_PROC_
|
|
|
|
|
#define FTN_UNSET_AFFINITY_MASK_PROC KMP_UNSET_AFFINITY_MASK_PROC_
|
|
|
|
|
#define FTN_GET_AFFINITY_MASK_PROC KMP_GET_AFFINITY_MASK_PROC_
|
|
|
|
|
|
|
|
|
|
#define FTN_MALLOC KMP_MALLOC_
|
|
|
|
|
#define FTN_CALLOC KMP_CALLOC_
|
|
|
|
|
#define FTN_REALLOC KMP_REALLOC_
|
|
|
|
|
#define FTN_FREE KMP_FREE_
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_NUM_KNOWN_THREADS KMP_GET_NUM_KNOWN_THREADS_
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_NUM_THREADS OMP_SET_NUM_THREADS_
|
|
|
|
|
#define FTN_GET_NUM_THREADS OMP_GET_NUM_THREADS_
|
|
|
|
|
#define FTN_GET_MAX_THREADS OMP_GET_MAX_THREADS_
|
|
|
|
|
#define FTN_GET_THREAD_NUM OMP_GET_THREAD_NUM_
|
|
|
|
|
#define FTN_GET_NUM_PROCS OMP_GET_NUM_PROCS_
|
|
|
|
|
#define FTN_SET_DYNAMIC OMP_SET_DYNAMIC_
|
|
|
|
|
#define FTN_GET_DYNAMIC OMP_GET_DYNAMIC_
|
|
|
|
|
#define FTN_SET_NESTED OMP_SET_NESTED_
|
|
|
|
|
#define FTN_GET_NESTED OMP_GET_NESTED_
|
|
|
|
|
#define FTN_IN_PARALLEL OMP_IN_PARALLEL_
|
|
|
|
|
#define FTN_GET_THREAD_LIMIT OMP_GET_THREAD_LIMIT_
|
|
|
|
|
#define FTN_SET_SCHEDULE OMP_SET_SCHEDULE_
|
|
|
|
|
#define FTN_GET_SCHEDULE OMP_GET_SCHEDULE_
|
|
|
|
|
#define FTN_SET_MAX_ACTIVE_LEVELS OMP_SET_MAX_ACTIVE_LEVELS_
|
|
|
|
|
#define FTN_GET_MAX_ACTIVE_LEVELS OMP_GET_MAX_ACTIVE_LEVELS_
|
|
|
|
|
#define FTN_GET_ACTIVE_LEVEL OMP_GET_ACTIVE_LEVEL_
|
|
|
|
|
#define FTN_GET_LEVEL OMP_GET_LEVEL_
|
|
|
|
|
#define FTN_GET_ANCESTOR_THREAD_NUM OMP_GET_ANCESTOR_THREAD_NUM_
|
|
|
|
|
#define FTN_GET_TEAM_SIZE OMP_GET_TEAM_SIZE_
|
|
|
|
|
#define FTN_IN_FINAL OMP_IN_FINAL_
|
|
|
|
|
// #define FTN_SET_PROC_BIND OMP_SET_PROC_BIND_
|
|
|
|
|
#define FTN_GET_PROC_BIND OMP_GET_PROC_BIND_
|
|
|
|
|
// #define FTN_CURR_PROC_BIND OMP_CURR_PROC_BIND_
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_NUM_TEAMS OMP_GET_NUM_TEAMS_
|
|
|
|
|
#define FTN_GET_TEAM_NUM OMP_GET_TEAM_NUM_
|
|
|
|
|
#endif
|
|
|
|
|
#define FTN_INIT_LOCK OMP_INIT_LOCK_
|
|
|
|
|
#define FTN_DESTROY_LOCK OMP_DESTROY_LOCK_
|
|
|
|
|
#define FTN_SET_LOCK OMP_SET_LOCK_
|
|
|
|
|
#define FTN_UNSET_LOCK OMP_UNSET_LOCK_
|
|
|
|
|
#define FTN_TEST_LOCK OMP_TEST_LOCK_
|
|
|
|
|
#define FTN_INIT_NEST_LOCK OMP_INIT_NEST_LOCK_
|
|
|
|
|
#define FTN_DESTROY_NEST_LOCK OMP_DESTROY_NEST_LOCK_
|
|
|
|
|
#define FTN_SET_NEST_LOCK OMP_SET_NEST_LOCK_
|
|
|
|
|
#define FTN_UNSET_NEST_LOCK OMP_UNSET_NEST_LOCK_
|
|
|
|
|
#define FTN_TEST_NEST_LOCK OMP_TEST_NEST_LOCK_
|
|
|
|
|
|
|
|
|
|
#define FTN_SET_WARNINGS_ON KMP_SET_WARNINGS_ON_
|
|
|
|
|
#define FTN_SET_WARNINGS_OFF KMP_SET_WARNINGS_OFF_
|
|
|
|
|
|
|
|
|
|
#define FTN_GET_WTIME OMP_GET_WTIME_
|
|
|
|
|
#define FTN_GET_WTICK OMP_GET_WTICK_
|
|
|
|
|
|
|
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#if KMP_MIC || KMP_OS_DARWIN
|
|
|
|
|
#define FTN_GET_DEFAULT_DEVICE OMP_GET_DEFAULT_DEVICE_
|
|
|
|
|
#define FTN_SET_DEFAULT_DEVICE OMP_SET_DEFAULT_DEVICE_
|
|
|
|
|
#define FTN_GET_NUM_DEVICES OMP_GET_NUM_DEVICES_
|
|
|
|
|
#endif
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
|
2013-12-24 01:28:57 +08:00
|
|
|
#if OMP_40_ENABLED
|
|
|
|
|
#define FTN_GET_CANCELLATION OMP_GET_CANCELLATION_
|
|
|
|
|
#define FTN_GET_CANCELLATION_STATUS KMP_GET_CANCELLATION_STATUS_
|
|
|
|
|
#endif
|
|
|
|
|
|
2013-09-27 18:38:44 +08:00
|
|
|
#endif /* KMP_FTN_UAPPEND */
|
|
|
|
|
|
2013-12-24 01:28:57 +08:00
|
|
|
/* ------------------------------------------------------------------ */
|
|
|
|
|
/* -------------------------- GOMP API NAMES ------------------------ */
