OpenE2K/gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
5afa955f12
gcc/libgomp/testsuite/libgomp.c/doacross-3.c
Jakub Jelinek e460634820 omp-low.c (lower_omp_ordered): Add argument to GOMP_SMD_ORDERED_* internal calls - 0 if... 
gcc/
2015-11-14  Jakub Jelinek  <jakub@redhat.com>

	* omp-low.c (lower_omp_ordered): Add argument to GOMP_SMD_ORDERED_*
	internal calls - 0 if ordered simd and 1 for ordered threads simd.
	* tree-vectorizer.c (adjust_simduid_builtins): If GOMP_SIMD_ORDERED_*
	argument is 1, replace it with GOMP_ordered_* call instead of removing
	it.
gcc/c/
2015-11-14  Jakub Jelinek  <jakub@redhat.com>

	* c-typeck.c (c_finish_omp_clauses): Don't mark
	GOMP_MAP_FIRSTPRIVATE_POINTER decls addressable.
gcc/cp/
2015-11-14  Jakub Jelinek  <jakub@redhat.com>

	* semantics.c (finish_omp_clauses): Don't mark
	GOMP_MAP_FIRSTPRIVATE_POINTER decls addressable.
libgomp/
2015-11-14  Jakub Jelinek  <jakub@redhat.com>
	    Aldy Hernandez  <aldyh@redhat.com>
	    Ilya Verbin  <ilya.verbin@intel.com>

	* ordered.c (gomp_doacross_init, GOMP_doacross_post,
	GOMP_doacross_wait, gomp_doacross_ull_init, GOMP_doacross_ull_post,
	GOMP_doacross_ull_wait): For GFS_GUIDED don't divide number of
	iterators or IV by chunk size.
	* parallel.c (gomp_resolve_num_threads): Don't assume that
	if thr->ts.team is non-NULL, then pool must be non-NULL.
	* libgomp-plugin.h (GOMP_PLUGIN_target_task_completion): Declare.
	* libgomp.map (GOMP_PLUGIN_1.1): New symbol version, export
	GOMP_PLUGIN_target_task_completion.
	* Makefile.am (libgomp_la_SOURCES): Add priority_queue.c.
	* Makefile.in: Regenerate.
	* libgomp.h: Shuffle prototypes and forward definitions around so
	priority queues can be defined.
	(enum gomp_task_kind): Add GOMP_TASK_ASYNC_RUNNING.
	(enum gomp_target_task_state): New enum.
	(struct gomp_target_task): Add state, tgt, task and team fields.
	(gomp_create_target_task): Change return type to bool, add
	state argument.
	(gomp_target_task_fn): Change return type to bool.
	(struct gomp_device_descr): Add async_run_func.
	(struct gomp_task): Remove children, next_child, prev_child,
	next_queue, prev_queue, next_taskgroup, prev_taskgroup.
	Add pnode field.
	(struct gomp_taskgroup): Remove children.
	Add taskgroup_queue.
	(struct gomp_team): Change task_queue type to a priority queue.
	(splay_compare): Define inline.
	(priority_queue_offset): New.
	(priority_node_to_task): New.
	(task_to_priority_node): New.
	* oacc-mem.c: Do not include splay-tree.h.
	* priority_queue.c: New file.
	* priority_queue.h: New file.
	* splay-tree.c: Do not include splay-tree.h.
	(splay_tree_foreach_internal): New.
	(splay_tree_foreach): New.
	* splay-tree.h: Become re-entrant if splay_tree_prefix is defined.
	(splay_tree_callback): Define typedef.
	* target.c (splay_compare): Move to libgomp.h.
	(GOMP_target): Don't adjust *thr in any way around running offloaded
	task.
	(GOMP_target_ext): Likewise.  Handle target nowait.
	(GOMP_target_update_ext, GOMP_target_enter_exit_data): Check
	return value from gomp_create_target_task, if false, fallthrough
	as if no dependencies exist.
	(gomp_target_task_fn): Change return type to bool, return true
	if the task should have another part scheduled later.  Handle
	target nowait.
	(gomp_load_plugin_for_device): Initialize async_run.
	* task.c (gomp_init_task): Initialize children_queue.
	(gomp_clear_parent_in_list): New.
	(gomp_clear_parent_in_tree): New.
	(gomp_clear_parent): Handle priorities.
	(GOMP_task): Likewise.
	(priority_queue_move_task_first,
	gomp_target_task_completion, GOMP_PLUGIN_target_task_completion):
	New functions.
	(gomp_create_target_task): Use priority queues.  Change return type
	to bool, add state argument, return false if for async
	{{enter,exit} data,update} constructs no dependencies need to be
	waited for, handle target nowait.  Set task->fn to NULL instead of
	gomp_target_task_fn.
	(verify_children_queue): Remove.
	(priority_list_upgrade_task): New.
	(priority_queue_upgrade_task): New.
	(verify_task_queue): Remove.
	(priority_list_downgrade_task): New.
	(priority_queue_downgrade_task): New.
	(gomp_task_run_pre): Use priority queues.
	Abstract code out to priority_queue_downgrade_task.
	(gomp_task_run_post_handle_dependers): Use priority queues.
	(gomp_task_run_post_remove_parent): Likewise.
	(gomp_task_run_post_remove_taskgroup): Likewise.
	(gomp_barrier_handle_tasks): Likewise.  Handle target nowait target
	tasks specially.
	(GOMP_taskwait): Likewise.
	(gomp_task_maybe_wait_for_dependencies): Likewise.  Abstract code to
	priority-queue_upgrade_task.
	(GOMP_taskgroup_start): Use priority queues.
	(GOMP_taskgroup_end): Likewise.  Handle target nowait target tasks
	specially.  If taskgroup is NULL, and thr->ts.level is 0, act as a
	barrier.
	* taskloop.c (GOMP_taskloop): Handle priorities.
	* team.c (gomp_new_team): Call priority_queue_init.
	(free_team): Call priority_queue_free.
	(gomp_free_thread): Call gomp_team_end if thr->ts.team is artificial
	team created for target nowait in implicit parallel region.
	(gomp_team_start): For nested check, test thr->ts.level instead of
	thr->ts.team != NULL.
	* testsuite/libgomp.c/doacross-3.c: New test.
	* testsuite/libgomp.c/ordered-5.c: New test.
	* testsuite/libgomp.c/priority.c: New test.
	* testsuite/libgomp.c/target-31.c: New test.
	* testsuite/libgomp.c/target-32.c: New test.
	* testsuite/libgomp.c/target-33.c: New test.
	* testsuite/libgomp.c/target-34.c: New test.
liboffloadmic/
2015-11-14  Ilya Verbin  <ilya.verbin@intel.com>

