Commit Graph

902 Commits

Author SHA1 Message Date
Chung-Lin Tang
1f4c5b9bb2 2019-05-13 Chung-Lin Tang <cltang@codesourcery.com>
Reviewed-by: Thomas Schwinge <thomas@codesourcery.com>

	libgomp/
	* libgomp-plugin.h (struct goacc_asyncqueue): Declare.
	(struct goacc_asyncqueue_list): Likewise.
	(goacc_aq): Likewise.
	(goacc_aq_list): Likewise.
	(GOMP_OFFLOAD_openacc_register_async_cleanup): Remove.
	(GOMP_OFFLOAD_openacc_async_test): Remove.
	(GOMP_OFFLOAD_openacc_async_test_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_async): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all_async): Remove.
	(GOMP_OFFLOAD_openacc_async_set_async): Remove.
	(GOMP_OFFLOAD_openacc_exec): Adjust declaration.
	(GOMP_OFFLOAD_openacc_cuda_get_stream): Likewise.
	(GOMP_OFFLOAD_openacc_cuda_set_stream): Likewise.
	(GOMP_OFFLOAD_openacc_async_exec): Declare.
	(GOMP_OFFLOAD_openacc_async_construct): Declare.
	(GOMP_OFFLOAD_openacc_async_destruct): Declare.
	(GOMP_OFFLOAD_openacc_async_test): Declare.
	(GOMP_OFFLOAD_openacc_async_synchronize): Declare.
	(GOMP_OFFLOAD_openacc_async_serialize): Declare.
	(GOMP_OFFLOAD_openacc_async_queue_callback): Declare.
	(GOMP_OFFLOAD_openacc_async_host2dev): Declare.
	(GOMP_OFFLOAD_openacc_async_dev2host): Declare.

	* libgomp.h (struct acc_dispatch_t): Define 'async' sub-struct.
	(gomp_acc_insert_pointer): Adjust declaration.
	(gomp_copy_host2dev): New declaration.
	(gomp_copy_dev2host): Likewise.
	(gomp_map_vars_async): Likewise.
	(gomp_unmap_tgt): Likewise.
	(gomp_unmap_vars_async): Likewise.
	(gomp_fini_device): Likewise.

	* oacc-async.c (get_goacc_thread): New function.
	(get_goacc_thread_device): New function.
	(lookup_goacc_asyncqueue): New function.
	(get_goacc_asyncqueue): New function.
	(acc_async_test): Adjust code to use new async design.
	(acc_async_test_all): Likewise.
	(acc_wait): Likewise.
	(acc_wait_async): Likewise.
	(acc_wait_all): Likewise.
	(acc_wait_all_async): Likewise.
	(goacc_async_free): New function.
	(goacc_init_asyncqueues): Likewise.
	(goacc_fini_asyncqueues): Likewise.
	* oacc-cuda.c (acc_get_cuda_stream): Adjust code to use new async
	design.
	(acc_set_cuda_stream): Likewise.
	* oacc-host.c (host_openacc_exec): Adjust parameters, remove 'async'.
	(host_openacc_register_async_cleanup): Remove.
	(host_openacc_async_exec): New function.
	(host_openacc_async_test): Adjust parameters.
	(host_openacc_async_test_all): Remove.
	(host_openacc_async_wait): Remove.
	(host_openacc_async_wait_async): Remove.
	(host_openacc_async_wait_all): Remove.
	(host_openacc_async_wait_all_async): Remove.
	(host_openacc_async_set_async): Remove.
	(host_openacc_async_synchronize): New function.
	(host_openacc_async_serialize): New function.
	(host_openacc_async_host2dev): New function.
	(host_openacc_async_dev2host): New function.
	(host_openacc_async_queue_callback): New function.
	(host_openacc_async_construct): New function.
	(host_openacc_async_destruct): New function.
	(struct gomp_device_descr host_dispatch): Remove initialization of old
	interface, add intialization of new async sub-struct.
	* oacc-init.c (acc_shutdown_1): Adjust to use gomp_fini_device.
	(goacc_attach_host_thread_to_device): Remove old async code usage.
	* oacc-int.h (goacc_init_asyncqueues): New declaration.
	(goacc_fini_asyncqueues): Likewise.
	(goacc_async_copyout_unmap_vars): Likewise.
	(goacc_async_free): Likewise.
	(get_goacc_asyncqueue): Likewise.
	(lookup_goacc_asyncqueue): Likewise.

	* oacc-mem.c (memcpy_tofrom_device): Adjust code to use new async
	design.
	(present_create_copy): Adjust code to use new async design.
	(delete_copyout): Likewise.
	(update_dev_host): Likewise.
	(gomp_acc_insert_pointer): Add async parameter, adjust code to use new
	async design.
	(gomp_acc_remove_pointer): Adjust code to use new async design.
	* oacc-parallel.c (GOACC_parallel_keyed): Adjust code to use new async
	design.
	(GOACC_enter_exit_data): Likewise.
	(goacc_wait): Likewise.
	(GOACC_update): Likewise.
	* oacc-plugin.c (GOMP_PLUGIN_async_unmap_vars): Change to assert fail
	when called, warn as obsolete in comment.