|
|
|
|
|
// All GOMP_1.0 symbols
|
|
|
|
|
#define KMP_API_NAME_GOMP_ATOMIC_END GOMP_atomic_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_ATOMIC_START GOMP_atomic_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_BARRIER GOMP_barrier
|
|
|
|
|
#define KMP_API_NAME_GOMP_CRITICAL_END GOMP_critical_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_CRITICAL_NAME_END GOMP_critical_name_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_CRITICAL_NAME_START GOMP_critical_name_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_CRITICAL_START GOMP_critical_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_DYNAMIC_NEXT GOMP_loop_dynamic_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_DYNAMIC_START GOMP_loop_dynamic_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_END GOMP_loop_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_END_NOWAIT GOMP_loop_end_nowait
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_GUIDED_NEXT GOMP_loop_guided_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_GUIDED_START GOMP_loop_guided_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_DYNAMIC_NEXT GOMP_loop_ordered_dynamic_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_DYNAMIC_START GOMP_loop_ordered_dynamic_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_GUIDED_NEXT GOMP_loop_ordered_guided_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_GUIDED_START GOMP_loop_ordered_guided_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_RUNTIME_NEXT GOMP_loop_ordered_runtime_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_RUNTIME_START GOMP_loop_ordered_runtime_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_STATIC_NEXT GOMP_loop_ordered_static_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ORDERED_STATIC_START GOMP_loop_ordered_static_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_RUNTIME_NEXT GOMP_loop_runtime_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_RUNTIME_START GOMP_loop_runtime_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_STATIC_NEXT GOMP_loop_static_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_STATIC_START GOMP_loop_static_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_ORDERED_END GOMP_ordered_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_ORDERED_START GOMP_ordered_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_END GOMP_parallel_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_DYNAMIC_START GOMP_parallel_loop_dynamic_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_GUIDED_START GOMP_parallel_loop_guided_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_RUNTIME_START GOMP_parallel_loop_runtime_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_STATIC_START GOMP_parallel_loop_static_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_SECTIONS_START GOMP_parallel_sections_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_START GOMP_parallel_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_SECTIONS_END GOMP_sections_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_SECTIONS_END_NOWAIT GOMP_sections_end_nowait
|
|
|
|
|
#define KMP_API_NAME_GOMP_SECTIONS_NEXT GOMP_sections_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_SECTIONS_START GOMP_sections_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_SINGLE_COPY_END GOMP_single_copy_end
|
|
|
|
|
#define KMP_API_NAME_GOMP_SINGLE_COPY_START GOMP_single_copy_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_SINGLE_START GOMP_single_start