	* runtime/offload_host.cpp (task_completion_callback): New
	variable.
	(offload_proxy_task_completed_ooo): Call task_completion_callback.
	(__offload_register_task_callback): New function.
	* runtime/offload_host.h (__offload_register_task_callback): New
	declaration.
	* plugin/libgomp-plugin-intelmic.cpp (offload): Add async_data
	argument, handle async offloading.
	(register_main_image): Call register_main_image.
	(GOMP_OFFLOAD_init_device, get_target_table, GOMP_OFFLOAD_alloc,
	GOMP_OFFLOAD_free, GOMP_OFFLOAD_host2dev, GOMP_OFFLOAD_dev2host,
	GOMP_OFFLOAD_dev2dev) Adjust offload callers.
	(GOMP_OFFLOAD_async_run): New function.
	(GOMP_OFFLOAD_run): Implement using GOMP_OFFLOAD_async_run.

From-SVN: r230381
2015-11-14 19:42:13 +01:00

226 lines
5.6 KiB
C
Raw Blame History

extern void abort (void);
#define N 256
int a[N], b[N / 16][8][4], c[N / 32][8][8], g[N / 16][8][6];
volatile int d, e;
volatile unsigned long long f;
int
main ()
{
unsigned long long i;
int j, k, l, m;
#pragma omp parallel private (l)
{
#pragma omp for schedule(guided, 3) ordered (1) nowait
for (i = 1; i < N + f; i++)
{
#pragma omp atomic write
a[i] = 1;
#pragma omp ordered depend(sink: i - 1)
if (i > 1)
{
#pragma omp atomic read
l = a[i - 1];
if (l < 2)
abort ();
}
#pragma omp atomic write
a[i] = 2;
if (i < N - 1)
{
#pragma omp atomic read
l = a[i + 1];
if (l == 3)
abort ();
}
#pragma omp ordered depend(source)
#pragma omp atomic write
a[i] = 3;
}
#pragma omp for schedule(guided) ordered (3) nowait
for (i = 3; i < N / 16 - 1 + f; i++)
for (j = 0; j < 8; j += 2)
for (k = 1; k <= 3; k++)
{
#pragma omp atomic write
b[i][j][k] = 1;
#pragma omp ordered depend(sink: i, j - 2, k - 1) \
depend(sink: i - 2, j - 2, k + 1)
#pragma omp ordered depend(sink: i - 3, j + 2, k - 2)
if (j >= 2 && k > 1)
{
#pragma omp atomic read
l = b[i][j - 2][k - 1];
if (l < 2)
abort ();
}
#pragma omp atomic write
b[i][j][k] = 2;
if (i >= 5 && j >= 2 && k < 3)
{
#pragma omp atomic read
l = b[i - 2][j - 2][k + 1];
if (l < 2)
abort ();
}
if (i >= 6 && j < N / 16 - 3 && k == 3)
{
#pragma omp atomic read
l = b[i - 3][j + 2][k - 2];
if (l < 2)
abort ();
}
#pragma omp ordered depend(source)
#pragma omp atomic write
b[i][j][k] = 3;
}
#define A(n) int n;
#define B(n) A(n##0) A(n##1) A(n##2) A(n##3)
#define C(n) B(n##0) B(n##1) B(n##2) B(n##3)
#define D(n) C(n##0) C(n##1) C(n##2) C(n##3)
D(m)
#undef A
#pragma omp for collapse (2) ordered(61) schedule(guided, 15)
for (i = 2; i < N / 32 + f; i++)
for (j = 7; j > 1; j--)
for (k = 6; k >= 0; k -= 2)
#define A(n) for (n = 4; n < 5; n++)
D(m)
#undef A
{
#pragma omp atomic write
c[i][j][k] = 1;
#define A(n) ,n
#define E(n) C(n##0) C(n##1) C(n##2) B(n##30) B(n##31) A(n##320) A(n##321)
#pragma omp ordered depend (sink: i, j, k + 2 E(m)) \
depend (sink:i - 2, j + 1, k - 4 E(m)) \
depend(sink: i - 1, j - 2, k - 2 E(m))