	* target.c (goacc_device_copy_async): New function.
	(gomp_copy_host2dev): Remove 'static', add goacc_asyncqueue parameter,
	add goacc_device_copy_async case.
	(gomp_copy_dev2host): Likewise.
	(gomp_map_vars_existing): Add goacc_asyncqueue parameter, adjust code.
	(gomp_map_pointer): Likewise.
	(gomp_map_fields_existing): Likewise.
	(gomp_map_vars_internal): New always_inline function, renamed from
	gomp_map_vars.
	(gomp_map_vars): Implement by calling gomp_map_vars_internal.
	(gomp_map_vars_async): Implement by calling gomp_map_vars_internal,
	passing goacc_asyncqueue argument.
	(gomp_unmap_tgt): Remove static, add attribute_hidden.
	(gomp_unref_tgt): New function.
	(gomp_unmap_vars_internal): New always_inline function, renamed from
	gomp_unmap_vars.
	(gomp_unmap_vars): Implement by calling gomp_unmap_vars_internal.
	(gomp_unmap_vars_async): Implement by calling
	gomp_unmap_vars_internal, passing goacc_asyncqueue argument.
	(gomp_fini_device): New function.
	(gomp_exit_data): Adjust gomp_copy_dev2host call.
	(gomp_load_plugin_for_device): Remove old interface, adjust to load
	new async interface.
	(gomp_target_fini): Adjust code to call gomp_fini_device.

	* plugin/plugin-nvptx.c (struct cuda_map): Remove.
	(struct ptx_stream): Remove.
	(struct nvptx_thread): Remove current_stream field.
	(cuda_map_create): Remove.
	(cuda_map_destroy): Remove.
	(map_init): Remove.
	(map_fini): Remove.
	(map_pop): Remove.
	(map_push): Remove.
	(struct goacc_asyncqueue): Define.
	(struct nvptx_callback): Define.
	(struct ptx_free_block): Define.
	(struct ptx_device): Remove null_stream, active_streams, async_streams,
	stream_lock, and next fields.
	(enum ptx_event_type): Remove.
	(struct ptx_event): Remove.
	(ptx_event_lock): Remove.
	(ptx_events): Remove.
	(init_streams_for_device): Remove.
	(fini_streams_for_device): Remove.
	(select_stream_for_async): Remove.
	(nvptx_init): Remove ptx_events and ptx_event_lock references.
	(nvptx_attach_host_thread_to_device): Remove CUDA_ERROR_NOT_PERMITTED
	case.
	(nvptx_open_device): Add free_blocks initialization, remove
	init_streams_for_device call.
	(nvptx_close_device): Remove fini_streams_for_device call, add
	free_blocks destruct code.
	(event_gc): Remove.
	(event_add): Remove.
	(nvptx_exec): Adjust parameters and code.
	(nvptx_free): Likewise.
	(nvptx_host2dev): Remove.
	(nvptx_dev2host): Remove.
	(nvptx_set_async): Remove.
	(nvptx_async_test): Remove.
	(nvptx_async_test_all): Remove.
	(nvptx_wait): Remove.
	(nvptx_wait_async): Remove.
	(nvptx_wait_all): Remove.
	(nvptx_wait_all_async): Remove.
	(nvptx_get_cuda_stream): Remove.
	(nvptx_set_cuda_stream): Remove.
	(GOMP_OFFLOAD_alloc): Adjust code.
	(GOMP_OFFLOAD_free): Likewise.
	(GOMP_OFFLOAD_openacc_register_async_cleanup): Remove.
	(GOMP_OFFLOAD_openacc_exec): Adjust parameters and code.
	(GOMP_OFFLOAD_openacc_async_test_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_async): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all_async): Remove.
	(GOMP_OFFLOAD_openacc_async_set_async): Remove.
	(cuda_free_argmem): New function.
	(GOMP_OFFLOAD_openacc_async_exec): New plugin hook function.
	(GOMP_OFFLOAD_openacc_create_thread_data): Adjust code.
	(GOMP_OFFLOAD_openacc_cuda_get_stream): Adjust code.
	(GOMP_OFFLOAD_openacc_cuda_set_stream): Adjust code.
	(GOMP_OFFLOAD_openacc_async_construct): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_destruct): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_test): Remove and re-implement.
	(GOMP_OFFLOAD_openacc_async_synchronize): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_serialize): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_queue_callback): New plugin hook function.
	(cuda_callback_wrapper): New function.
	(cuda_memcpy_sanity_check): New function.
	(GOMP_OFFLOAD_host2dev): Remove and re-implement.
	(GOMP_OFFLOAD_dev2host): Remove and re-implement.
	(GOMP_OFFLOAD_openacc_async_host2dev): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_dev2host): New plugin hook function.

From-SVN: r271128
2019-05-13 13:32:00 +00:00
Thomas Schwinge
da2d30c199 Address compiler diagnostics in libgomp.oacc-c-c++-common/pr87835.c
source-gcc/libgomp/testsuite/libgomp.oacc-c-c++-common/pr87835.c: In function 'main':
    source-gcc/libgomp/testsuite/libgomp.oacc-c-c++-common/pr87835.c:45: warning: ignoring #pragma loop gang [-Wunknown-pragmas]
       45 |     #pragma loop gang
          |
    source-gcc/libgomp/testsuite/libgomp.oacc-c-c++-common/pr87835.c:19:7: warning: unused variable 'b' [-Wunused-variable]
       19 |   int b[n];
          |       ^

	libgomp/
	PR target/87835
	* testsuite/libgomp.oacc-c-c++-common/pr87835.c: Update.

From-SVN: r271004
2019-05-08 12:01:30 +02:00
Thomas Schwinge
2bbbfa4e28 Clean up libgomp GCC 5 legacy support
libgomp/
	* oacc-parallel.c: Add comments to legacy entry points (GCC 5).

From-SVN: r270901
2019-05-06 10:49:55 +02:00
Kevin Buettner
bbf1efe1b4 team.c (gomp_team_start): Initialize pool->threads[0].
libgomp/ChangeLog:

	* team.c (gomp_team_start): Initialize pool->threads[0].