|
|
|
|
|
|
|
|
|
|
// All GOMP_2.0 symbols
|
|
|
|
|
#define KMP_API_NAME_GOMP_TASK GOMP_task
|
|
|
|
|
#define KMP_API_NAME_GOMP_TASKWAIT GOMP_taskwait
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_DYNAMIC_NEXT GOMP_loop_ull_dynamic_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_DYNAMIC_START GOMP_loop_ull_dynamic_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_GUIDED_NEXT GOMP_loop_ull_guided_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_GUIDED_START GOMP_loop_ull_guided_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_DYNAMIC_NEXT GOMP_loop_ull_ordered_dynamic_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_DYNAMIC_START GOMP_loop_ull_ordered_dynamic_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_GUIDED_NEXT GOMP_loop_ull_ordered_guided_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_GUIDED_START GOMP_loop_ull_ordered_guided_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT GOMP_loop_ull_ordered_runtime_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_RUNTIME_START GOMP_loop_ull_ordered_runtime_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_STATIC_NEXT GOMP_loop_ull_ordered_static_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_ORDERED_STATIC_START GOMP_loop_ull_ordered_static_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_RUNTIME_NEXT GOMP_loop_ull_runtime_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_RUNTIME_START GOMP_loop_ull_runtime_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_STATIC_NEXT GOMP_loop_ull_static_next
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_ULL_STATIC_START GOMP_loop_ull_static_start
|
|
|
|
|
|
|
|
|
|
// All GOMP_3.0 symbols
|
|
|
|
|
#define KMP_API_NAME_GOMP_TASKYIELD GOMP_taskyield
|
|
|
|
|
|
|
|
|
|
// All GOMP_4.0 symbols
|
|
|
|
|
// TODO: As of 2013-10-14, none of the GOMP_4.0 functions are implemented in libiomp5
|
|
|
|
|
#define KMP_API_NAME_GOMP_BARRIER_CANCEL GOMP_barrier_cancel
|
|
|
|
|
#define KMP_API_NAME_GOMP_CANCEL GOMP_cancel
|
|
|
|
|
#define KMP_API_NAME_GOMP_CANCELLATION_POINT GOMP_cancellation_point
|
|
|
|
|
#define KMP_API_NAME_GOMP_LOOP_END_CANCEL GOMP_loop_end_cancel
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_DYNAMIC GOMP_parallel_loop_dynamic
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_GUIDED GOMP_parallel_loop_guided
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_RUNTIME GOMP_parallel_loop_runtime
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_LOOP_STATIC GOMP_parallel_loop_static
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL_SECTIONS GOMP_parallel_sections
|
|
|
|
|
#define KMP_API_NAME_GOMP_PARALLEL GOMP_parallel
|
|
|
|
|
#define KMP_API_NAME_GOMP_SECTIONS_END_CANCEL GOMP_sections_end_cancel
|
|
|
|
|
#define KMP_API_NAME_GOMP_TASKGROUP_START GOMP_taskgroup_start
|
|
|
|
|
#define KMP_API_NAME_GOMP_TASKGROUP_END GOMP_taskgroup_end
|
|
|
|
|
/* Target functions should be taken care of by liboffload */
|
I apologise in advance for the size of this check-in. At Intel we do
understand that this is not friendly, and are working to change our
internal code-development to make it easier to make development
features available more frequently and in finer (more functional)
chunks. Unfortunately we haven't got that in place yet, and unpicking
this into multiple separate check-ins would be non-trivial, so please
bear with me on this one. We should be better in the future.
