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.

4 files changed, 33 insertions, 5 deletions

diff --git a/gcc/c-family/c-omp.c b/gcc/c-family/c-omp.c
index fad0606..3f84fd1 100644
--- a/gcc/c-family/c-omp.c
+++ b/gcc/c-family/c-omp.c
@@ -1867,7 +1867,6 @@ c_omp_split_clauses (location_t loc, enum tree_code code,
 	  s = C_OMP_CLAUSE_SPLIT_TARGET;
 	  break;
 	case OMP_CLAUSE_NUM_TEAMS:
-	case OMP_CLAUSE_THREAD_LIMIT:
 	  s = C_OMP_CLAUSE_SPLIT_TEAMS;
 	  break;
 	case OMP_CLAUSE_DIST_SCHEDULE:
@@ -2531,6 +2530,30 @@ c_omp_split_clauses (location_t loc, enum tree_code code,
 	  else
 	    s = C_OMP_CLAUSE_SPLIT_FOR;
 	  break;
+	  /* thread_limit is allowed on target and teams.  Distribute it
+	     to all.  */
+	case OMP_CLAUSE_THREAD_LIMIT:
+	  if ((mask & (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_MAP))
+	      != 0)
+	    {
+	      if ((mask & (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_NUM_TEAMS))
+		  != 0)
+		{
+		  c = build_omp_clause (OMP_CLAUSE_LOCATION (clauses),
+					OMP_CLAUSE_THREAD_LIMIT);
+		  OMP_CLAUSE_THREAD_LIMIT_EXPR (c)
+		    = OMP_CLAUSE_THREAD_LIMIT_EXPR (clauses);
+		  OMP_CLAUSE_CHAIN (c) = cclauses[C_OMP_CLAUSE_SPLIT_TARGET];
+		  cclauses[C_OMP_CLAUSE_SPLIT_TARGET] = c;
+		}
+	      else
+		{
+		  s = C_OMP_CLAUSE_SPLIT_TARGET;
+		  break;
+		}
+	    }
+	  s = C_OMP_CLAUSE_SPLIT_TEAMS;
+	  break;
 	/* Allocate clause is allowed on target, teams, distribute, parallel,
 	   for, sections and taskloop.  Distribute it to all.  */
 	case OMP_CLAUSE_ALLOCATE:
diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c
index 3c9f587..83e837c 100644
--- a/gcc/c/c-parser.c
+++ b/gcc/c/c-parser.c
@@ -20963,6 +20963,7 @@ c_parser_omp_target_exit_data (location_t loc, c_parser *parser,
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_ALLOCATE)	\
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_DEFAULTMAP)	\
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_IN_REDUCTION)	\
+	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_THREAD_LIMIT)	\
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_IS_DEVICE_PTR))
 
 static bool
diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index adfd3c1..e86e2b5 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -44015,6 +44015,7 @@ cp_parser_omp_target_update (cp_parser *parser, cp_token *pragma_tok,
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_DEFAULTMAP)	\
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_ALLOCATE)	\
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_IN_REDUCTION)	\
+	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_THREAD_LIMIT)	\
 	| (OMP_CLAUSE_MASK_1 << PRAGMA_OMP_CLAUSE_IS_DEVICE_PTR))
 
 static bool
diff --git a/gcc/gimplify.c b/gcc/gimplify.c
index 4e022d8..1602a62 100644
--- a/gcc/gimplify.c
+++ b/gcc/gimplify.c
@@ -13637,10 +13637,13 @@ optimize_target_teams (tree target, gimple_seq *pre_p)
 	if (!DECL_P (expr) && TREE_CODE (expr) != TARGET_EXPR)
 	  OMP_CLAUSE_OPERAND (c, 0) = *p;
       }
-  c = build_omp_clause (thread_limit_loc, OMP_CLAUSE_THREAD_LIMIT);
-  OMP_CLAUSE_THREAD_LIMIT_EXPR (c) = thread_limit;
-  OMP_CLAUSE_CHAIN (c) = OMP_TARGET_CLAUSES (target);
-  OMP_TARGET_CLAUSES (target) = c;
+  if (!omp_find_clause (OMP_TARGET_CLAUSES (target), OMP_CLAUSE_THREAD_LIMIT))
+    {
+      c = build_omp_clause (thread_limit_loc, OMP_CLAUSE_THREAD_LIMIT);
+      OMP_CLAUSE_THREAD_LIMIT_EXPR (c) = thread_limit;
+      OMP_CLAUSE_CHAIN (c) = OMP_TARGET_CLAUSES (target);
+      OMP_TARGET_CLAUSES (target) = c;
+    }
   c = build_omp_clause (num_teams_loc, OMP_CLAUSE_NUM_TEAMS);
   OMP_CLAUSE_NUM_TEAMS_UPPER_EXPR (c) = num_teams_upper;
   OMP_CLAUSE_NUM_TEAMS_LOWER_EXPR (c) = num_teams_lower;