From-SVN: r269971
2019-03-27 18:30:44 +00:00
Thomas Schwinge
b03d721a62 [libgomp] In OpenACC testing, by default only build for the offload target that we're actually going to test
... to avoid compilation overhead, and to keep simple '-foffload=[...]'
handling in test cases.

	libgomp/
	* testsuite/libgomp.oacc-c++/c++.exp: Specify
	"-foffload=$offload_target".
	* testsuite/libgomp.oacc-c/c.exp: Likewise.
	* testsuite/libgomp.oacc-fortran/fortran.exp: Likewise.
	* testsuite/lib/libgomp.exp
	(check_effective_target_openacc_nvidia_accel_configured): Remove,
	as (conceptually) merged into
	check_effective_target_openacc_nvidia_accel_selected.  Adjust all
	users.

From-SVN: r269109
2019-02-22 11:51:35 +01:00
Thomas Schwinge
0a0384b43a [libgomp] In OpenACC testing, cycle though all offload targets
... instead of through offload plugins.

	libgomp/
	* plugin/configfrag.ac: Populate and AC_SUBST offload_targets.
	* testsuite/libgomp-test-support.exp.in: Adjust.
	* testsuite/lib/libgomp.exp: Likewise.  Don't populate
	openacc_device_types_s.
	(offload_target_to_openacc_device_type): New proc.
	* testsuite/libgomp.oacc-c++/c++.exp: Adjust.
	* testsuite/libgomp.oacc-c/c.exp: Likewise.
	* testsuite/libgomp.oacc-fortran/fortran.exp: Likewise.
	* Makefile.in: Regenerate.
	* configure: Likewise.
	* testsuite/Makefile.in: Likewise.

From-SVN: r269108
2019-02-22 11:51:20 +01:00
Thomas Schwinge
ee332b4a9a [libgomp] Clarify difference between offload target, offload plugin, and OpenACC device type
libgomp/
	* plugin/configfrag.ac: Populate and AC_SUBST offload_plugins
	instead of offload_targets, and AC_DEFINE_UNQUOTED OFFLOAD_PLUGINS
	instead of OFFLOAD_TARGETS.
	* target.c (gomp_target_init): Adjust.
	* testsuite/libgomp-test-support.exp.in: Likewise.
	* testsuite/lib/libgomp.exp: Likewise.  Populate
	openacc_device_types_s instead of offload_targets_s_openacc.
	(check_effective_target_openacc_nvidia_accel_selected)
	(check_effective_target_openacc_host_selected): Adjust.
	* testsuite/libgomp.oacc-c++/c++.exp: Likewise.
	* testsuite/libgomp.oacc-c/c.exp: Likewise.
	* testsuite/libgomp.oacc-fortran/fortran.exp: Likewise.
	* Makefile.in: Regenerate.
	* config.h.in: Likewise.
	* configure: Likewise.
	* testsuite/Makefile.in: Likewise.

From-SVN: r269107
2019-02-22 11:51:05 +01:00
Thomas Schwinge
1241136c71 [libgomp] In OpenACC offloading testing, be more explicit in what is supported, and what is not, or why not
libgomp/
	* testsuite/lib/libgomp.exp: Error out for unknown offload target.
	* testsuite/libgomp.oacc-c++/c++.exp: Likewise.  Report if
	"offloading: supported, but hardware not accessible".
	* testsuite/libgomp.oacc-c/c.exp: Likewise.
	* testsuite/libgomp.oacc-fortran/fortran.exp: Likewise.

From-SVN: r269106
2019-02-22 11:50:49 +01:00
Chung-Lin Tang
19695f4d99 re PR c/87924 (OpenACC wait clauses without async-arguments)
2019-02-19  Chung-Lin Tang <cltang@codesourcery.com>

	PR c/87924
	gcc/c/
	* c-parser.c (c_parser_oacc_clause_wait): Add representation of wait
	clause without argument as 'wait (GOMP_ASYNC_NOVAL)', adjust comments.

	gcc/cp/
	* parser.c (cp_parser_oacc_clause_wait): Add representation of wait
	clause without argument as 'wait (GOMP_ASYNC_NOVAL)', adjust comments.

	gcc/fortran/
	* openmp.c (gfc_match_omp_clauses): Add representation of wait clause
	without argument as 'wait (GOMP_ASYNC_NOVAL)'.

	libgomp/
	* oacc-parallel.c (GOACC_parallel_keyed): Remove condition on call to
	goacc_wait().
	(goacc_wait): Handle ACC_ASYNC_NOVAL case, remove goacc_thread() call
	and related adjustment.

	Reviewed-by: Thomas Schwinge  <thomas@codesourcery.com>

From-SVN: r269016
2019-02-19 14:10:15 +00:00
Jakub Jelinek
8b44f8ec4b re PR c++/88988 (ICE: Segmentation fault (in lookup_name_real_1))
PR c++/88988
	* lambda.c (is_capture_proxy): Don't return true for
	DECL_OMP_PRIVATIZED_MEMBER artificial vars.

	* testsuite/libgomp.c++/pr88988.C: New test.

From-SVN: r268407
2019-01-31 00:28:53 +01:00
Jakub Jelinek
52bfbb69e7 re PR middle-end/89002 (ICE in scan_omp_1_op, at omp-low.c:3166)
PR middle-end/89002
	* gimplify.c (gimplify_omp_for): When adding OMP_CLAUSE_*_GIMPLE_SEQ
	for lastprivate/linear IV, push gimplify context around gimplify_assign
	and, if it needed any temporaries, pop it into a gimple bind around the
	sequence.