Apologies over, what do we have here?
GGC 4.9 compatibility
--------------------
* We have implemented the new entrypoints used by code compiled by GCC
4.9 to implement the same functionality in gcc 4.8. Therefore code
compiled with gcc 4.9 that used to work will continue to do so.
However, there are some other new entrypoints (associated with task
cancellation) which are not implemented. Therefore user code compiled
by gcc 4.9 that uses these new features will not link against the LLVM
runtime. (It remains unclear how to handle those entrypoints, since
the GCC interface has potentially unpleasant performance implications
for join barriers even when cancellation is not used)
--- new parallel entry points ---
new entry points that aren't OpenMP 4.0 related
These are implemented fully :-
GOMP_parallel_loop_dynamic()
GOMP_parallel_loop_guided()
GOMP_parallel_loop_runtime()
GOMP_parallel_loop_static()
GOMP_parallel_sections()
GOMP_parallel()
--- cancellation entry points ---
Currently, these only give a runtime error if OMP_CANCELLATION is true
because our plain barriers don't check for cancellation while waiting
GOMP_barrier_cancel()
GOMP_cancel()
GOMP_cancellation_point()
GOMP_loop_end_cancel()
GOMP_sections_end_cancel()
--- taskgroup entry points ---
These are implemented fully.
GOMP_taskgroup_start()
GOMP_taskgroup_end()
--- target entry points ---
These are empty (as they are in libgomp)
GOMP_target()
GOMP_target_data()
GOMP_target_end_data()
GOMP_target_update()
GOMP_teams()
Improvements in Barriers and Fork/Join
--------------------------------------
* Barrier and fork/join code is now in its own file (which makes it
easier to understand and modify).
* Wait/release code is now templated and in its own file; suspend/resume code is also templated
* There's a new, hierarchical, barrier, which exploits the
cache-hierarchy of the Intel(r) Xeon Phi(tm) coprocessor to improve
fork/join and barrier performance.
***BEWARE*** the new source files have *not* been added to the legacy
Cmake build system. If you want to use that fixes wil be required.
Statistics Collection Code
--------------------------
* New code has been added to collect application statistics (if this
is enabled at library compile time; by default it is not). The
statistics code itself is generally useful, the lightweight timing
code uses the X86 rdtsc instruction, so will require changes for other
architectures.
The intent of this code is not for users to tune their codes but
rather
1) For timing code-paths inside the runtime
2) For gathering general properties of OpenMP codes to focus attention
on which OpenMP features are most used.
Nested Hot Teams
----------------
* The runtime now maintains more state to reduce the overhead of
creating and destroying inner parallel teams. This improves the
performance of code that repeatedly uses nested parallelism with the
same resource allocation. Set the new KMP_HOT_TEAMS_MAX_LEVEL
envirable to a depth to enable this (and, of course, OMP_NESTED=true
to enable nested parallelism at all).
Improved Intel(r) VTune(Tm) Amplifier support
---------------------------------------------
* The runtime provides additional information to Vtune via the
itt_notify interface to allow it to display better OpenMP specific
analyses of load-imbalance.
Support for OpenMP Composite Statements
---------------------------------------
* Implement new entrypoints required by some of the OpenMP 4.1
composite statements.
Improved ifdefs
---------------
* More separation of concepts ("Does this platform do X?") from
platforms ("Are we compiling for platform Y?"), which should simplify
future porting.
ScaleMP* contribution
---------------------
Stack padding to improve the performance in their environment where
cross-node coherency is managed at the page level.
Redesign of wait and release code
---------------------------------
The code is simplified and performance improved.
Bug Fixes
---------
*Fixes for Windows multiple processor groups.
*Fix Fortran module build on Linux: offload attribute added.
*Fix entry names for distribute-parallel-loop construct to be consistent with the compiler codegen.