if (k <= 4)
{
l = c[i][j][k + 2];
if (l < 2)
abort ();
}
#pragma omp atomic write
c[i][j][k] = 2;
if (i >= 4 && j < 7 && k >= 4)
{
l = c[i - 2][j + 1][k - 4];
if (l < 2)
abort ();
}
if (i >= 3 && j >= 4 && k >= 2)
{
l = c[i - 1][j - 2][k - 2];
if (l < 2)
abort ();
}
#pragma omp ordered depend (source)
#pragma omp atomic write
c[i][j][k] = 3;
}
#pragma omp for schedule(guided, 5) ordered (3) nowait
for (j = 0; j < N / 16 - 1; j++)
for (k = 0; k < 8; k += 2)
for (i = 3; i <= 5 + f; i++)
{
#pragma omp atomic write
g[j][k][i] = 1;
#pragma omp ordered depend(sink: j, k - 2, i - 1) \
depend(sink: j - 2, k - 2, i + 1)
#pragma omp ordered depend(sink: j - 3, k + 2, i - 2)
if (k >= 2 && i > 3)
{
#pragma omp atomic read
l = g[j][k - 2][i - 1];
if (l < 2)
abort ();
}
#pragma omp atomic write
g[j][k][i] = 2;
if (j >= 2 && k >= 2 && i < 5)
{
#pragma omp atomic read
l = g[j - 2][k - 2][i + 1];
if (l < 2)
abort ();
}
if (j >= 3 && k < N / 16 - 3 && i == 5)
{
#pragma omp atomic read
l = g[j - 3][k + 2][i - 2];
if (l < 2)
abort ();
}
#pragma omp ordered depend(source)
#pragma omp atomic write
g[j][k][i] = 3;
}
#pragma omp for collapse(2) ordered(4) lastprivate (i, j, k)
for (i = 2; i < f + 3; i++)
for (j = d + 1; j >= 0; j--)
for (k = 0; k < d; k++)
for (l = 0; l < d + 2; l++)
{
#pragma omp ordered depend (source)
#pragma omp ordered depend (sink:i - 2, j + 2, k - 2, l)
if (!e)
abort ();
}
#pragma omp single
{
if (i != 3 || j != -1 || k != 0)
abort ();
i = 8; j = 9; k = 10;
}
#pragma omp for collapse(2) ordered(4) lastprivate (i, j, k, m)
for (i = 2; i < f + 3; i++)
for (j = d + 1; j >= 0; j--)
for (k = 0; k < d + 2; k++)
for (m = 0; m < d; m++)
{
#pragma omp ordered depend (source)
#pragma omp ordered depend (sink:i - 2, j + 2, k - 2, m)
abort ();
}
#pragma omp single
if (i != 3 || j != -1 || k != 2 || m != 0)
abort ();
#pragma omp for collapse(2) ordered(4) nowait
for (i = 2; i < f + 3; i++)
for (j = d; j > 0; j--)
for (k = 0; k < d + 2; k++)
for (l = 0; l < d + 4; l++)
{
#pragma omp ordered depend (source)
#pragma omp ordered depend (sink:i - 2, j + 2, k - 2, l)
if (!e)
abort ();
}
#pragma omp for nowait
for (i = 0; i < N; i++)
if (a[i] != 3 * (i >= 1))
abort ();
#pragma omp for collapse(2) private(k) nowait
for (i = 0; i < N / 16; i++)
for (j = 0; j < 8; j++)
for (k = 0; k < 4; k++)
if (b[i][j][k] != 3 * (i >= 3 && i < N / 16 - 1 && (j & 1) == 0 && k >= 1))
abort ();
#pragma omp for collapse(3) nowait
for (i = 0; i < N / 32; i++)
for (j = 0; j < 8; j++)
for (k = 0; k < 8; k++)
if (c[i][j][k] != 3 * (i >= 2 && j >= 2 && (k & 1) == 0))
abort ();
#pragma omp for collapse(2) private(k) nowait
for (i = 0; i < N / 16; i++)
for (j = 0; j < 8; j++)
for (k = 0; k < 6; k++)
if (g[i][j][k] != 3 * (i < N / 16 - 1 && (j & 1) == 0 && k >= 3))
abort ();
}
return 0;
}
Reference in New Issue View Git Blame Copy Permalink