	* testsuite/libgomp.c/pr89002.c: New test.

From-SVN: r268346
2019-01-28 23:34:32 +01:00
Jakub Jelinek
be3a87e7b5 re PR middle-end/89002 (ICE in scan_omp_1_op, at omp-low.c:3166)
PR middle-end/89002
	* gimplify.c (gimplify_omp_for): When adding OMP_CLAUSE_*_GIMPLE_SEQ
	for lastprivate/linear IV, push gimplify context around gimplify_assign
	and, if it needed any temporaries, pop it into a gimple bind around the
	sequence.

	* testsuite/libgomp.c/pr89002.c: New test.

From-SVN: r268345
2019-01-28 23:33:33 +01:00
Richard Biener
497ef4d7f5 re PR testsuite/89064 (libgomp.graphite/force-parallel-5.c fails starting with r268257)
2019-01-28  Richard Biener  <rguenther@suse.de>

	PR testsuite/89064
	PR tree-optimization/86865
	* testsuite/libgomp.graphite/force-parallel-5.c: XFAIL.

From-SVN: r268333
2019-01-28 09:07:30 +00:00
Tom de Vries
738c56d410 [nvptx, libgomp] Fix memleak in GOMP_OFFLOAD_fini_device
I wrote a test-case:
...
int
main (void)
{
  for (unsigned i = 0; i < 128; ++i)
    {
      acc_init (acc_device_nvidia);
      acc_shutdown (acc_device_nvidia);
    }

  return 0;
}
...
and ran it under valgrind.  The only leak location reported with a frequency
of 128, was the allocation of ptx_devices in nvptx_init.

Fix this by freeing ptx_devices in GOMP_OFFLOAD_fini_device, once
instantiated_devices drops to 0.

2019-01-24  Tom de Vries  <tdevries@suse.de>

	* plugin/plugin-nvptx.c (GOMP_OFFLOAD_fini_device): Free ptx_devices
	once instantiated_devices drops to 0.

From-SVN: r268237
2019-01-24 14:12:19 +00:00
Tom de Vries
4a75460b00 [nvptx, libgomp] Fix cuMemAlloc with size zero
Consider test-case:
...
int
main (void)
{
  #pragma acc parallel async
  ;
  #pragma acc parallel async
  ;
  #pragma acc wait

  return 0;
}
...

This fails with:
...
libgomp: cuMemAlloc error: invalid argument
Segmentation fault (core dumped)
...
The cuMemAlloc error is due to the fact that we're try to allocate 0 bytes.

Fix this by preventing calling map_push with size zero argument in nvptx_exec.

This also has the consequence that for the abort-1.c test-case, we end up
calling cuMemFree during map_fini for the struct cuda_map allocated in
map_init, which fails because an abort happened.  Fix this by calling
cuMemFree with CUDA_CALL_NOCHECK in cuda_map_destroy.

2019-01-23  Tom de Vries  <tdevries@suse.de>

	PR target/PR88946
	* plugin/plugin-nvptx.c (cuda_map_destroy): Use CUDA_CALL_NOCHECK for
	cuMemFree.
	(nvptx_exec): Don't call map_push if mapnum == 0.
	* testsuite/libgomp.oacc-c-c++-common/pr88946.c: New test.

From-SVN: r268178
2019-01-23 08:16:56 +00:00
Tom de Vries
4fef8e4d8c [nvptx, libgomp] Fix assert (!s->map->active) in map_fini
There are currently two situations where this assert triggers:
...
libgomp/plugin/plugin-nvptx.c: map_fini: Assertion `!s->map->active' failed.
...

First, in abort-1.c, a parallel region triggering an abort:
...
int
main (void)
{
  #pragma acc parallel
  abort ();

  return 0;
}
...

The abort is detected in nvptx_exec as the CUDA_ERROR_ILLEGAL_INSTRUCTION
return status of the cuStreamSynchronize call after kernel launch, which is
then handled by calling non-returning function GOMP_PLUGIN_fatal.
Consequently, the map_pop in nvptx_exec that in case of cuStreamSynchronize
success would remove or inactive the element added by the map_push earlier in
nvptx_exec, does not trigger.  With the element no longer active, but still
marked active and a member of s->map,  we run into the assert during
GOMP_OFFLOAD_fini_device, which is triggered from atexit handler
gomp_target_fini (which is triggered by the GOMP_PLUGIN_fatal mentioned above
calling exit).

Second, in pr88941.c, an async parallel region without wait:
...
int
main (void)
{
  #pragma acc parallel async
  ;

  /* no #pragma acc wait */
  return 0;
}
...

Because nvptx_exec is handling an async region, it does not call map_pop for
the element added by map_push, but schedules an kernel execution completion
event to call map_pop.  Again, we run into the assert during
GOMP_OFFLOAD_fini_device, which is triggered from atexit handler
gomp_target_fini, but the exit in this case is triggered by returning from main.
So either the kernel is still running, or the kernel has completed but the
corresponding event that is supposed to call map_pop is stuck in the event
queue, waiting for an event_gc.

Fix this by removing the assert, and skipping the freeing of device memory if
the map is still marked active (though in the async case, this is more a
workaround than an fix).

2019-01-23  Tom de Vries  <tdevries@suse.de>

	PR target/88941
	PR target/88939
	* plugin/plugin-nvptx.c (cuda_map_destroy): Handle map->active case.
	(map_fini): Remove "assert (!s->map->active)".
	* testsuite/libgomp.oacc-c-c++-common/pr88941.c: New test.