*Fix an inconsistent error message for KMP_PLACE_THREADS environment variable.
llvm-svn: 219214
2014-10-08 00:25:50 +08:00
|
|
|
#define KMP_API_NAME_GOMP_TARGET GOMP_target
|
|
|
|
|
#define KMP_API_NAME_GOMP_TARGET_DATA GOMP_target_data
|
|
|
|
|
#define KMP_API_NAME_GOMP_TARGET_END_DATA GOMP_target_end_data
|
|
|
|
|
#define KMP_API_NAME_GOMP_TARGET_UPDATE GOMP_target_update
|
2013-12-24 01:28:57 +08:00
|
|
|
#define KMP_API_NAME_GOMP_TEAMS GOMP_teams
|
|
|
|
|
|
I apologise in advance for the size of this check-in. At Intel we do
understand that this is not friendly, and are working to change our
internal code-development to make it easier to make development
features available more frequently and in finer (more functional)
chunks. Unfortunately we haven't got that in place yet, and unpicking
this into multiple separate check-ins would be non-trivial, so please
bear with me on this one. We should be better in the future.
Apologies over, what do we have here?
GGC 4.9 compatibility
--------------------
* We have implemented the new entrypoints used by code compiled by GCC
4.9 to implement the same functionality in gcc 4.8. Therefore code
compiled with gcc 4.9 that used to work will continue to do so.
However, there are some other new entrypoints (associated with task
cancellation) which are not implemented. Therefore user code compiled
by gcc 4.9 that uses these new features will not link against the LLVM
runtime. (It remains unclear how to handle those entrypoints, since
the GCC interface has potentially unpleasant performance implications
for join barriers even when cancellation is not used)
--- new parallel entry points ---
new entry points that aren't OpenMP 4.0 related
These are implemented fully :-
GOMP_parallel_loop_dynamic()
GOMP_parallel_loop_guided()
GOMP_parallel_loop_runtime()
GOMP_parallel_loop_static()
GOMP_parallel_sections()
GOMP_parallel()
--- cancellation entry points ---
Currently, these only give a runtime error if OMP_CANCELLATION is true
because our plain barriers don't check for cancellation while waiting
GOMP_barrier_cancel()
GOMP_cancel()
GOMP_cancellation_point()
GOMP_loop_end_cancel()
GOMP_sections_end_cancel()
--- taskgroup entry points ---
These are implemented fully.
GOMP_taskgroup_start()
GOMP_taskgroup_end()
--- target entry points ---
These are empty (as they are in libgomp)
GOMP_target()
GOMP_target_data()
GOMP_target_end_data()
GOMP_target_update()
GOMP_teams()
Improvements in Barriers and Fork/Join
--------------------------------------
* Barrier and fork/join code is now in its own file (which makes it
easier to understand and modify).
* Wait/release code is now templated and in its own file; suspend/resume code is also templated
* There's a new, hierarchical, barrier, which exploits the
cache-hierarchy of the Intel(r) Xeon Phi(tm) coprocessor to improve
fork/join and barrier performance.
***BEWARE*** the new source files have *not* been added to the legacy
Cmake build system. If you want to use that fixes wil be required.
Statistics Collection Code
--------------------------
* New code has been added to collect application statistics (if this
is enabled at library compile time; by default it is not). The
statistics code itself is generally useful, the lightweight timing
code uses the X86 rdtsc instruction, so will require changes for other
architectures.
The intent of this code is not for users to tune their codes but
rather
1) For timing code-paths inside the runtime
2) For gathering general properties of OpenMP codes to focus attention
on which OpenMP features are most used.
Nested Hot Teams
----------------
* The runtime now maintains more state to reduce the overhead of
creating and destroying inner parallel teams. This improves the
performance of code that repeatedly uses nested parallelism with the
same resource allocation. Set the new KMP_HOT_TEAMS_MAX_LEVEL
envirable to a depth to enable this (and, of course, OMP_NESTED=true
to enable nested parallelism at all).
Improved Intel(r) VTune(Tm) Amplifier support
---------------------------------------------
* The runtime provides additional information to Vtune via the
itt_notify interface to allow it to display better OpenMP specific
analyses of load-imbalance.
