[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

gcc/ChangeLog

 2017-05-12  Thomas Schwinge  <thomas@codesourcery.com>
 
+	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.
+
 	* omp-expand.c (expand_omp_target) <GF_OMP_TARGET_KIND_OACC_KERNELS>:
 	Set "oacc kernels" attribute.
 	* omp-general.c (oacc_set_fn_attrib): Remove is_kernel formal

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)

gcc/testsuite/ChangeLog

@@ -2,6 +2,32 @@
 
 	* 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.
+
+	* c-c++-common/goacc/classify-kernels-unparallelized.c: Adjust.
+	* c-c++-common/goacc/classify-kernels.c: Likewise.
 	* c-c++-common/goacc/classify-parallel.c: Likewise.
 	* c-c++-common/goacc/classify-routine.c: Likewise.
 	* gfortran.dg/goacc/classify-kernels-unparallelized.f95: Likewise.

gcc/testsuite/c-c++-common/goacc/classify-kernels-unparallelized.c

@@ -34,6 +34,6 @@ void KERNELS ()
 
 /* Check the offloaded function's classification and compute dimensions (will
    always be 1 x 1 x 1 for non-offloading compilation).
-   { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
+   { dg-final { scan-tree-dump-times "(?n)Function is unparallelized OpenACC kernels offload" 1 "oaccdevlow" } }
    { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
    { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */

gcc/testsuite/c-c++-common/goacc/classify-kernels.c

@@ -25,11 +25,11 @@ void KERNELS ()
 /* Check that exactly one OpenACC kernels construct is analyzed, and that it
    can be parallelized.
    { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
-   { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
+   { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
    { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check the offloaded function's classification and compute dimensions (will
    always be 1 x 1 x 1 for non-offloading compilation).
-   { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
+   { dg-final { scan-tree-dump-times "(?n)Function is parallelized OpenACC kernels offload" 1 "oaccdevlow" } }
    { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
-   { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */
+   { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } } */

gcc/testsuite/c-c++-common/goacc/kernels-counter-vars-function-scope.c

@@ -45,9 +45,8 @@ main (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-double-reduction-n.c

@@ -27,10 +27,9 @@ foo (unsigned int n)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 /* { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-double-reduction.c

@@ -27,10 +27,9 @@ foo (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 /* { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-loop-2.c

@@ -59,11 +59,10 @@ main (void)
 /* Check that only three loops are analyzed, and that all can be
    parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.1" 1 "optimized" } } */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.2" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 3 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-loop-3.c

@@ -39,9 +39,8 @@ main (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-loop-g.c

@@ -7,9 +7,8 @@
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-loop-mod-not-zero.c

@@ -43,9 +43,8 @@ main (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-loop-n.c

@@ -46,9 +46,8 @@ foo (COUNTERTYPE n)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-loop-nest.c

@@ -30,9 +30,8 @@ main (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-loop.c

@@ -46,9 +46,8 @@ main (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-one-counter-var.c

@@ -44,9 +44,8 @@ main (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*main._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/c-c++-common/goacc/kernels-reduction.c

@@ -26,9 +26,8 @@ foo (void)
 
 /* Check that only one loop is analyzed, and that it can be parallelized.  */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } } */
+/* { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } } */
 /* { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } } */
 
 /* Check that the loop has been split off into a function.  */
 /* { dg-final { scan-tree-dump-times "(?n);; Function .*foo.*._omp_fn.0" 1 "optimized" } } */
-
-/* { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } } */

gcc/testsuite/gfortran.dg/goacc/classify-kernels-unparallelized.f95

@@ -36,6 +36,6 @@ end program main
 
 ! Check the offloaded function's classification and compute dimensions (will
 ! always be 1 x 1 x 1 for non-offloading compilation).
-! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is unparallelized OpenACC kernels offload" 1 "oaccdevlow" } }
 ! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
 ! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } }

gcc/testsuite/gfortran.dg/goacc/classify-kernels.f95

@@ -27,11 +27,11 @@ end program main
 ! Check that exactly one OpenACC kernels construct is analyzed, and that it
 ! can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(0, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check the offloaded function's classification and compute dimensions (will
 ! always be 1 x 1 x 1 for non-offloading compilation).
-! { dg-final { scan-tree-dump-times "(?n)Function is OpenACC kernels offload" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)Function is parallelized OpenACC kernels offload" 1 "oaccdevlow" } }
 ! { dg-final { scan-tree-dump-times "(?n)Compute dimensions \\\[1, 1, 1\\\]" 1 "oaccdevlow" } }
-! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc function \\(1, 1, 1\\), oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "oaccdevlow" } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop-2.f95