From-SVN: r268177
2019-01-23 08:16:42 +00:00
Tom de Vries
2ee6cb22c1 [nvptx, libgomp] Fix map_push
The map field of a struct ptx_stream is a FIFO.  The FIFO is implemented as a
single linked list, with pop-from-the-front semantics.

The function map_pop pops an element, either by:
- deallocating the element, if there is more than one element
- or marking the element inactive, if there's only one element

The responsibility of map_push is to push an element to the back, as well as
selecting the element to push, by:
- allocating an element, or
- reusing the element at the front if inactive and big enough, or
- dropping the element at the front if inactive and not big enough, and
  allocating one that's big enough

The current implemention gets at least the first and most basic scenario wrong:

> map = cuda_map_create (size);

We create an element, and assign it to map.

> for (t = s->map; t->next != NULL; t = t->next)
>   ;

We determine the last element in the fifo.

> t->next = map;

We append the new element.

> s->map = map;

But here, we throw away the rest of the FIFO, and declare the FIFO to be just
the new element.

This problem causes the test-case asyncwait-1.c to fail intermittently on some
systems.  The pr87835.c test-case added here is a a minimized and modified
version of asyncwait-1.c (avoiding the kernel construct) that is more likely to
fail.

Fix this by rewriting map_pop more robustly, by:
- seperating the function in two phases: select element, push element
- when reusing or dropping an element, making sure that the element is cleanly
  popped from the queue
- rewriting the push element part in such a way that it can handle all cases
  without needing if statements, such that each line is exercised for each of
  the three cases.

2019-01-23  Tom de Vries  <tdevries@suse.de>

	PR target/87835
	* plugin/plugin-nvptx.c (map_push): Fix adding of allocated element.
	* testsuite/libgomp.oacc-c-c++-common/pr87835.c: New test.

From-SVN: r268176
2019-01-23 08:16:11 +00:00
Tom de Vries
d41d952c9b [nvptx] Handle assignment to gang-level reduction variable
2019-01-15  Tom de Vries  <tdevries@suse.de>

	PR target/80547
	* config/nvptx/nvptx.c (nvptx_goacc_reduction_init): Handle
	lhs == NULL_TREE for gang-level reduction.

	* testsuite/libgomp.oacc-c-c++-common/gang-reduction-var-assignment.c:
	New test.

From-SVN: r267934
2019-01-15 10:11:16 +00:00
Tom de Vries
efb56ae82b [nvptx] Enable setting vector length using -fopenacc-dim -- testcases
Add some test-cases that set vector length using -fopenacc-dim.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/pr85486-2.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-2.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-5.c: New test.
	* testsuite/libgomp.oacc-fortran/gemm-2.f90: New test.

From-SVN: r267897
2019-01-12 22:19:31 +00:00
Tom de Vries
2c2ff1684d [nvptx] Enable setting vector length using -fopenacc-dim
Enable setting vector length using -fopenacc-dim, f.i. -fopenacc-dim=::128.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (nvptx_goacc_validate_dims_1): Alow setting
	vector length using -fopenacc-dim.

	* plugin/plugin-nvptx.c (nvptx_exec): Update error message.

From-SVN: r267896
2019-01-12 22:19:15 +00:00
Tom de Vries
a105775825 [nvptx] Add vector_length 64 test-cases
Add some test-cases using vector_length 64.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/vector-length-64-1.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-64-2.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-64-3.c: New test.

From-SVN: r267895
2019-01-12 22:19:02 +00:00
Tom de Vries
56314b772f [nvptx] Force vl32 if calling vector-partitionable routines -- test-cases
Add test-cases for "[nvptx] Force vl32 if calling vector-partitionable
routines".

2019-01-12  Tom de Vries  <tdevries@suse.de>

	PR target/85486
	* testsuite/libgomp.oacc-c-c++-common/pr85486-3.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr85486.c: New test.

From-SVN: r267894
2019-01-12 22:18:50 +00:00
Tom de Vries
b39e4366a2 [nvptx] Don't emit barriers for empty loops -- test-cases
Add test-cases for PR85381.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	PR target/85381
	* testsuite/libgomp.oacc-c-c++-common/pr85381-5.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr85381.c: New test.

From-SVN: r267893
2019-01-12 22:18:39 +00:00
Tom de Vries
2cb7a501ab [nvptx] Enable large vectors -- reduction testcases
Add various reduction test-cases with vector length 128.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/vred2d-128.c: New test.
	* testsuite/libgomp.oacc-fortran/gemm.f90: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-10.c: New test.

From-SVN: r267892
2019-01-12 22:18:27 +00:00
Tom de Vries
8e77f71eda [nvptx] Enable large vectors -- test-cases
Add various test-cases with vector length 128.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-7.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-4.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-6.c: New test.

From-SVN: r267891
2019-01-12 22:18:11 +00:00
Tom de Vries
52d22ece49 [nvptx] Update insufficient launch message for variable vector_length
Update message in nvptx libgomp plugin about insufficient resources to launch
kernel, to accommodate for the fact the vector_length can now be variable.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	* plugin/plugin-nvptx.c (nvptx_exec): Update insufficient hardware
	resources diagnostic.

From-SVN: r267890
2019-01-12 22:18:00 +00:00
Tom de Vries
2b9d9e3937 [nvptx] Enable large vectors
Allow vector_length clauses to accept values larger than warp size.  Note that
this does not enable setting vector_length to values larger than warp size using
-fopenacc-dim.

2019-01-12  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (nvptx_goacc_validate_dims): Take larger vector
	lengths into account.

	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-1.c: Expect
	vector length to be 128.
	* testsuite/libgomp.oacc-c-c++-common/parallel-dims.c: Expect vector
	length 2097152 to be reduced to 1024 instead of 32.