Support for OpenMP Composite Statements
---------------------------------------
* Implement new entrypoints required by some of the OpenMP 4.1
composite statements.
Improved ifdefs
---------------
* More separation of concepts ("Does this platform do X?") from
platforms ("Are we compiling for platform Y?"), which should simplify
future porting.
ScaleMP* contribution
---------------------
Stack padding to improve the performance in their environment where
cross-node coherency is managed at the page level.
Redesign of wait and release code
---------------------------------
The code is simplified and performance improved.
Bug Fixes
---------
*Fixes for Windows multiple processor groups.
*Fix Fortran module build on Linux: offload attribute added.
*Fix entry names for distribute-parallel-loop construct to be consistent with the compiler codegen.
*Fix an inconsistent error message for KMP_PLACE_THREADS environment variable.
llvm-svn: 219214
2014-10-08 00:25:50 +08:00
|
|
|
#ifdef KMP_USE_VERSION_SYMBOLS
|
|
|
|
|
#define xstr(x) str(x)
|
2013-12-24 01:28:57 +08:00
|
|
|
#define str(x) #x
|
|
|
|
|
|
|
|
|
|
// If Linux, xexpand prepends __kmp_api_ to the real API name
|
|
|
|
|
#define xexpand(api_name) expand(api_name)
|
|
|
|
|
#define expand(api_name) __kmp_api_##api_name
|
|
|
|
|
|
|
|
|
|
#define xaliasify(api_name,ver) aliasify(api_name,ver)
|
|
|
|
|
#define aliasify(api_name,ver) __typeof__(__kmp_api_##api_name) __kmp_api_##api_name##_##ver##_alias __attribute__((alias(xstr(__kmp_api_##api_name))))
|
|
|
|
|
|
|
|
|
|
#define xversionify(api_name, version_num, version_str) versionify(api_name, version_num, version_str, "VERSION")
|
|
|
|
|
#define versionify(api_name, version_num, version_str, default_ver) \
|
|
|
|
|
__asm__(".symver " xstr(__kmp_api_##api_name##_##version_num##_alias) "," xstr(api_name) "@" version_str "\n\t"); \
|
|
|
|
|
__asm__(".symver " xstr(__kmp_api_##api_name) "," xstr(api_name) "@@" default_ver "\n\t")
|
|
|
|
|
|
I apologise in advance for the size of this check-in. At Intel we do
understand that this is not friendly, and are working to change our
internal code-development to make it easier to make development
features available more frequently and in finer (more functional)
chunks. Unfortunately we haven't got that in place yet, and unpicking
this into multiple separate check-ins would be non-trivial, so please
bear with me on this one. We should be better in the future.
Apologies over, what do we have here?
GGC 4.9 compatibility
--------------------
* We have implemented the new entrypoints used by code compiled by GCC
4.9 to implement the same functionality in gcc 4.8. Therefore code
compiled with gcc 4.9 that used to work will continue to do so.
However, there are some other new entrypoints (associated with task
cancellation) which are not implemented. Therefore user code compiled
by gcc 4.9 that uses these new features will not link against the LLVM
runtime. (It remains unclear how to handle those entrypoints, since
the GCC interface has potentially unpleasant performance implications
for join barriers even when cancellation is not used)
--- new parallel entry points ---
new entry points that aren't OpenMP 4.0 related
These are implemented fully :-
GOMP_parallel_loop_dynamic()
GOMP_parallel_loop_guided()
GOMP_parallel_loop_runtime()
GOMP_parallel_loop_static()
GOMP_parallel_sections()
GOMP_parallel()
--- cancellation entry points ---
Currently, these only give a runtime error if OMP_CANCELLATION is true
because our plain barriers don't check for cancellation while waiting
GOMP_barrier_cancel()
GOMP_cancel()
GOMP_cancellation_point()
GOMP_loop_end_cancel()
GOMP_sections_end_cancel()
--- taskgroup entry points ---
These are implemented fully.
