openmp: Add support for thread_limit clause on target

OpenMP 5.1 says that thread_limit clause can also appear on target,
and similarly to teams should affect the thread-limit-var ICV.
On combined target teams, the clause goes to both.

We actually passed thread_limit internally on target already before,
but only used it for gcn/ptx offloading to hint how many threads should be
created and for ptx didn't set thread_limit_var in that case.
Similarly for host fallback.
Also, I found that we weren't copying the args array that contains encoded
thread_limit and num_teams clause for target (etc.) for async target.

2021-11-15  Jakub Jelinek  <jakub@redhat.com>

gcc/
	* gimplify.c (optimize_target_teams): Only add OMP_CLAUSE_THREAD_LIMIT
	to OMP_TARGET_CLAUSES if it isn't there already.
gcc/c-family/
	* c-omp.c (c_omp_split_clauses) <case OMP_CLAUSE_THREAD_LIMIT>:
	Duplicate to both OMP_TARGET and OMP_TEAMS.
gcc/c/
	* c-parser.c (OMP_TARGET_CLAUSE_MASK): Add
	PRAGMA_OMP_CLAUSE_THREAD_LIMIT.
gcc/cp/
	* parser.c (OMP_TARGET_CLAUSE_MASK): Add
	PRAGMA_OMP_CLAUSE_THREAD_LIMIT.
libgomp/
	* task.c (gomp_create_target_task): Copy args array as well.
	* target.c (gomp_target_fallback): Add args argument.
	Set gomp_icv (true)->thread_limit_var if thread_limit is present.
	(GOMP_target): Adjust gomp_target_fallback caller.
	(GOMP_target_ext): Likewise.
	(gomp_target_task_fn): Likewise.
	* config/nvptx/team.c (gomp_nvptx_main): Set
	gomp_global_icv.thread_limit_var.
	* testsuite/libgomp.c-c++-common/thread-limit-1.c: New test.

1 files changed, 24 insertions, 2 deletions

diff --git a/libgomp/task.c b/libgomp/task.c
index feb4796..414ca6e 100644
--- a/libgomp/task.c
+++ b/libgomp/task.c
@@ -745,6 +745,7 @@ gomp_create_target_task (struct gomp_device_descr *devicep,
   size_t depend_size = 0;
   uintptr_t depend_cnt = 0;
   size_t tgt_align = 0, tgt_size = 0;
+  uintptr_t args_cnt = 0;
 
   if (depend != NULL)
     {
@@ -769,10 +770,22 @@ gomp_create_target_task (struct gomp_device_descr *devicep,
 	tgt_size += tgt_align - 1;
       else
 	tgt_size = 0;
+      if (args)
+	{
+	  void **cargs = args;
+	  while (*cargs)
+	    {
+	      intptr_t id = (intptr_t) *cargs++;
+	      if (id & GOMP_TARGET_ARG_SUBSEQUENT_PARAM)
+		cargs++;
+	    }
+	  args_cnt = cargs + 1 - args;
+	}
     }
 
   task = gomp_malloc (sizeof (*task) + depend_size
 		      + sizeof (*ttask)
+		      + args_cnt * sizeof (void *)
 		      + mapnum * (sizeof (void *) + sizeof (size_t)
 				  + sizeof (unsigned short))
 		      + tgt_size);
@@ -785,9 +798,18 @@ gomp_create_target_task (struct gomp_device_descr *devicep,
   ttask->devicep = devicep;
   ttask->fn = fn;
   ttask->mapnum = mapnum;
-  ttask->args = args;
   memcpy (ttask->hostaddrs, hostaddrs, mapnum * sizeof (void *));
-  ttask->sizes = (size_t *) &ttask->hostaddrs[mapnum];
+  if (args_cnt)
+    {
+      ttask->args = (void **) &ttask->hostaddrs[mapnum];
+      memcpy (ttask->args, args, args_cnt * sizeof (void *));
+      ttask->sizes = (size_t *) &ttask->args[args_cnt];
+    }
+  else
+    {
+      ttask->args = args;
+      ttask->sizes = (size_t *) &ttask->hostaddrs[mapnum];
+    }
   memcpy (ttask->sizes, sizes, mapnum * sizeof (size_t));
   ttask->kinds = (unsigned short *) &ttask->sizes[mapnum];
   memcpy (ttask->kinds, kinds, mapnum * sizeof (unsigned short));