From-SVN: r267889
2019-01-12 22:17:42 +00:00
Thomas Schwinge
4102bda64c Better distinguish OpenACC and OpenMP sections in libgomp.texi
2019-01-11  Thomas Schwinge  <thomas@codesourcery.com>
            James Norris  <jnorris@codesourcery.com>

	* libgomp.texi: Better distinguish OpenACC and OpenMP "Runtime
	Library Routines", and "Environment Variables".

Co-Authored-By: James Norris <jnorris@codesourcery.com>

From-SVN: r267841
2019-01-11 13:55:01 +00:00
Tom de Vries
052aaaceed [nvptx] Don't allow vector_length 64 with num_workers 16
When using a compiler build with:
...
+#define PTX_DEFAULT_VECTOR_LENGTH PTX_CTA_SIZE
...

consider a test-case:
...
int
main (void)
{
  #pragma acc parallel vector_length (64)
    #pragma acc loop worker
    for (unsigned int i = 0; i < 32; i++)
      #pragma acc loop vector
      for (unsigned int j = 0; j < 64; j++)
        ;

  return 0;
}
...

If num_workers is 16, either because:
- we add a "num_workers (16)" clause on the parallel directive, or
- we set "GOMP_OPENACC_DIM=:16:", or
- the libgomp plugin chooses 16 num_workers
we run into an illegal instruction at runtime, because a bar.sync instruction
tries to use a barrier 16.  The instruction is illegal, because ptx supports
only 16 barriers per CTA, and the valid range is 0..15.

The problem is that with a warp-multiple vector length, we use a code generation
scheme with a per-worker barrier.  And because barrier zero is reserved for
per-cta barrier, only the remaining 15 barriers can be used as per-worker
barrier, and consequently we can't use num_workers larger than 15.

This problem occurs only for vector_length 64.  For vector_length 32, we use a
different code generation scheme, and for vector_length >= 96, the maximum
num_workers is not big enough not to trigger this problem.

Also, this problem only occurs for num_workers 16.  As explained above,
num_workers 15 is safe to use, and 16 is already the maximum num_workers for
vector_length 64.

This patch fixes the problem in both the compiler (handling "num_workers (16)")
and in the libgomp nvptx plugin (with and without "GOMP_OPENACC_DIM=:16:").

2019-01-11  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (PTX_CTA_NUM_BARRIERS, PTX_PER_CTA_BARRIER)
	(PTX_NUM_PER_CTA_BARRIER, PTX_FIRST_PER_WORKER_BARRIER)
	(PTX_NUM_PER_WORKER_BARRIERS): Define.
	(nvptx_apply_dim_limits): Prevent vector_length 64 and
	num_workers 16.

	* plugin/plugin-nvptx.c (nvptx_exec): Prevent vector_length 64 and
	num_workers 16.

From-SVN: r267838
2019-01-11 11:46:43 +00:00
Tom de Vries
9390f91687 [libgomp, testsuite, openacc] Remove -foffload=-w in reduction-[1-5].c
Before the commit "[libgomp, testsuite, openacc] Don't use const int for
dimensions", the "const int" construct was used to set launch dimensions in
reductions-[1-5].c.  In the case of -xc -O0, the const int is implemented as a
variable by the C front-end.  Consequently, the nvptx back-end generated
warnings that vector_length was overridden to be hard-coded, rather than left to
be set at runtime.  The test-cases silenced these warnings by switching off all
warnings in the accelerator compiler using "-foffload=-w".

Given that no warnings occur anymore, remove the "-foffload=-w" setting.

2019-01-11  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/reduction-1.c: Remove
	-foffload=-w.
	* testsuite/libgomp.oacc-c-c++-common/reduction-2.c: Same.
	* testsuite/libgomp.oacc-c-c++-common/reduction-3.c: Same.
	* testsuite/libgomp.oacc-c-c++-common/reduction-4.c: Same.
	* testsuite/libgomp.oacc-c-c++-common/reduction-5.c: Same.

From-SVN: r267836
2019-01-11 11:46:06 +00:00
Tom de Vries
2c3e7ad20b [nvptx, testsuite, openacc, libgomp] Add insufficient-resources.c
Add a test-case that tests the "insufficient resources" fatal in the nvptx
libgomp plugin.

2019-01-11  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/insufficient-resources.c: New
	test.

From-SVN: r267835
2019-01-11 11:45:55 +00:00
Nathan Sidwell
e222497dcb Add testcase from PR71959
libgomp/

	PR lto/71959
	* testsuite/libgomp.oacc-c++/pr71959-aux.cc: New.
	* testsuite/libgomp.oacc-c++/pr71959.C: New.

Co-Authored-By: Julian Brown <julian@codesourcery.com>

From-SVN: r267806
2019-01-10 12:32:03 +00:00
Sebastian Huber
cb87fec331 libgomp: Reduce copy and paste for RTEMS
libgomp/

	* config/rtems/bar.c: Include "../linux/bar.c" and delete copy
	and paste code.

From-SVN: r267752
2019-01-09 06:16:05 +00:00
Sebastian Huber
30b4d0d0b9 libgomp: Avoid complex dependencies for RTEMS
libgomp/

	* config/rtems/affinity-fmt.c: New file.  Include affinity-fmt.c,
	undefining HAVE_GETPID and HAVE_GETHOSTNAME, and mapping fwrite to
	write.

From-SVN: r267751
2019-01-09 06:14:15 +00:00
Tom de Vries
5d0bc70ae4 [libgomp, testsuite, openacc] Don't use const int for dimensions
Const int is handled differently at -O0 for -xc and -xc++, which can cause noise
in testsuite/libgomp.oacc-c-c++-common test-cases (which are both run for c and
c++) if const int is used for launch dimensions.