GOMP_taskgroup_start()
GOMP_taskgroup_end()
--- target entry points ---
These are empty (as they are in libgomp)
GOMP_target()
GOMP_target_data()
GOMP_target_end_data()
GOMP_target_update()
GOMP_teams()
Improvements in Barriers and Fork/Join
--------------------------------------
* Barrier and fork/join code is now in its own file (which makes it
easier to understand and modify).
* Wait/release code is now templated and in its own file; suspend/resume code is also templated
* There's a new, hierarchical, barrier, which exploits the
cache-hierarchy of the Intel(r) Xeon Phi(tm) coprocessor to improve
fork/join and barrier performance.
***BEWARE*** the new source files have *not* been added to the legacy
Cmake build system. If you want to use that fixes wil be required.
Statistics Collection Code
--------------------------
* New code has been added to collect application statistics (if this
is enabled at library compile time; by default it is not). The
statistics code itself is generally useful, the lightweight timing
code uses the X86 rdtsc instruction, so will require changes for other
architectures.
The intent of this code is not for users to tune their codes but
rather
1) For timing code-paths inside the runtime
2) For gathering general properties of OpenMP codes to focus attention
on which OpenMP features are most used.
Nested Hot Teams
----------------
* The runtime now maintains more state to reduce the overhead of
creating and destroying inner parallel teams. This improves the
performance of code that repeatedly uses nested parallelism with the
same resource allocation. Set the new KMP_HOT_TEAMS_MAX_LEVEL
envirable to a depth to enable this (and, of course, OMP_NESTED=true
to enable nested parallelism at all).
Improved Intel(r) VTune(Tm) Amplifier support
---------------------------------------------
* The runtime provides additional information to Vtune via the
itt_notify interface to allow it to display better OpenMP specific
analyses of load-imbalance.
Support for OpenMP Composite Statements
---------------------------------------
* Implement new entrypoints required by some of the OpenMP 4.1
composite statements.
Improved ifdefs
---------------
* More separation of concepts ("Does this platform do X?") from
platforms ("Are we compiling for platform Y?"), which should simplify
future porting.
ScaleMP* contribution
---------------------
Stack padding to improve the performance in their environment where
cross-node coherency is managed at the page level.
Redesign of wait and release code
---------------------------------
The code is simplified and performance improved.
Bug Fixes
---------
*Fixes for Windows multiple processor groups.
*Fix Fortran module build on Linux: offload attribute added.
*Fix entry names for distribute-parallel-loop construct to be consistent with the compiler codegen.
*Fix an inconsistent error message for KMP_PLACE_THREADS environment variable.
llvm-svn: 219214
2014-10-08 00:25:50 +08:00
|
|
|
#else // KMP_USE_VERSION_SYMBOLS
|
2013-12-24 01:28:57 +08:00
|
|
|
#define xstr(x) /* Nothing */
|
|
|
|
|
#define str(x) /* Nothing */
|
|
|
|
|
|
|
|
|
|
// if Windows or Mac, xexpand does no name transformation
|
|
|
|
|
#define xexpand(api_name) expand(api_name)
|
|
|
|
|
#define expand(api_name) api_name
|
|
|
|
|
|
|
|
|
|
#define xaliasify(api_name,ver) /* Nothing */
|
|
|
|
|
#define aliasify(api_name,ver) /* Nothing */
|
|
|
|
|
|
|
|
|
|
#define xversionify(api_name, version_num, version_str) /* Nothing */
|
|
|
|
|
#define versionify(api_name, version_num, version_str, default_ver) /* Nothing */
|
|
|
|
|
|
I apologise in advance for the size of this check-in. At Intel we do
understand that this is not friendly, and are working to change our
internal code-development to make it easier to make development
features available more frequently and in finer (more functional)
chunks. Unfortunately we haven't got that in place yet, and unpicking
this into multiple separate check-ins would be non-trivial, so please
bear with me on this one. We should be better in the future.
Apologies over, what do we have here?
GGC 4.9 compatibility
--------------------
* We have implemented the new entrypoints used by code compiled by GCC
4.9 to implement the same functionality in gcc 4.8. Therefore code
compiled with gcc 4.9 that used to work will continue to do so.
