[PR middle-end/69921] Use "oacc kernels parallelized" attribute for parallelized OpenACC kernels

	gcc/
	PR middle-end/69921
	* tree-parloops.c (create_parallel_loop): Set "oacc kernels
	parallelized" attribute for parallelized OpenACC kernels.
	* omp-offload.c (execute_oacc_device_lower): Use it.
	gcc/testsuite/
	* c-c++-common/goacc/classify-kernels-unparallelized.c: Adjust.
	* c-c++-common/goacc/classify-kernels.c: Likewise.
	* c-c++-common/goacc/kernels-counter-vars-function-scope.c:
	Likewise.
	* c-c++-common/goacc/kernels-double-reduction-n.c: Likewise.
	* c-c++-common/goacc/kernels-double-reduction.c: Likewise.
	* c-c++-common/goacc/kernels-loop-2.c: Likewise.
	* c-c++-common/goacc/kernels-loop-3.c: Likewise.
	* c-c++-common/goacc/kernels-loop-g.c: Likewise.
	* c-c++-common/goacc/kernels-loop-mod-not-zero.c: Likewise.
	* c-c++-common/goacc/kernels-loop-n.c: Likewise.
	* c-c++-common/goacc/kernels-loop-nest.c: Likewise.
	* c-c++-common/goacc/kernels-loop.c: Likewise.
	* c-c++-common/goacc/kernels-one-counter-var.c: Likewise.
	* c-c++-common/goacc/kernels-reduction.c: Likewise.
	* gfortran.dg/goacc/classify-kernels-unparallelized.f95: Likewise.
	* gfortran.dg/goacc/classify-kernels.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop-2.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop-data-2.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop-data-enter-exit-2.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop-data-enter-exit.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop-data-update.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop-data.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop-n.f95: Likewise.
	* gfortran.dg/goacc/kernels-loop.f95: Likewise.

From-SVN: r247957

1 files changed, 20 insertions, 4 deletions

diff --git a/gcc/omp-offload.c b/gcc/omp-offload.c
index d24f131..9372f9e 100644
--- a/gcc/omp-offload.c
+++ b/gcc/omp-offload.c
@@ -1444,6 +1444,13 @@ execute_oacc_device_lower ()
       flag_openacc_dims = (char *)&flag_openacc_dims;
     }
 
+  bool is_oacc_kernels
+    = (lookup_attribute ("oacc kernels",
+			 DECL_ATTRIBUTES (current_function_decl)) != NULL);
+  bool is_oacc_kernels_parallelized
+    = (lookup_attribute ("oacc kernels parallelized",
+			 DECL_ATTRIBUTES (current_function_decl)) != NULL);
+
   /* Discover, partition and process the loops.  */
   oacc_loop *loops = oacc_loop_discovery ();
   int fn_level = oacc_fn_attrib_level (attrs);
@@ -1453,17 +1460,26 @@ execute_oacc_device_lower ()
       if (fn_level >= 0)
 	fprintf (dump_file, "Function is OpenACC routine level %d\n",
 		 fn_level);
-      else if (lookup_attribute ("oacc kernels",
-				 DECL_ATTRIBUTES (current_function_decl)))
-	fprintf (dump_file, "Function is OpenACC kernels offload\n");
+      else if (is_oacc_kernels)
+	fprintf (dump_file, "Function is %s OpenACC kernels offload\n",
+		 (is_oacc_kernels_parallelized
+		  ? "parallelized" : "unparallelized"));
       else
 	fprintf (dump_file, "Function is OpenACC parallel offload\n");
     }
 
   unsigned outer_mask = fn_level >= 0 ? GOMP_DIM_MASK (fn_level) - 1 : 0;
   unsigned used_mask = oacc_loop_partition (loops, outer_mask);
-  int dims[GOMP_DIM_MAX];
+  /* OpenACC kernels constructs are special: they currently don't use the
+     generic oacc_loop infrastructure and attribute/dimension processing.  */
+  if (is_oacc_kernels && is_oacc_kernels_parallelized)
+    {
+      /* Parallelized OpenACC kernels constructs use gang parallelism.  See
+	 also tree-parloops.c:create_parallel_loop.  */
+      used_mask |= GOMP_DIM_MASK (GOMP_DIM_GANG);
+    }
 
+  int dims[GOMP_DIM_MAX];
   oacc_validate_dims (current_function_decl, attrs, dims, fn_level, used_mask);
 
   if (dump_file)