Fix this by using #defines instead.

2019-01-09  Tom de Vries  <tdevries@suse.de>

	PR target/88756
	* testsuite/libgomp.oacc-c-c++-common/reduction-1.c (ng, nw, vl): Use
	#define instead of "const int".
	* testsuite/libgomp.oacc-c-c++-common/reduction-2.c (ng, nw, vl): Same.
	* testsuite/libgomp.oacc-c-c++-common/reduction-3.c (ng, nw, vl): Same.
	* testsuite/libgomp.oacc-c-c++-common/reduction-4.c (ng, nw, vl): Same.
	* testsuite/libgomp.oacc-c-c++-common/reduction-5.c (ng, nw, vl): Same.

From-SVN: r267747
2019-01-09 00:07:55 +00:00
Tom de Vries
2c372e81a9 [nvptx, libgomp] Don't launch with num_workers == 0
When using a compiler build with:
...
+#define PTX_DEFAULT_VECTOR_LENGTH PTX_CTA_SIZE
+#define PTX_MAX_VECTOR_LENGTH PTX_CTA_SIZE
...
and running the libgomp testsuite, we run into an execution failure in
parallel-loop-1.c, due to a cuda launch failure:
...
  nvptx_exec: kernel f6_none_none$_omp_fn$0: launch gangs=480, workers=0, \
    vectors=1024

libgomp: cuLaunchKernel error: invalid argument
...
because workers == 0.

The workers variable is set to 0 here in nvptx_exec:
...
                workers = blocks / actual_vectors;
...
because actual_vectors is 1024, and blocks is 768:
...
cuOccupancyMaxPotentialBlockSize: grid = 10, block = 768
...

Fix this by ensuring that workers is at least one.

2019-01-09  Tom de Vries  <tdevries@suse.de>

	* plugin/plugin-nvptx.c (nvptx_exec): Make sure to launch with at least
	one worker.

From-SVN: r267746
2019-01-09 00:07:45 +00:00
Tom de Vries
43493c97a6 [nvptx] Fix libgomp.oacc-c-c++-common/vector-length-128-3.c
The vector-length-128-3.c test-case uses GOMP_OPENACC_DIM=-:-:128, but '-' is
not yet supported on trunk.  Use GOMP_OPENACC_DIM=::128 instead.

2019-01-07  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-3.c: Fix
	GOMP_OPENACC_DIM argument.

From-SVN: r267624
2019-01-07 08:09:49 +00:00
Tom de Vries
5c571497e1 [nvptx] Add vector_length 128 testcases
Add a couple of test-cases using vector length 128, while checking that we
override to vector length 32.

2019-01-03  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-1.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/vector-length-128-3.c: New test.

From-SVN: r267559
2019-01-03 15:08:46 +00:00
Jakub Jelinek
a554497024 Update copyright years.
From-SVN: r267494
2019-01-01 13:31:55 +01:00
Jakub Jelinek
3f27508ce4 gcc.c (process_command): Update copyright notice dates.
* gcc.c (process_command): Update copyright notice dates.
	* gcov-dump.c (print_version): Ditto.
	* gcov.c (print_version): Ditto.
	* gcov-tool.c (print_version): Ditto.
	* gengtype.c (create_file): Ditto.
	* doc/cpp.texi: Bump @copying's copyright year.
	* doc/cppinternals.texi: Ditto.
	* doc/gcc.texi: Ditto.
	* doc/gccint.texi: Ditto.
	* doc/gcov.texi: Ditto.
	* doc/install.texi: Ditto.
	* doc/invoke.texi: Ditto.
gcc/fortran/
	* gfortranspec.c (lang_specific_driver): Update copyright notice
	dates.
	* gfc-internals.texi: Bump @copying's copyright year.
	* gfortran.texi: Ditto.
	* intrinsic.texi: Ditto.
	* invoke.texi: Ditto.
gcc/go/
	* gccgo.texi: Bump @copyrights-go year.
gcc/ada/
 	* gnat_ugn.texi: Bump @copying's copyright year.
 	* gnat_rm.texi: Likewise.
gcc/d/
	* gdc.texi: Bump @copyrights-d year.
libitm/
	* libitm.texi: Bump @copying's copyright year.
libgomp/
	* libgomp.texi: Bump @copying's copyright year.
libquadmath/
	* libquadmath.texi: Bump @copying's copyright year.

From-SVN: r267492
2019-01-01 12:34:49 +01:00
Thomas Schwinge
59d5960cdb For libgomp OpenACC entry points, redefine the "device" argument to "flags"
... so that we're then able to use this for other flags in addition to
"GOACC_FLAG_HOST_FALLBACK".

	gcc/
	* omp-expand.c (expand_omp_target): Restructure OpenACC vs. OpenMP
	code paths.  Update for libgomp OpenACC entry points change.
	include/
	* gomp-constants.h (GOACC_FLAG_HOST_FALLBACK)
	(GOACC_FLAGS_MARSHAL_OP, GOACC_FLAGS_UNMARSHAL): Define.
	libgomp/
	* oacc-parallel.c (GOACC_parallel_keyed, GOACC_parallel)
	(GOACC_data_start, GOACC_enter_exit_data, GOACC_update)
	(GOACC_declare): Redefine the "device" argument to "flags".

From-SVN: r267448
2018-12-28 12:34:14 +01:00
Thomas Schwinge
a44c17909a Cleanup libgomp's coalesce chunk data structures
libgomp/
	* target.c (struct gomp_coalesce_chunk): New structure.
	(struct gomp_coalesce_buf): Update the chunks member to use that
	type.  Adjust all users.