However, there are some other new entrypoints (associated with task
cancellation) which are not implemented. Therefore user code compiled
by gcc 4.9 that uses these new features will not link against the LLVM
runtime. (It remains unclear how to handle those entrypoints, since
the GCC interface has potentially unpleasant performance implications
for join barriers even when cancellation is not used)
--- new parallel entry points ---
new entry points that aren't OpenMP 4.0 related
These are implemented fully :-
GOMP_parallel_loop_dynamic()
GOMP_parallel_loop_guided()
GOMP_parallel_loop_runtime()
GOMP_parallel_loop_static()
GOMP_parallel_sections()
GOMP_parallel()
--- cancellation entry points ---
Currently, these only give a runtime error if OMP_CANCELLATION is true
because our plain barriers don't check for cancellation while waiting
GOMP_barrier_cancel()
GOMP_cancel()
GOMP_cancellation_point()
GOMP_loop_end_cancel()
GOMP_sections_end_cancel()
--- taskgroup entry points ---
These are implemented fully.
GOMP_taskgroup_start()
GOMP_taskgroup_end()
--- target entry points ---
These are empty (as they are in libgomp)
GOMP_target()
GOMP_target_data()
GOMP_target_end_data()
GOMP_target_update()
GOMP_teams()
Improvements in Barriers and Fork/Join
--------------------------------------
* Barrier and fork/join code is now in its own file (which makes it
easier to understand and modify).
* Wait/release code is now templated and in its own file; suspend/resume code is also templated
* There's a new, hierarchical, barrier, which exploits the
cache-hierarchy of the Intel(r) Xeon Phi(tm) coprocessor to improve
fork/join and barrier performance.
***BEWARE*** the new source files have *not* been added to the legacy
Cmake build system. If you want to use that fixes wil be required.
Statistics Collection Code
--------------------------
* New code has been added to collect application statistics (if this
is enabled at library compile time; by default it is not). The
statistics code itself is generally useful, the lightweight timing
code uses the X86 rdtsc instruction, so will require changes for other
architectures.
The intent of this code is not for users to tune their codes but
rather
1) For timing code-paths inside the runtime
2) For gathering general properties of OpenMP codes to focus attention
on which OpenMP features are most used.
Nested Hot Teams
----------------
* The runtime now maintains more state to reduce the overhead of
creating and destroying inner parallel teams. This improves the
performance of code that repeatedly uses nested parallelism with the
same resource allocation. Set the new KMP_HOT_TEAMS_MAX_LEVEL
envirable to a depth to enable this (and, of course, OMP_NESTED=true
to enable nested parallelism at all).
Improved Intel(r) VTune(Tm) Amplifier support
---------------------------------------------
* The runtime provides additional information to Vtune via the
itt_notify interface to allow it to display better OpenMP specific
analyses of load-imbalance.
Support for OpenMP Composite Statements
---------------------------------------
* Implement new entrypoints required by some of the OpenMP 4.1
composite statements.
Improved ifdefs
---------------
* More separation of concepts ("Does this platform do X?") from
platforms ("Are we compiling for platform Y?"), which should simplify
future porting.
ScaleMP* contribution
---------------------
Stack padding to improve the performance in their environment where
cross-node coherency is managed at the page level.
Redesign of wait and release code
---------------------------------
The code is simplified and performance improved.
Bug Fixes
---------
*Fixes for Windows multiple processor groups.
*Fix Fortran module build on Linux: offload attribute added.
*Fix entry names for distribute-parallel-loop construct to be consistent with the compiler codegen.
*Fix an inconsistent error message for KMP_PLACE_THREADS environment variable.
llvm-svn: 219214
2014-10-08 00:25:50 +08:00
|
|
|
#endif // KMP_USE_VERSION_SYMBOLS
|
2013-12-24 01:28:57 +08:00
|
|
|
|
2013-09-27 18:38:44 +08:00
|
|
|
#endif /* KMP_FTN_OS_H */
|
|
|
|
|
|