@@ -34,11 +34,10 @@ end program main
 
 ! Check that only three loops are analyzed, and that all can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.1 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.2 " 1 "optimized" } }
-
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 3 "parloops1" } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop-data-2.f95

@@ -40,11 +40,10 @@ end program main
 
 ! Check that only three loops are analyzed, and that all can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.1 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.2 " 1 "optimized" } }
-
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 3 "parloops1" } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop-data-enter-exit-2.f95

@@ -40,11 +40,10 @@ end program main
 
 ! Check that only three loops are analyzed, and that all can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.1 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.2 " 1 "optimized" } }
-
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 3 "parloops1" } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop-data-enter-exit.f95

@@ -38,11 +38,10 @@ end program main
 
 ! Check that only three loops are analyzed, and that all can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.1 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.2 " 1 "optimized" } }
-
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 3 "parloops1" } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop-data-update.f95

@@ -38,10 +38,9 @@ end program main
 
 ! Check that only three loops are analyzed, and that all can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 2 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.1 " 1 "optimized" } }
-
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 2 "parloops1" } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop-data.f95

@@ -38,11 +38,10 @@ end program main
 
 ! Check that only three loops are analyzed, and that all can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 3 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.1 " 1 "optimized" } }
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.2 " 1 "optimized" } }
-
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 3 "parloops1" } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop-n.f95

@@ -32,10 +32,9 @@ end module test
 
 ! Check that only one loop is analyzed, and that it can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
+! TODO, PR70545.
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" { xfail *-*-* } } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function __test_MOD_foo._omp_fn.0 " 1 "optimized" } }
-
-! TODO, PR70545.
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" { xfail *-*-* } } }

gcc/testsuite/gfortran.dg/goacc/kernels-loop.f95

@@ -30,9 +30,8 @@ end program main
 
 ! Check that only one loop is analyzed, and that it can be parallelized.
 ! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops1" } }
+! { dg-final { scan-tree-dump-times "(?n)__attribute__\\(\\(oacc kernels parallelized, oacc function \\(, , \\), oacc kernels, omp target entrypoint\\)\\)" 1 "parloops1" } }
 ! { dg-final { scan-tree-dump-not "FAILED:" "parloops1" } }
 
 ! Check that the loop has been split off into a function.
 ! { dg-final { scan-tree-dump-times "(?n);; Function MAIN__._omp_fn.0 " 1 "optimized" } }
-
-! { dg-final { scan-tree-dump-times "(?n)oacc function \\(0," 1 "parloops1" } }

gcc/tree-parloops.c

@@ -2040,19 +2040,20 @@ create_parallel_loop (struct loop *loop, tree loop_fn, tree data,
   tree cvar, cvar_init, initvar, cvar_next, cvar_base, type;
   edge exit, nexit, guard, end, e;
 
-  /* Prepare the GIMPLE_OMP_PARALLEL statement.  */
   if (oacc_kernels_p)
     {
       gcc_checking_assert (lookup_attribute ("oacc kernels",
 					     DECL_ATTRIBUTES (cfun->decl)));
-
-      tree clause = build_omp_clause (loc, OMP_CLAUSE_NUM_GANGS);
-      OMP_CLAUSE_NUM_GANGS_EXPR (clause)
-	= build_int_cst (integer_type_node, n_threads);
-      oacc_set_fn_attrib (cfun->decl, clause, NULL);
+      /* Indicate to later processing that this is a parallelized OpenACC
+	 kernels construct.  */
+      DECL_ATTRIBUTES (cfun->decl)
+	= tree_cons (get_identifier ("oacc kernels parallelized"),
+		     NULL_TREE, DECL_ATTRIBUTES (cfun->decl));
     }
   else
     {
+      /* Prepare the GIMPLE_OMP_PARALLEL statement.  */
+
       basic_block bb = loop_preheader_edge (loop)->src;
       basic_block paral_bb = single_pred (bb);
       gsi = gsi_last_bb (paral_bb);
@@ -2154,7 +2155,8 @@ create_parallel_loop (struct loop *loop, tree loop_fn, tree data,
 
   /* Emit GIMPLE_OMP_FOR.  */
   if (oacc_kernels_p)
-    /* In combination with the NUM_GANGS on the parallel.  */
+    /* Parallelized OpenACC kernels constructs use gang parallelism.  See also
+       omp-offload.c:execute_oacc_device_lower.  */
     t = build_omp_clause (loc, OMP_CLAUSE_GANG);
   else
     {