Co-Authored-By: Cesar Philippidis <cesar@codesourcery.com>

From-SVN: r267446
2018-12-28 12:33:54 +01:00
Steven G. Kargl
b3c64ed0b0 aligned1.f03: Fix invalid code that now causes an error after r267415.
2018-12-27  Steven G. Kargl  <kargl@gcc.gnu.org>

	* libgomp.fortran/aligned1.f03: Fix invalid code that now causes
	an error after r267415.

From-SVN: r267436
2018-12-27 20:57:12 +00:00
Tom de Vries
a152954ea4 [nvptx] Commit passing pr85381-*.c test-cases
Add pr85381*.c test-cases that are already passing without the fix for PR85381.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/pr85381-2.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr85381-3.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr85381-4.c: New test.

From-SVN: r267268
2018-12-19 14:20:54 +00:00
Tom de Vries
49188cd1f2 [nvptx, libgomp] Move rtl-dump test-cases to libgomp
The goacc.exp test-cases nvptx-merged-loop.c and nvptx-sese-1.c are failing
during linking due to missing libgomp.spec.

Move them to the libgomp testsuite.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* gcc.dg/goacc/nvptx-merged-loop.c: Move to
	libgomp/testsuite/libgomp.oacc-c-c++-common.
	* gcc.dg/goacc/nvptx-sese-1.c: Same.

	* testsuite/lib/libgomp.exp: Add load_lib of scanoffloadrtl.exp.
	* testsuite/libgomp.oacc-c-c++-common/nvptx-merged-loop.c: Move from
	gcc/testsuite/gcc.dg/goacc.
	* testsuite/libgomp.oacc-c-c++-common/nvptx-sese-1.c: Same.

From-SVN: r267267
2018-12-19 14:20:44 +00:00
Thomas Schwinge
c759830b29 Missing changes from "Adjust copy/copyin/copyout/create for OpenACC 2.5"
Most of that patch's changes were already committed as part of r261813 "Update
OpenACC data clause semantics to the 2.5 behavior", but not all of them.

	libgomp/
	* oacc-mem.c (acc_present_or_create): Remove definition and change
	to alias of acc_create.
	(acc_present_or_copyin): Remove definition and change to alias of
	acc_copyin.
	* oacc-parallel.c (GOACC_enter_exit_data): Call acc_create instead
	of acc_present_or_create.
	* testsuite/libgomp.oacc-c-c++-common/data-already-1.c: Remove.
	* testsuite/libgomp.oacc-c-c++-common/data-already-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-5.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-6.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-7.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-8.c: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-1.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-2.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-3.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-4.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-5.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-6.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-7.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-8.f: Likewise.

Co-Authored-By: Chung-Lin Tang <cltang@codesourcery.com>

From-SVN: r267153
2018-12-14 21:43:12 +01:00
Thomas Schwinge
f847198ec3 [PR88495] An OpenACC async queue is always synchronized with itself
An OpenACC async queue is always synchronized with itself, so invocations like
"#pragma acc wait(0) async(0)", or "acc_wait_async (0, 0)" don't make a lot of
sense, but are still valid.

	libgomp/
	PR libgomp/88495
	* plugin/plugin-nvptx.c (nvptx_wait_async): Don't refuse
	"identical parameters".
	* testsuite/libgomp.oacc-c-c++-common/asyncwait-nop-1.c: Update.
	* testsuite/libgomp.oacc-c-c++-common/lib-80.c: Remove.

From-SVN: r267152
2018-12-14 21:43:02 +01:00
Thomas Schwinge
c8ab8aab9f [PR88484] OpenACC wait directive without wait argument but with async clause
We don't correctly handle "#pragma acc wait async (a)" for "a >= 0", handling
as a no-op whereas it should enqueue the appropriate wait operations on
"async (a)".

	libgomp/
	PR libgomp/88484
	* oacc-parallel.c (GOACC_wait): Correct handling for "async >= 0".
	* testsuite/libgomp.oacc-c-c++-common/asyncwait-nop-1.c: New file.

From-SVN: r267151
2018-12-14 21:42:50 +01:00
Thomas Schwinge
1404af62dc [PR88407] [OpenACC] Correctly handle unseen async-arguments
... which turn the operation into a no-op.

	libgomp/
	PR libgomp/88407
	* plugin/plugin-nvptx.c (nvptx_async_test, nvptx_wait)
	(nvptx_wait_async): Unseen async-argument is a no-op.
	* testsuite/libgomp.oacc-c-c++-common/async_queue-1.c: Update.
	* testsuite/libgomp.oacc-c-c++-common/data-2-lib.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-79.c: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-12.f90: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-71.c: Merge into...
	* testsuite/libgomp.oacc-c-c++-common/lib-69.c: ... this.  Update.
	* testsuite/libgomp.oacc-c-c++-common/lib-77.c: Merge into...
	* testsuite/libgomp.oacc-c-c++-common/lib-74.c: ... this.  Update

From-SVN: r267150
2018-12-14 21:42:40 +01:00
Thomas Schwinge
7de562eec2 Revise libgomp.oacc-c-c++-common/data-2-lib.c, libgomp.oacc-c-c++-common/data-2.c
These are meant to be functionally equivalent (but no longer are), just using
different means.  Also, use the OpenACC "*_async" functions recently added.

	libgomp/
	* testsuite/libgomp.oacc-c-c++-common/data-2-lib.c: Revise.
	* testsuite/libgomp.oacc-c-c++-common/data-2.c: Likewise.

From-SVN: r267149
2018-12-14 21:42:29 +01:00